Asista al Simposio Mujeres en ML el 7 de diciembre Regístrese ahora

Dialecto 'tfl'

Organiza tus páginas con colecciones Guarda y categoriza el contenido según tus preferencias.

El dialecto de TensorFlow Lite.

Este dialecto se asigna a las operaciones de TensorFlow Lite.

Invariantes:

  • Todos los valores son del tipo Tensor (en particular, los escalares se representan usando tensores de dimensión cero);

Definición de operación

tfl.abs (::mlir::TFL::AbsOp)

Operador de valor absoluto

Dado un tensor x , esta operación devuelve un tensor que contiene el valor absoluto de cada elemento en x . Por ejemplo, si x es un elemento de entrada e y es un elemento de salida, esta operación calcula \(y = |x|\).

Rasgos: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
x tensor de entero sin signo de 16 bits o entero sin signo de 32 bits o flotante de 32 bits o tipo QI8 o valores de tipo QI16

Resultados:

Resultado Descripción
y tensor de entero sin signo de 16 bits o entero sin signo de 32 bits o flotante de 32 bits o tipo QI8 o valores de tipo QI16

tfl.add_n (::mlir::TFL::AddNOp)

operador add_n

Agrega todos los tensores de entrada por elementos.

Rasgos: SiempreSpeculatableImplRasgo, Conmutativo

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
inputs tensor de cualquier tipo de valores

Resultados:

Resultado Descripción
sum tensor de valores flotantes de 32 bits o enteros sin signo de 32 bits

tfl.add (::mlir::TFL::AddOp)

Operador de suma

Operación de suma por elementos.

Rasgos: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Conmutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT

operandos:

operando Descripción
lhs tensor de 32 bits flotante o entero sin signo de 32 bits o entero sin signo de 64 bits o valores de tipo QI8 o tipo QUI8 o tipo QI16
rhs tensor de 32 bits flotante o entero sin signo de 32 bits o entero sin signo de 64 bits o valores de tipo QI8 o tipo QUI8 o tipo QI16

Resultados:

Resultado Descripción
output tensor de 32 bits flotante o entero sin signo de 32 bits o entero sin signo de 64 bits o valores de tipo QI8 o tipo QUI8 o tipo QI16

tfl.arg_max (::mlir::TFL::ArgMaxOp)

Operador ArgMax

Devuelve el índice con el mayor valor entre las dimensiones de un tensor.

Rasgos: SiempreSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
output_type ::mlir::Atributo atributo derivado

operandos:

operando Descripción
input tensor de entero sin signo de 1 bit o flotante de 32 bits o entero sin signo de 32 bits o entero sin signo de 8 bits o entero sin signo de 8 bits o tipo QI8 o valores de tipo QUI8
dim tensor de valores enteros sin signo de 32/64 bits

Resultados:

Resultado Descripción
output tensor de valores enteros sin signo de 32/64 bits

tfl.arg_min (::mlir::TFL::ArgMinOp)

Operador ArgMin

Devuelve el índice con el valor más pequeño entre las dimensiones de un tensor. a = [1, 10, 26.9, 2.8, 166.32, 62.3] b = tf.math.argmin(entrada = a) c = tf.keras.backend.eval(b)

Rasgos: SiempreSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
output_type ::mlir::Atributo atributo derivado

operandos:

operando Descripción
input tensor de entero sin signo de 1 bit o flotante de 32 bits o entero sin signo de 32 bits o entero sin signo de 8 bits o entero sin signo de 8 bits o tipo QI8 o valores de tipo QUI8
dim tensor de valores enteros sin signo de 32/64 bits

Resultados:

Resultado Descripción
output tensor de valores enteros sin signo de 32/64 bits

tfl.assign_variable (::mlir::TFL::AssignVariableOp)

Asigna un nuevo valor a una variable.

Se garantiza que cualquier ReadVariableOp con una dependencia de control en esta operación devolverá este valor o un valor posterior más nuevo de la variable.

Interfaces: TflRuntimeVerifyOpInterface

operandos:

operando Descripción
resource_id tensor de valores de recursos
value tensor de flotante de 32 bits o flotante de 64 bits o entero sin signo de 1 bit o entero sin signo de 8 bits o entero sin signo de 8 bits o tipo QI8 o tipo QUI8 o entero sin signo de 32 bits o entero sin signo de 64 bits o tipo QI16 o tipo complejo con elementos flotantes de 32 bits o tipo complejo con valores de elementos flotantes de 64 bits

tfl.atan2 (::mlir::TFL::Atan2Op)

Operación Atan2

La operación "atan2" calcula la arcotangente de y/x por elementos, respetando los signos de los argumentos.

Rasgos: AlwaysSpeculatableImplTrait, SameOperandsAndResultElementType, SameOperandsAndResultShape

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
y tensor de valores flotantes de 32 bits o flotantes de 64 bits
x tensor de valores flotantes de 32 bits o flotantes de 64 bits

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits o flotantes de 64 bits

tfl.average_pool_2d (::mlir::TFL::AveragePool2DOp)

Operador Average_pool_2d

Realiza una operación de agrupación promedio en la entrada.

Rasgos: SiempreSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
filter_height ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
filter_width ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
padding ::mlir::StringAttr atributo de cadena cuyo valor es MISMO o VÁLIDO
stride_h ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
stride_w ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT

operandos:

operando Descripción
input tensor de valores flotantes de 32 bits o tipo QI8 o tipo QUI8 o tipo QI16

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits o tipo QI8 o tipo QUI8 o tipo QI16

tfl.basic_lstm (::mlir::TFL::BasicLSTMOp)

El operador lstm básico

Operador de celda LSTM básico.

Rasgos: SiempreSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT
cell_clip ::mlir::FloatAttr Atributo flotante de 32 bits cuyo valor no es negativo
proj_clip ::mlir::FloatAttr Atributo flotante de 32 bits cuyo valor no es negativo
kernel_type ::mlir::TFL::LSTMKernelTypeAttr lstm_kernel_type cuyo valor es mlir::TFL::LSTMKernelType::BASIC

operandos:

operando Descripción
data_input tensor de valores de tipo float o QUI8 de 32 bits
prev_activ_input tensor de valores de tipo float o QUI8 de 32 bits
weights_input tensor de valores de tipo float o QUI8 de 32 bits
biases_input tensor de valores flotantes de 32 bits o tipo QI32
prev_state_input tensor de valores tipo float o QI16 de 32 bits

Resultados:

Resultado Descripción
activ_output Tensor 2D de cualquier tipo de valores
state_output Tensor 2D de cualquier tipo de valores
concat_temp Tensor 2D de cualquier tipo de valores
activ_temp Tensor 2D de cualquier tipo de valores

tfl.batch_matmul (::mlir::TFL::BatchMatMulOp)

Operador de multiplicación de matriz por lotes

Realiza una multiplicación de matriz por lotes en las entradas. Sigue las convenciones de TensorFlow BatchMatMulV2, con soporte para dimensiones desconocidas en las dimensiones del lote y la transmisión.

Inputs:
  `inputs[0]`: required: input LHS
  `inputs[1]`: required: input RHS
  `adjoint_lhs`: optional: Transpose LHS (default false)
  `adjoint_lhs`: optional: Transpose LHS (default false)

Rasgos: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
adj_x ::mlir::BoolAttr atributo booleano
adj_y ::mlir::BoolAttr atributo booleano
asymmetric_quantize_inputs ::mlir::BoolAttr atributo booleano

operandos:

operando Descripción
x tensor de 32 bits flotante o tipo QI8 o tipo QI16 o valores enteros sin signo de 8 bits
y tensor de 32 bits flotante o tipo QI8 o tipo QI16 o valores enteros sin signo de 8 bits

Resultados:

Resultado Descripción
output tensor de 32 bits flotante o tipo QI8 o tipo QI16 o valores enteros sin signo de 32 bits

tfl.batch_to_space_nd (::mlir::TFL::BatchToSpaceNdOp)

Operador BatchToSpaceNd

Esta operación transforma la dimensión 0 del "lote" en dimensiones espaciales.

Rasgos: SiempreSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
input tensor de 32 bits flotante o entero sin signo de 8 bits o entero sin signo de 32 bits o entero sin signo de 64 bits o entero sin signo de 8 bits o tipo QI8 o valores de tipo QUI8
block_shape tensor de valores enteros sin signo de 32 bits
indices tensor de valores enteros sin signo de 32 bits

Resultados:

Resultado Descripción
output tensor de flotante de 32 bits o entero sin signo de 16 bits o entero sin signo de 32 bits o entero sin signo de 64 bits o entero sin signo de 8 bits o tipo QI8 o valores de tipo QUI8

tfl.bidirectional_sequence_lstm (::mlir::TFL::BidireccionalSecuenciaLSTMOp)

Operador lstm de secuencia bidireccional

El lstm bidireccional es esencialmente dos lstms, uno hacia adelante y el otro hacia atrás. Y la salida es la concatenación de los dos lstms.

Rasgos: resultado cuantificable

Interfaces: DynamicRangeQuantizedOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Atributos:

Atributo Tipo MLIR Descripción
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT
cell_clip ::mlir::FloatAttr Atributo flotante de 32 bits cuyo valor no es negativo
proj_clip ::mlir::FloatAttr Atributo flotante de 32 bits cuyo valor no es negativo
merge_outputs ::mlir::BoolAttr atributo booleano
time_major ::mlir::BoolAttr atributo booleano
asymmetric_quantize_inputs ::mlir::BoolAttr atributo booleano

operandos:

operando Descripción
input tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
fw_input_to_input_weights tensor de cualquier tipo valores o ningún tipo
fw_input_to_forget_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
fw_input_to_cell_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
fw_input_to_output_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
fw_recurrent_to_input_weights tensor de cualquier tipo valores o ningún tipo
fw_recurrent_to_forget_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
fw_recurrent_to_cell_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
fw_recurrent_to_output_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
fw_cell_to_input_weights tensor de cualquier tipo valores o ningún tipo
fw_cell_to_forget_weights tensor de cualquier tipo valores o ningún tipo
fw_cell_to_output_weights tensor de cualquier tipo valores o ningún tipo
fw_input_gate_bias tensor de cualquier tipo valores o ningún tipo
fw_forget_gate_bias tensor de valores flotantes de 32 bits
fw_cell_bias tensor de valores flotantes de 32 bits
fw_output_gate_bias tensor de valores flotantes de 32 bits
fw_projection_weights tensor de cualquier tipo valores o ningún tipo
fw_projection_bias tensor de cualquier tipo valores o ningún tipo
bw_input_to_input_weights tensor de cualquier tipo valores o ningún tipo
bw_input_to_forget_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
bw_input_to_cell_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
bw_input_to_output_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
bw_recurrent_to_input_weights tensor de cualquier tipo valores o ningún tipo
bw_recurrent_to_forget_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
bw_recurrent_to_cell_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
bw_recurrent_to_output_weights tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits
bw_cell_to_input_weights tensor de cualquier tipo valores o ningún tipo
bw_cell_to_forget_weights tensor de cualquier tipo valores o ningún tipo
bw_cell_to_output_weights tensor de cualquier tipo valores o ningún tipo
bw_input_gate_bias tensor de cualquier tipo valores o ningún tipo
bw_forget_gate_bias tensor de valores flotantes de 32 bits
bw_cell_bias tensor de valores flotantes de 32 bits
bw_output_gate_bias tensor de valores flotantes de 32 bits
bw_projection_weights tensor de cualquier tipo valores o ningún tipo
bw_projection_bias tensor de cualquier tipo valores o ningún tipo
fw_input_activation_state tensor de estado
fw_input_cell_state tensor de estado
bw_input_activation_state tensor de estado
bw_input_cell_state tensor de estado
aux_input tensor de cualquier tipo valores o ningún tipo
fw_aux_input_to_input_weights tensor de cualquier tipo valores o ningún tipo
fw_aux_input_to_forget_weights tensor de cualquier tipo valores o ningún tipo
fw_aux_input_to_cell_weights tensor de cualquier tipo valores o ningún tipo
fw_aux_input_to_output_weights tensor de cualquier tipo valores o ningún tipo
bw_aux_input_to_input_weights tensor de cualquier tipo valores o ningún tipo
bw_aux_input_to_forget_weights tensor de cualquier tipo valores o ningún tipo
bw_aux_input_to_cell_weights tensor de cualquier tipo valores o ningún tipo
bw_aux_input_to_output_weights tensor de cualquier tipo valores o ningún tipo

Resultados:

Resultado Descripción
fw_output tensor de cualquier tipo de valores
bw_output tensor de cualquier tipo de valores

tfl.broadcast_args (::mlir::TFL::BroadcastArgsOp)

Devuelve la forma de s0 op s1 con transmisión.

Dados s0 y s1 , tensores que representan formas, calcule r0 , la forma transmitida. s0 , s1 y r0 son todos vectores enteros.

Rasgos: SiempreSpeculatableImplTrait

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
s0 tensor de valores enteros sin signo de 32/64 bits
s1 tensor de valores enteros sin signo de 32/64 bits

Resultados:

Resultado Descripción
r0 tensor de valores enteros sin signo de 32/64 bits

tfl.broadcast_to (::mlir::TFL::BroadcastToOp)

Transmita una matriz para una forma compatible.

La transmisión es el proceso de hacer que las matrices tengan formas compatibles para las operaciones aritméticas. Dos formas son compatibles si para cada par de dimensiones son iguales o una de ellas es uno. Al intentar transmitir un tensor a una forma, comienza con las dimensiones finales y avanza.

Por ejemplo,

x = tf.constant([1, 2, 3]) y = tf.broadcast_to(x, [3, 3]) print(y) tf.Tensor( [[1 2 3] [1 2 3] [1 2 3]], forma=(3, 3), dtipo=int32)

En el ejemplo anterior, el tensor de entrada con la forma de [1, 3] se transmite al tensor de salida con la forma de [3, 3] .

Cuando se realizan operaciones de transmisión, como multiplicar un tensor por un escalar, la transmisión (generalmente) otorga algún beneficio de tiempo o espacio, ya que el tensor de transmisión nunca se materializa.

Sin embargo, broadcast_to no conlleva tales beneficios. El tensor recién creado toma la memoria completa de la forma transmitida. (Sin embargo, en un contexto gráfico, broadcast_to podría fusionarse con la operación posterior y luego optimizarse).

Rasgos: SiempreSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
input tensor de 32 bits flotante o entero sin signo de 32 bits o entero sin signo de 1 bit o entero sin signo de 8 bits o tipo QI8 o entero sin signo de 8 bits o tipo QUI8 o entero sin signo de 16 bits o tipo QI16 o sin signo de 64 bits tipo entero o complejo con valores de elementos flotantes de 32 bits
shape tensor de valores enteros sin signo de 32/64 bits

Resultados:

Resultado Descripción
output tensor de 32 bits flotante o entero sin signo de 32 bits o entero sin signo de 1 bit o entero sin signo de 8 bits o tipo QI8 o entero sin signo de 8 bits o tipo QUI8 o entero sin signo de 16 bits o tipo QI16 o sin signo de 64 bits tipo entero o complejo con valores de elementos flotantes de 32 bits

tfl.bucketize (::mlir::TFL::BucketizeOp)

Divide en cubos la 'entrada' en función de los 'límites'.

Ejemplo:

Si las entradas son boundaries = [0, 10, 100] y input = [[-5, 10000][150, 10][5, 100]] , entonces la salida será output = [[0, 3][3, 2][1, 3]] .

Rasgos: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
boundaries ::mlir::ArrayAttr Atributo de matriz flotante de 32 bits

operandos:

operando Descripción
input tensor de valores flotantes de 32 bits o flotantes de 64 bits o enteros sin signo de 32 bits o enteros sin signo de 64 bits

Resultados:

Resultado Descripción
output tensor de valores enteros sin signo de 32 bits

tfl.call_once (::mlir::TFL::CallOnceOp)

Invoca una función de inicialización

Esta operación invoca la función de inicialización dada para el inicializador de sesión en el dialecto del modelo guardado tf.

Interfaces: TflRuntimeVerifyOpInterface

Atributos:

Atributo Tipo MLIR Descripción
session_init_function ::mlir::StringAttr atributo de cadena

tfl.cast (::mlir::TFL::CastOp)

Operador de reparto

Convierte la entrada del tipo de entrada al tipo de salida.

Rasgos: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
input tensor de 32 bits flotante o entero sin signo de 1 bit o entero sin signo de 16 bits o entero sin signo de 16 bits o entero sin signo de 32 bits o entero sin signo de 32 bits o entero sin signo de 64 bits o tipo TFLite quint8 o 8 bits entero sin signo o entero sin signo de 8 bits o tipo complejo con valores de elementos flotantes de 32 bits

Resultados:

Resultado Descripción
output tensor de 32 bits flotante o entero sin signo de 1 bit o entero sin signo de 16 bits o entero sin signo de 16 bits o entero sin signo de 32 bits o entero sin signo de 32 bits o entero sin signo de 64 bits o tipo TFLite quint8 o 8 bits entero sin signo o entero sin signo de 8 bits o tipo complejo con valores de elementos flotantes de 32 bits

tfl.ceil (::mlir::TFL::CeilOp)

operador de techo

Devuelve el valor máximo de elemento de la entrada.

Rasgos: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: condicionalmente especulable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
x tensor de valores flotantes de 32 bits

Resultados:

Resultado Descripción
y tensor de valores flotantes de 32 bits

tfl.complex_abs (::mlir::TFL::ComplexAbsOp)

Calcula el valor absoluto complejo de un tensor.

Dado un tensor x de números complejos, esta operación devuelve un tensor de tipo float o double que es el valor absoluto de cada elemento en x . Todos los elementos en x deben ser números complejos de la forma \(a + bj\). El valor absoluto se calcula como \( \sqrt{a^2 + b^2}\).

Rasgos: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
input tensor de tipo complejo con elementos flotantes de 32 bits o tipo complejo con valores de elementos flotantes de 64 bits

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits o flotantes de 64 bits

tfl.concatenation (::mlir::TFL::ConcatenationOp)

Operador de concatenación

Concatena tensores a lo largo de una dimensión

Rasgos: SiempreSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
axis ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT

operandos:

operando Descripción
values tensor de cualquier tipo de valores

Resultados:

Resultado Descripción
output tensor de 32 bits flotante o entero sin signo de 64 bits o entero sin signo de 32 bits o entero sin signo de 16 bits o entero sin signo de 8 bits o tipo QI8 o tipo QUI8 o valores enteros sin signo de 8 bits o enteros sin signo de 1 bit

tfl.pseudo_const (::mlir::TFL::ConstOp)

Pseudo op constante.

Representa un valor constante en el dialecto de TensorFlow Lite. Esta no es una operación real y se reducirá al búfer en su lugar.

Se permite que la operación tenga el mismo tipo de atributos que tf.Const (por ejemplo, se permiten atributos TF opacos).

Rasgos: AlwaysSpeculatableImplTrait, ConstantLike, FirstAttrDerivedResultType, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
value ::mlir::ElementosAttr vector constante/atributo de tensor

Resultados:

Resultado Descripción
output tensor de cualquier tipo de valores

tfl.control_node (::mlir::TFL::ControlNodeOp)

The `TFL.control_node` operation wraps single-block operations in order to attach control edges.

Esto se usa para envolver regiones y adjuntarles dependencias de control. Por lo general, esto sucederá en uno de los últimos pasos antes de emitir el modelo de búfer plano para habilitar las optimizaciones que se basan en un orden fijo de operaciones (como la rematerialización). El exportador de búfer plano desenvolverá la región envuelta y anotará el modelo generado con metadatos. de modo que cualquier reordenamiento en tiempo de ejecución respetará el orden dado por las dependencias de control.

Rasgos: HasParent mlir::func::FuncOp , RecursiveMemoryEffects, SingleBlockImplicitTerminator

operandos:

operando Descripción
controlInputs control

Resultados:

Resultado Descripción
outputs tensor de cualquier tipo de valores
control control

tfl.conv_2d (::mlir::TFL::Conv2DOp)

Operador de convolución

Realiza la operación de convolución en las entradas.

Entradas: inputs[0] : requerida: el tensor de activación de entrada inputs[1] : requerida: el tensor de ponderación del filtro inputs[2] : opcional: el tensor de polarización

Rasgos: AlwaysSpeculatableImplTrait, QuantizableResult, quant::AccumulatorUniformScale<2, 0, 1>, quant::AffineOpCoficient<0, 1>

Interfaces: AffineQuantizedOpInterface, Conditionally Speculatable, DynamicRangeQuantizedOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TFL_SparseOp, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
dilation_h_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
dilation_w_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT
padding ::mlir::StringAttr atributo de cadena cuyo valor es MISMO o VÁLIDO
stride_h ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
stride_w ::mlir::IntegerAttr Atributo entero sin signo de 32 bits

operandos:

operando Descripción
input tensor de valores flotantes de 32 bits o tipo QI8 o tipo QUI8 o tipo QI16
filter tensor de valores flotantes de 32 bits o tipo QI4 o tipo QI8 o tipo QUI8
bias tensor de cualquier tipo valores o ningún tipo

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits o tipo QI8 o tipo QUI8 o tipo QI16

tfl.conv_3d (::mlir::TFL::Conv3DOp)

Operador 3D de convolución

Realiza operaciones de convolución en entradas 3D. Entradas: inputs[0] : requerida: el tensor de activación de entrada inputs[1] : requerida: el tensor de ponderación del filtro inputs[2] : opcional: el tensor de polarización

Rasgos: AlwaysSpeculatableImplTrait, quant::AccumulatorUniformScale<2, 0, 1>

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
dilation_d_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
dilation_h_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
dilation_w_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT
padding ::mlir::StringAttr atributo de cadena cuyo valor es MISMO o VÁLIDO
stride_d ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
stride_h ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
stride_w ::mlir::IntegerAttr Atributo entero sin signo de 32 bits

operandos:

operando Descripción
input tensor de valores flotantes de 32 bits
filter tensor de valores flotantes de 32 bits
bias tensor de cualquier tipo valores o ningún tipo

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits

tfl.conv_3d_transpose (::mlir::TFL::Conv3DTransposeOp)

Operador 3D de convolución transpuesta

Realiza la operación de convolución transpuesta en entradas 3D. Entradas: inputs[0] : requerida: la forma del tensor de salida inputs[1] : requerida: el tensor de ponderación del filtro inputs[2] : requerida: el tensor de activación de entrada inputs[3] : opcional: el tensor de polarización

Rasgos: AlwaysSpeculatableImplTrait, quant::AccumulatorUniformScale<2, 0, 1>

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
dilation_d_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
dilation_h_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
dilation_w_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT
padding ::mlir::StringAttr atributo de cadena cuyo valor es MISMO o VÁLIDO
stride_d ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
stride_h ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
stride_w ::mlir::IntegerAttr Atributo entero sin signo de 32 bits

operandos:

operando Descripción
output_shape tensor de valores enteros sin signo de 32 bits
filter tensor de valores flotantes de 32 bits
input tensor de valores flotantes de 32 bits
bias tensor de cualquier tipo valores o ningún tipo

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits

tfl.cos (::mlir::TFL::CosOp)

Operador coseno

Calcula el coseno de entrada por elemento

Rasgos: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: condicionalmente especulable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
x tensor de valores flotantes de 32 bits

Resultados:

Resultado Descripción
y tensor de valores flotantes de 32 bits

tfl.cumsum (::mlir::TFL::CumsumOp)

Operador de suma total

Calcule la suma acumulativa del tensor x a lo largo del eje.

Rasgos: SiempreSpeculatableImplTrait

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
exclusive ::mlir::BoolAttr atributo booleano
reverse ::mlir::BoolAttr atributo booleano

operandos:

operando Descripción
input tensor de valores flotantes de 32 bits o enteros sin signo de 32 bits o enteros sin signo de 64 bits
axis tensor de valores enteros sin signo de 32 bits

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits o enteros sin signo de 32 bits o enteros sin signo de 64 bits

tfl.custom (::mlir::TFL::CustomOp)

operación personalizada

Una operación genérica para cualquier operación personalizada de TFLite.

entrada: una lista de entradas en la operación original. custom_code: una cadena utilizada para identificar cuál es exactamente esta operación, que corresponde a operator_codes.custom_code en el búfer plano. custom_option: un contenedor para guardar los atributos op en forma de bytes. salida: una lista de salidas en la operación original.

Interfaces: TflRuntimeVerifyOpInterface

Atributos:

Atributo Tipo MLIR Descripción
custom_code ::mlir::StringAttr atributo de cadena
custom_option ::mlir::TFL::ConstBytesAttr Una representación de atributo de cadena de bytes compilados

operandos:

operando Descripción
input tensor de cualquier tipo valores o ningún tipo

Resultados:

Resultado Descripción
output tensor de cualquier tipo de valores

tfl.custom_tf (::mlir::TFL::CustomTfOp)

Wrapper Op para operaciones personalizadas de TF.

Una operación de envoltorio alrededor de cualquier operación TF personalizada. Esto incluye operaciones definidas usando custom_opdefs o vinculadas que no están definidas en el dialecto TF. Esta operación simplemente envuelve la operación personalizada dentro de una región. Nota n.º 1: esta operación no incluirá operaciones personalizadas de TF Lite definidas con CustomOp. Nota #2, esta operación es solo una representación interna dentro del convertidor y no se expone/exporta cuando el modelo se exporta a Flatbuffer.

Rasgos: IsolatedFromAbove, RecursiveMemoryEffects, SingleBlockImplicitTerminator

Interfaces: InferTypeOpInterface, TflRuntimeVerifyOpInterface

operandos:

operando Descripción
input tensor de cualquier tipo valores o ningún tipo

Resultados:

Resultado Descripción
output tensor de cualquier tipo de valores

tfl.densify (::mlir::TFL::DensifyOp)

Operador densificar

Convierte tensor disperso a formato denso.

Rasgos: SiempreSpeculatableImplTrait

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
input tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits o enteros sin signo de 8 bits

tfl.depth_to_space (::mlir::TFL::DepthToSpaceOp)

Operador ProfundidadAlEspacio

Reorganiza los datos de profundidad en bloques de datos espaciales. Esta es la transformación inversa de SpaceToDepth. Más específicamente, esta operación genera una copia del tensor de entrada donde los valores de la dimensión de depth se mueven en bloques espaciales a las dimensiones de height y width . El attr block_size indica el tamaño del bloque de entrada y cómo se mueven los datos.

Rasgos: SiempreSpeculatableImplTrait, QuantizableResult

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
block_size ::mlir::IntegerAttr Atributo entero sin signo de 32 bits cuyo valor es positivo

operandos:

operando Descripción
input tensor de 32 bits flotante o entero sin signo de 8 bits o entero sin signo de 32 bits o entero sin signo de 64 bits o tipo TFLite quint8 o entero sin signo de 8 bits o tipo QI8 o valores de tipo QUI8

Resultados:

Resultado Descripción
output tensor de 32 bits flotante o entero sin signo de 8 bits o entero sin signo de 32 bits o entero sin signo de 64 bits o tipo TFLite quint8 o entero sin signo de 8 bits o tipo QI8 o valores de tipo QUI8

tfl.depthwise_conv_2d (::mlir::TFL::DepthwiseConv2DOp)

Operador de convolución separable en profundidad

Realiza la operación de convolución en las entradas.

Entradas: inputs[0] : requerida: el tensor de activación de entrada inputs[1] : requerida: el tensor de ponderación del filtro inputs[2] : opcional: el tensor de polarización

Rasgos: AlwaysSpeculatableImplTrait, QuantizableResult, quant::AccumulatorUniformScale<2, 0, 1>, quant::AffineOpCoficient<3, 1>

Interfaces: AffineQuantizedOpInterface, Conditionally Speculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TFL_SparseOp, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
dilation_h_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
dilation_w_factor ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT
padding ::mlir::StringAttr atributo de cadena cuyo valor es MISMO o VÁLIDO
stride_h ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
stride_w ::mlir::IntegerAttr Atributo entero sin signo de 32 bits
depth_multiplier ::mlir::IntegerAttr Atributo entero sin signo de 32 bits

operandos:

operando Descripción
input tensor de valores flotantes de 32 bits o tipo QI8 o tipo QUI8 o tipo QI16
filter tensor de valores flotantes de 32 bits o tipo QI4 o tipo QI8 o tipo QUI8
bias tensor de cualquier tipo valores o ningún tipo

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits o tipo QI8 o tipo QUI8 o tipo QI16

tfl.dequantize (::mlir::TFL::DequantizeOp)

operador descuantificar

Convierte una matriz cuantificada de enteros en puntos flotantes de acuerdo con los parámetros de cuantificación.

Interfaces: TflRuntimeVerifyOpInterface

operandos:

operando Descripción
input tensor de tipo QI4 o tipo QI8 o tipo QUI8 o tipo QI16 o valores flotantes de 16 bits

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits

tfl.div (::mlir::TFL::DivOp)

operador de división

Operación de división por elementos.

Rasgos: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, ResultsBroadcastableShape

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

Atributos:

Atributo Tipo MLIR Descripción
fused_activation_function ::mlir::StringAttr atributo de cadena cuyo valor es NONE, RELU, RELU_N1_TO_1, RELU6, TANH o SIGN_BIT

operandos:

operando Descripción
lhs tensor de valores flotantes de 32 bits o enteros sin signo de 32 bits o valores de tipo QUI8
rhs tensor de valores flotantes de 32 bits o enteros sin signo de 32 bits o valores de tipo QUI8

Resultados:

Resultado Descripción
output tensor de valores flotantes de 32 bits o enteros sin signo de 32 bits o valores de tipo QUI8

tfl.dynamic_update_slice (::mlir::TFL::DynamicUpdateSliceOp)

Segmento de actualización dinámica.

DynamicUpdateSlice op que tienen la misma semántica con XLA DynamicUpdateSlice. Genera un resultado que es el valor del operando de matriz de entrada, con una actualización de segmento sobrescrita en start_indices.

Consulte https://www.tensorflow.org/xla/operation_semantics#dynamicupdateslice

Rasgos: SiempreSpeculatableImplTrait

Interfaces: condicionalmente especulable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Efectos: MemoryEffects::Effect{}

operandos:

operando Descripción
operand tensor de entero sin signo de 1 bit o entero sin signo de 8 bits o entero sin signo de 32 bits o entero sin signo de 64 bits o valores flotantes de 32 bits
update tensor de entero sin signo de 1 bit o entero sin signo de 8 bits o entero sin signo de 32 bits o entero sin signo de 64 bits o valores flotantes de 32 bits
start_indices tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 1-bit signless integer or 8-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit float values

tfl.elu (::mlir::TFL::EluOp)

Exponential Linear Unit operator

Computes the exponential linear f(x) -> exp(x) - 1 for x < 0, x for x >= 0. element-wise.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or 8-bit signless integer values

Results:

Result Description
y tensor of 32-bit float or 8-bit signless integer values

tfl.embedding_lookup (::mlir::TFL::EmbeddingLookupOp)

Embedding lookup operator

Looks up ids in a list of embedding tensors.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lookup tensor of 32-bit signless integer values
value tensor of 32-bit float or 8-bit signless integer or 8-bit unsigned integer values

Results:

Result Description
output tensor of 32-bit float or 8-bit signless integer or 8-bit unsigned integer values

tfl.equal (::mlir::TFL::EqualOp)

Equal operator

Returns the truth element of x == y element-wise

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 1-bit signless integer or 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or 8-bit unsigned integer or TFLite string type values
y tensor of 1-bit signless integer or 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or 8-bit unsigned integer or TFLite string type values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.exp (::mlir::TFL::ExpOp)

Natural exponentiation operator

Performs element-wise natural exponentiation operation on input.

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float values

Results:

Result Description
y tensor of 32-bit float values

tfl.expand_dims (::mlir::TFL::ExpandDimsOp)

Inserts a dimension of 1 into a tensor's shape.

Given a tensor input , this operation inserts a dimension of 1 at the dimension index axis of input 's shape. The dimension index axis starts at zero; if you specify a negative number for axis it is counted backward from the end.

This operation is useful if you want to add a batch dimension to a single element. For example, if you have a single image of shape [height, width, channels] , you can make it a batch of 1 image with expand_dims(image, 0) , which will make the shape [1, height, width, channels] .

Other examples:

# 't' is a tensor of shape [2]
shape(expand_dims(t, 0)) ==> [1, 2]
shape(expand_dims(t, 1)) ==> [2, 1]
shape(expand_dims(t, -1)) ==> [2, 1]

# 't2' is a tensor of shape [2, 3, 5]
shape(expand_dims(t2, 0)) ==> [1, 2, 3, 5]
shape(expand_dims(t2, 2)) ==> [2, 3, 1, 5]
shape(expand_dims(t2, 3)) ==> [2, 3, 5, 1]

This operation requires that:

-1-input.dims() <= dim <= input.dims()

This operation is related to squeeze() , which removes dimensions of size 1.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of any type values
dim tensor of 32/64-bit signless integer values

Results:

Result Description
output tensor of any type values

tfl.external_const (::mlir::TFL::ExternalConstOp)

External const op.

External const op holds a buffer_index which points to a constant in the flatbuffer.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
buffer_index ::mlir::IntegerAttr 32-bit signless integer attribute

Results:

Result Description
output tensor of any type values

tfl.fake_quant (::mlir::TFL::FakeQuantOp)

FakeQuant operator

Fake-quantize the 'inputs' tensor of type float via float scalars min and max to 'outputs' tensor of same shape as inputs.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
min ::mlir::FloatAttr 32-bit float attribute
max ::mlir::FloatAttr 32-bit float attribute
num_bits ::mlir::IntegerAttr 32-bit signless integer attribute whose minimum value is 2 whose maximum value is 16
narrow_range ::mlir::BoolAttr bool attribute whose value is false

Operands:

Operand Description
input tensor of 32-bit float values

Results:

Result Description
output tensor of 32-bit float values

tfl.fill (::mlir::TFL::FillOp)

Fill the tensor with given value.

Fill the tensor with given value.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
dims tensor of 32/64-bit signless integer values
input tensor of 32-bit float or 16-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or QI8 type or QI16 type or TFLite string type values

Results:

Result Description
result tensor of 32-bit float or 16-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or QI8 type or QI16 type or TFLite string type values

tfl.floor_div (::mlir::TFL::FloorDivOp)

Floor div operator

Element-wise floor div operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer values
rhs tensor of 32-bit float or 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer values

tfl.floor_mod (::mlir::TFL::FloorModOp)

Division reminder

Element-wise division reminder operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit signless integer or 64-bit signless integer or 32-bit float values
rhs tensor of 32-bit signless integer or 64-bit signless integer or 32-bit float values

Results:

Result Description
output tensor of 32-bit signless integer or 64-bit signless integer or 32-bit float values

tfl.floor (::mlir::TFL::FloorOp)

Floor operator

Returns element-wise floor value of the input.

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float values

Results:

Result Description
y tensor of 32-bit float values

tfl.fully_connected (::mlir::TFL::FullyConnectedOp)

Fully connected op

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, quant::AccumulatorUniformScale<2, 0, 1>, quant::AffineOpCoefficient<-1, 1>

Interfaces: AffineQuantizedOpInterface, ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TFL_SparseOp, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
weights_format ::mlir::StringAttr string attribute whose value is DEFAULT, or SHUFFLED4x16INT8
keep_num_dims ::mlir::BoolAttr bool attribute
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or QUI16 type values
filter tensor of 32-bit float or QI4 type or QI8 type or QUI8 type or QI16 type values
bias tensor of any type values or none type

Results:

Result Description
output tensor of any type values

tfl.gather_nd (::mlir::TFL::GatherNdOp)

Gather_nd operator

Gather slices from params into a Tensor with shape specified by indices .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
params tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 64-bit signless integer or 32-bit signless integer or 8-bit unsigned integer or TFLite string type values
indices tensor of 32/64-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 64-bit signless integer or 32-bit signless integer or 8-bit unsigned integer or TFLite string type values

tfl.gather (::mlir::TFL::GatherOp)

Gather operator

Gather slices from params axis axis according to indices .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
axis ::mlir::IntegerAttr 32-bit signless integer attribute
batch_dims ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand Description
params tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 32-bit signless integer or 64-bit signless integer or TFLite string type or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values
indices tensor of 32-bit signless integer or 64-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 32-bit signless integer or 64-bit signless integer or TFLite string type or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values

tfl.gelu (::mlir::TFL::GeluOp)

GELU activation function.

Computes GELU activation function element-wise.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
approximate ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or QI8 type or QUI8 type values

Results:

Result Description
output tensor of 32-bit float or QI8 type or QUI8 type values

tfl.greater_equal (::mlir::TFL::GreaterEqualOp)

Greater_equal operator

Element-wise greater_equal operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.greater (::mlir::TFL::GreaterOp)

Greater operator

Element-wise greater operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.hard_swish (::mlir::TFL::HardSwishOp)

Hardswish activation function.

Computes hard-swish activation function f(x) -> (x * relu6(x+3))/6 element-wise.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or QUI8 type or QI8 type values

Results:

Result Description
output tensor of 32-bit float or QUI8 type or QI8 type values

tfl.hashtable_find (::mlir::TFL::HashtableFindOp)

Looks up keys in a table, outputs the corresponding values.

The tensor keys must of the same type as the keys of the table. The output values is of the type of the table values.

The scalar default_value is the value output for keys not present in the table. It must also be of the same type as the table values.

Interfaces: TflRuntimeVerifyOpInterface

Operands:

Operand Description
hash_table tensor of resource values
keys tensor of 32-bit signless integer or TFLite string type or 64-bit signless integer values
default_value tensor of 32-bit float or 32-bit signless integer or TFLite string type or 64-bit signless integer values

Results:

Result Description
out tensor of 32-bit float or 32-bit signless integer or TFLite string type or 64-bit signless integer values

tfl.hashtable_import (::mlir::TFL::HashtableImportOp)

Replaces the contents of the table with the specified keys and values.

The tensor keys must be of the same type as the keys of the table. The tensor values must be of the type of the table values.

Interfaces: TflRuntimeVerifyOpInterface

Operands:

Operand Description
hash_table tensor of resource values
keys tensor of 32-bit signless integer or TFLite string type or 64-bit signless integer values
values tensor of 32-bit float or 32-bit signless integer or TFLite string type or 64-bit signless integer values

tfl.hashtable (::mlir::TFL::HashtableOp)

Creates a non-initialized hash table.

This op creates a hash table, specifying the type of its keys and values. Before using the table you will have to initialize it. After initialization the table will be immutable.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
table_id ::mlir::IntegerAttr 32-bit signless integer attribute
key_dtype ::mlir::TypeAttr any type attribute
value_dtype ::mlir::TypeAttr any type attribute

Results:

Result Description
out tensor of resource values

tfl.hashtable_size (::mlir::TFL::HashtableSizeOp)

Computes the number of elements in the given table.

Interfaces: TflRuntimeVerifyOpInterface

Operands:

Operand Description
hash_table tensor of resource values

Results:

Result Description
out tensor of 64-bit signless integer values

tfl.if (::mlir::TFL::IfOp)

if-then-else operation

The tfl.if operation represents an if-then-else construct for conditionally executing two regions of code. The operand to an if operation is a boolean value. For example:

tfl.if %b  {
  ...
} else {
  ...
}

tfl.if may also return results that are defined in its regions. The values defined are determined by which execution path is taken.

Example:

%x, %y = tfl.if %b -> (tensor<f32>, tensor<f32>) {
  %x_true = ...
  %y_true = ...
  tfl.yield %x_true, %y_true : tensor<f32>, tensor<f32>
} else {
  %x_false = ...
  %y_false = ...
  tfl.yield %x_false, %y_false : tensor<f32>, tensor<f32>
}

tfl.if regions are always terminated with "tfl.yield". If "tfl.if" defines no values, the "tfl.yield" can be left out, and will be inserted implicitly. Otherwise, it must be explicit. Also, if "tfl.if" defines one or more values, the 'else' block cannot be omitted.

Example:

tfl.if %b  {
  ...
}

Traits: NoRegionArguments, RecursiveMemoryEffects, SingleBlockImplicitTerminator

Interfaces: RegionBranchOpInterface, TflRuntimeVerifyOpInterface

Operands:

Operand Description
cond tensor of 1-bit signless integer values

Results:

Result Description
results tensor of any type values

tfl.imag (::mlir::TFL::ImagOp)

Returns the imaginary part of a complex number.

Given a tensor input of complex numbers, this operation returns a tensor of type float that is the imaginary part of each element in input . All elements in input must be complex numbers of the form \(a + bj\), where a is the real part and b is the imaginary part returned by this operation.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of complex type with 32-bit float elements or complex type with 64-bit float elements values

Results:

Result Description
output tensor of 32-bit float or 64-bit float values

tfl.l2_normalization (::mlir::TFL::L2NormalizationOp)

L2 Normalize Operator

L2Normalization Op

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand Description
input tensor of 32-bit float or QUI8 type or QI8 type or QUI16 type or QI16 type or 8-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or QUI8 type or QI8 type or QUI16 type or QI16 type or 8-bit signless integer values

tfl.lstm (::mlir::TFL::LSTMOp)

The full lstm operator

Long short-term memory unit (LSTM) recurrent network layer. The default non-peephole implementation is based on: http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf S. Hochreiter and J. Schmidhuber. 'Long Short-Term Memory'. Neural Computation, 9(8):1735-1780, 1997. The peephole implementation is based on: https://research.google.com/pubs/archive/43905.pdf Hasim Sak, Andrew Senior, and Francoise Beaufays. 'Long short-term memory recurrent neural network architectures for large scale acoustic modeling.' INTERSPEECH, 2014. The coupling of input and forget gate (CIFG) is based on: http://arxiv.org/pdf/1503.04069.pdf Greff et al. 'LSTM: A Search Space Odyssey' The layer normalization is based on: https://arxiv.org/pdf/1607.06450.pdf Ba et al. 'Layer Normalization'

Traits: QuantizableResult

Interfaces: DynamicRangeQuantizedOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
cell_clip ::mlir::FloatAttr 32-bit float attribute whose value is non-negative
proj_clip ::mlir::FloatAttr 32-bit float attribute whose value is non-negative
kernel_type ::mlir::TFL::LSTMKernelTypeAttr lstm_kernel_type whose value is mlir::TFL::LSTMKernelType::FULL
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute
input_to_input_intermediate ::mlir::TypeAttr any type attribute
input_to_forget_intermediate ::mlir::TypeAttr any type attribute
input_to_cell_intermediate ::mlir::TypeAttr any type attribute
input_to_output_intermediate ::mlir::TypeAttr any type attribute
effective_hidden_scale_intermediate ::mlir::TypeAttr any type attribute

Operands:

Operand Description
input tensor of 32-bit float or QI8 type values
input_to_input_weights tensor of any type values or none type
input_to_forget_weights tensor of 32-bit float or QI8 type values
input_to_cell_weights tensor of 32-bit float or QI8 type values
input_to_output_weights tensor of 32-bit float or QI8 type values
recurrent_to_input_weights tensor of any type values or none type
recurrent_to_forget_weights tensor of 32-bit float or QI8 type values
recurrent_to_cell_weights tensor of 32-bit float or QI8 type values
recurrent_to_output_weights tensor of 32-bit float or QI8 type values
cell_to_input_weights tensor of any type values or none type
cell_to_forget_weights tensor of any type values or none type
cell_to_output_weights tensor of any type values or none type
input_gate_bias tensor of any type values or none type
forget_gate_bias tensor of 32-bit float or QI32 type values
cell_bias tensor of 32-bit float or QI32 type values
output_gate_bias tensor of 32-bit float or QI32 type values
projection_weights tensor of any type values or none type
projection_bias tensor of any type values or none type
input_activation_state stateful tensor
input_cell_state stateful tensor
input_layer_norm_coefficients tensor of any type values or none type
forget_layer_norm_coefficients tensor of any type values or none type
cell_layer_norm_coefficients tensor of any type values or none type
output_layer_norm_coefficients tensor of any type values or none type

Results:

Result Description
output tensor of any type values

tfl.leaky_relu (::mlir::TFL::LeakyReluOp)

Leaky Relu operator

Element-wise Leaky ReLU operator x -> x >= 0 ? x : (alpha * x)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
alpha ::mlir::FloatAttr 32-bit float attribute

Operands:

Operand Description
input tensor of 32-bit float or QUI8 type or QI8 type or TFLite quint8 type or QI16 type values

Results:

Result Description
output tensor of 32-bit float or QUI8 type or QI8 type or TFLite quint8 type or QI16 type values

tfl.less_equal (::mlir::TFL::LessEqualOp)

Less_equal operator

Element-wise less_equal operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.less (::mlir::TFL::LessOp)

Less operator

Element-wise less operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.local_response_normalization (::mlir::TFL::LocalResponseNormalizationOp)

Local Response Normalization.

The 4-D input tensor is treated as a 3-D array of 1-D vectors (along the last dimension), and each vector is normalized independently. Within a given vector, each component is divided by the weighted, squared sum of inputs within depth_radius . In detail,

sqr_sum[a, b, c, d] =
    sum(input[a, b, c, d - depth_radius : d + depth_radius + 1] ** 2)
output = input / (bias + alpha * sqr_sum) ** beta

For details, see Krizhevsky et al., ImageNet classification with deep convolutional neural networks (NIPS 2012) .

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
radius ::mlir::IntegerAttr 32-bit signless integer attribute
bias ::mlir::FloatAttr 32-bit float attribute
alpha ::mlir::FloatAttr 32-bit float attribute
beta ::mlir::FloatAttr 32-bit float attribute

Operands:

Operand Description
input tensor of 32-bit float values

Results:

Result Description
output tensor of 32-bit float values

tfl.log (::mlir::TFL::LogOp)

Natural logarithm operator

Performs element-wise natural logarithm operation on input.

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float values

Results:

Result Description
y tensor of 32-bit float values

tfl.log_softmax (::mlir::TFL::LogSoftmaxOp)

Log softmax operator

Computes element-wise log softmax activations with the following formula

input - log(reduce_sum(exp(input), dim))

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or QUI8 type or QI8 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or QUI8 type or QI8 type or TFLite quint8 type values

tfl.logical_and (::mlir::TFL::LogicalAndOp)

Logical AND operator

Element-wise logical AND operation.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 1-bit signless integer values
rhs tensor of 1-bit signless integer values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.logical_not (::mlir::TFL::LogicalNotOp)

Logical NOT operator

Element-wise logical NOT operation.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 1-bit signless integer values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.logical_or (::mlir::TFL::LogicalOrOp)

Logical OR operator

Element-wise logical OR operation.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 1-bit signless integer values
rhs tensor of 1-bit signless integer values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.logistic (::mlir::TFL::LogisticOp)

Logistic operator

Computes element-wise Sigmoid of input

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result Description
y tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.matrix_diag (::mlir::TFL::MatrixDiagOp)

Returns a tensor with the provided diagonal and everything else padded with zeros.

Given a diagonal, returns a tensor with the diagonal and everything else padded with zeros. Assume diagonal has k dimensions [I, J, K, ..., N] , then the output is a tensor of rank k+1 with dimensions [I, J, K, ..., N, N] where: output[i, j, k, ..., m, n] = 1{m=n} * diagonal[i, j, k, ..., n].

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
diagonal tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QUI8 type or QI8 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QUI8 type or QI8 type or TFLite quint8 type values

tfl.matrix_set_diag (::mlir::TFL::MatrixSetDiagOp)

Returns a batched matrix tensor with new batched diagonal values.

Given input and diagonal , this operation returns a tensor with the same shape and values as input , except for the main diagonal of the innermost matrices. These will be overwritten by the values in diagonal .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QI16 type or QUI8 type or TFLite quint8 type values
diagonal tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QI16 type or QUI8 type or TFLite quint8 type values

Results:

Result Description
result tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QI16 type or QUI8 type or TFLite quint8 type values

tfl.max_pool_2d (::mlir::TFL::MaxPool2DOp)

Max Pool 2D op

Performs max pool 2D on input.

Inputs: inputs[0] : required: the input tensor

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
padding ::mlir::StringAttr string attribute whose value is SAME, or VALID
stride_w ::mlir::IntegerAttr 32-bit signless integer attribute
stride_h ::mlir::IntegerAttr 32-bit signless integer attribute
filter_width ::mlir::IntegerAttr 32-bit signless integer attribute
filter_height ::mlir::IntegerAttr 32-bit signless integer attribute
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand Description
input tensor of 32-bit float or QUI8 type or QI8 type or QI16 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or QUI8 type or QI8 type or QI16 type or TFLite quint8 type values

tfl.maximum (::mlir::TFL::MaximumOp)

Max operator

Element-wise max operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values
rhs tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values

Results:

Result Description
max tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values

tfl.mean (::mlir::TFL::MeanOp)

Mean operator

Computes the mean of elements across dimensions of a tensor. Reduces input_tensor along the dimensions given in axis. Unless keepdims is true, the rank of the tensor is reduced by 1 for each entry in axis. If keepdims is true, the reduced dimensions are retained with length 1.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or 8-bit unsigned integer or QI16 type values
axis tensor of 32-bit signless integer or 64-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or 8-bit unsigned integer or QI16 type values

tfl.minimum (::mlir::TFL::MinimumOp)

Min operator

Element-wise min operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values
rhs tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values

Results:

Result Description
min tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values

tfl.mirror_pad (::mlir::TFL::MirrorPadOp)

MirrorPad Operator. Pads a tensor with mirrored values.

This operation pads a input with mirrored values according to the paddings you specify. paddings is an integer tensor with shape [n, 2], where n is the rank of input. For each dimension D of input, paddings[D, 0] indicates how many values to add before the contents of input in that dimension, and paddings[D, 1] indicates how many values to add after the contents of input in that dimension.

Both paddings[D, 0] and paddings[D, 1] must be no greater than input.dim_size(D) (or input.dim_size(D) - 1) if copy_border is true (if false, respectively).

The padded size of each dimension D of the output is:

paddings(D, 0) + input.dim_size(D) + paddings(D, 1)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
mode ::mlir::TFL::MirrorPaddingTypeAttr mirror_pad_enum

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type values
pad tensor of 32-bit signless integer or 64-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type values

tfl.mul (::mlir::TFL::MulOp)

Multiplication operator

Element-wise multiplication operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or complex type with 32-bit float elements values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or complex type with 32-bit float elements values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or complex type with 32-bit float elements values

tfl.multinomial (::mlir::TFL::MultinomialOp)

Draws samples from a categorical distribution.

The generated values will have a categorical distribution based on the logits or unnormalized log-probabilities provided for all classes.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
seed ::mlir::IntegerAttr 64-bit signless integer attribute
seed2 ::mlir::IntegerAttr 64-bit signless integer attribute

Operands:

Operand Description
logits tensor of 32-bit float values
num_samples tensor of 32-bit signless integer values

Results:

Result Description
out tensor of 32-bit signless integer or 64-bit signless integer values

tfl.neg (::mlir::TFL::NegOp)

Negation operator

Computes element-wise negation of input

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer values

Results:

Result Description
y tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer values

tfl.no_value (::mlir::TFL::NoValueOp)

constant representing no value.

No value constant op.

Traits: AlwaysSpeculatableImplTrait, ConstantLike

Interfaces: ConditionallySpeculatable, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface)

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
value ::mlir::UnitAttr unit attribute

Results:

Result Description
none_val none type

tfl.non_max_suppression_v4 (::mlir::TFL::NonMaxSuppressionV4Op)

Greedily selects a subset of bounding boxes in descending order of score,

pruning away boxes that have high intersection-over-union (IOU) overlap with previously selected boxes. Bounding boxes with score less than score_threshold are removed. Bounding boxes are supplied as [y1, x1, y2, x2], where (y1, x1) and (y2, x2) are the coordinates of any diagonal pair of box corners and the coordinates can be provided as normalized (ie, lying in the interval [0, 1]) or absolute. Note that this algorithm is agnostic to where the origin is in the coordinate system and more generally is invariant to orthogonal transformations and translations of the coordinate system; thus translating or reflections of the coordinate system result in the same boxes being selected by the algorithm. The output of this operation is a set of integers indexing into the input collection of bounding boxes representing the selected boxes. The bounding box coordinates corresponding to the selected indices can then be obtained using the tf.gather operation . For example: selected_indices = tf.image.non_max_suppression_v2( boxes, scores, max_output_size, iou_threshold, score_threshold) selected_boxes = tf.gather(boxes, selected_indices)

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
boxes tensor of 32-bit float values
scores tensor of 32-bit float values
max_output_size tensor of 32-bit signless integer values
iou_threshold tensor of 32-bit float values
score_threshold tensor of 32-bit float values

Results:

Result Description
selected_indices tensor of 32-bit signless integer values
valid_outputs tensor of 32-bit signless integer values

tfl.non_max_suppression_v5 (::mlir::TFL::NonMaxSuppressionV5Op)

Greedily selects a subset of bounding boxes in descending order of score,

pruning away boxes that have high intersection-over-union (IOU) overlap with previously selected boxes. Bounding boxes with score less than score_threshold are removed. Bounding boxes are supplied as [y1, x1, y2, x2], where (y1, x1) and (y2, x2) are the coordinates of any diagonal pair of box corners and the coordinates can be provided as normalized (ie, lying in the interval [0, 1]) or absolute. Note that this algorithm is agnostic to where the origin is in the coordinate system and more generally is invariant to orthogonal transformations and translations of the coordinate system; thus translating or reflections of the coordinate system result in the same boxes being selected by the algorithm. The output of this operation is a set of integers indexing into the input collection of bounding boxes representing the selected boxes. The bounding box coordinates corresponding to the selected indices can then be obtained using the tf.gather operation . For example: selected_indices = tf.image.non_max_suppression_v2( boxes, scores, max_output_size, iou_threshold, score_threshold) selected_boxes = tf.gather(boxes, selected_indices) This op also supports a Soft-NMS (with Gaussian weighting) mode (cf Bodla et al, https://arxiv.org/abs/1704.04503 ) where boxes reduce the score of other overlapping boxes instead of directly causing them to be pruned. To enable this Soft-NMS mode, set the soft_nms_sigma parameter to be larger than 0.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
boxes tensor of 32-bit float values
scores tensor of 32-bit float values
max_output_size tensor of 32-bit signless integer values
iou_threshold tensor of 32-bit float values
score_threshold tensor of 32-bit float values
soft_nms_sigma tensor of 32-bit float values

Results:

Result Description
selected_indices tensor of 32-bit signless integer values
selected_scores tensor of 32-bit float values
valid_outputs tensor of 32-bit signless integer values

tfl.not_equal (::mlir::TFL::NotEqualOp)

Not_equal operator

Element-wise not_equal operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 1-bit signless integer or 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type or TFLite string type values
rhs tensor of 1-bit signless integer or 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type or TFLite string type values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.NumericVerify (::mlir::TFL::NumericVerifyOp)

Verifies the numericals of the two operands

The NumericVerify op is a debugging op to verify the numericals of the two activations. It is a custom op in TFLite. If log_if_failed is true, the NumericVerify op calculates statistics on differences between float and quantized activations, output logs, set differences to the output tensors, and throws an error if errors above tolerance exist. If log_if_failed = false, then it doesn't care about errors.

Traits: QuantizableResult, SameOperandsShape

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
tolerance ::mlir::FloatAttr 32-bit float attribute
log_if_failed ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of QI8 type or QUI8 type or QI16 type or 16-bit float or TFLite quint8 type values
ref tensor of 32-bit float values

Results:

Result Description
output tensor of 32-bit float values

tfl.one_hot (::mlir::TFL::OneHotOp)

OneHot operator

Returns a one-hot tensor.The locations represented by indices in indices take value on_value , while all other locations take value off_value .

If the input indices is rank N , the output will have rank N+1 , The new axis is created at dimension axis (default: the new axis is appended at the end).

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
axis ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand Description
indices tensor of 32-bit signless integer or 64-bit signless integer values
depth tensor of 32-bit signless integer values
on_value tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or 8-bit signless integer or 8-bit unsigned integer values
off_value tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or 8-bit signless integer or 8-bit unsigned integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or 8-bit signless integer or 8-bit unsigned integer values

tfl.prelu (::mlir::TFL::PReluOp)

Parameterized Relu operator

Parameterized Relu operator x -> x >= 0 ? x : (alpha * x) where alpha is a trainable tensor. input and alpha should be the same size as input or be broadcastable.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape, quant::AffineOpCoefficient<-1, 1>

Interfaces: AffineQuantizedOpInterface, ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type values
alpha tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type values

tfl.pack (::mlir::TFL::PackOp)

Packs a list of tensors along a dimension into one tensor

Packs a list of values_count rank- R tensors into one rank- (R+1) tensor.

Packs the values_count tensors in values into a tensor with rank one higher than each tensor in values , by packing them along the axis dimension.

Given a list of tensors of shape (A, B, C) ;

if axis == 0 then the output tensor will have the shape (N, A, B, C) . if axis == 1 then the output tensor will have the shape (A, N, B, C) . Etc.

For example:

# 'x' is [1, 4]
# 'y' is [2, 5]
# 'z' is [3, 6]
pack([x, y, z]) => [[1, 4], [2, 5], [3, 6]]  # Pack along first dim.
pack([x, y, z], axis=1) => [[1, 2, 3], [4, 5, 6]]

This is the opposite of unpack .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
values_count ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive
axis ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand Description
values tensor of any type values

Results:

Result Description
output tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.pad (::mlir::TFL::PadOp)

Padding operator

This operation pads a input with zeros according to the paddings you specify. paddings is an integer tensor with shape [Dn, 2] , where n is the rank of input . For each dimension D of input , paddings[D, 0] indicates how many zeros to add before the contents of input in that dimension, and paddings[D, 1] indicates how many zeros to add after the contents of input in that dimension.

The padded size of each dimension D of the output is:

paddings(D, 0) + input.dim_size(D) + paddings(D, 1)

For example:

# 't' is [[1, 1], [2, 2]]
# 'paddings' is [[1, 1], [2, 2]]
# rank of 't' is 2
pad(t, paddings) ==> [[0, 0, 0, 0, 0, 0]
                      [0, 0, 1, 1, 0, 0]
                      [0, 0, 2, 2, 0, 0]
                      [0, 0, 0, 0, 0, 0]]

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
padding tensor of 32/64-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.padv2 (::mlir::TFL::PadV2Op)

Padding operator v2

This operation pads a input according to the paddings and constant_values you specify. paddings is an integer tensor with shape [Dn, 2] , where n is the rank of input . For each dimension D of input , paddings[D, 0] indicates how many zeros to add before the contents of input in that dimension, and paddings[D, 1] indicates how many zeros to add after the contents of input in that dimension. constant_values is a scalar tensor of the same type as input that indicates the value to use for padding input .

The padded size of each dimension D of the output is:

paddings(D, 0) + input.dim_size(D) + paddings(D, 1)

For example:

# 't' is [[1, 1], [2, 2]]
# 'paddings' is [[1, 1], [2, 2]]
# rank of 't' is 2
pad(t, paddings) ==> [[0, 0, 0, 0, 0, 0]
                      [0, 0, 1, 1, 0, 0]
                      [0, 0, 2, 2, 0, 0]
                      [0, 0, 0, 0, 0, 0]]

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type values
padding tensor of 32/64-bit signless integer values
constant_values tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type values

tfl.poly_call (::mlir::TFL::PolyCallOp)

Poly call

Have multiple function bodies for the same computation. This allows a program compiler/interpreter to choose one of the available options to execute the program based on which one is most suitable for the target backend.

input: A list of input tensors whose types are T. output: A list of output tensors whose types are T.

call: Multiple regions, each of which encapsulates the same semantic computation but in different forms.

Traits: SingleBlockImplicitTerminator

Interfaces: RegionBranchOpInterface

Operands:

Operand Description
input tensor of any type values

Results:

Result Description
output tensor of any type values

tfl.pow (::mlir::TFL::PowOp)

Power operator

Element-wise power operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer values
rhs tensor of 32-bit float or 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer values

tfl.pseudo_qconst (::mlir::TFL::QConstOp)

Quantized constant pseudo op

Represents a quantized constant value in TensorFlow Lite dialect. This is not an actual operation and it will be lowered to buffer instead. The quantization parameters are stored as a type attribute in this constant.

Traits: AlwaysSpeculatableImplTrait, FirstAttrDerivedResultType

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface)

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
qtype ::mlir::TypeAttr Tensor type attribute
value ::mlir::ElementsAttr constant vector/tensor attribute

Results:

Result Description
output tensor of QUI8 type or QI8 type or QI16 type or QUI16 type or TFLite quint8 type values

tfl.quantize (::mlir::TFL::QuantizeOp)

Quantize operator

Converts floating point tensors to quantized integer tensors according to the quantization parameters defined in the type attribute.

Traits: FirstAttrDerivedResultType, SameOperandsAndResultShape

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
qtype ::mlir::TypeAttr Tensor type attribute

Operands:

Operand Description
input tensor of 32-bit float or QI4 type or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result Description
output tensor of QI4 type or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.rfft2d (::mlir::TFL::RFFT2dOp)

2D real-valued fast Fourier transform.

Computes the 2-dimensional discrete Fourier transform of a real-valued signal over the inner-most 2 dimensions of input .

Since the DFT of a real signal is Hermitian-symmetric, RFFT2D only returns the fft_length / 2 + 1 unique components of the FFT for the inner-most dimension of output : the zero-frequency term, followed by the fft_length / 2 positive-frequency terms.

Along each axis RFFT2D is computed on, if fft_length is smaller than the corresponding dimension of input , the dimension is cropped. If it is larger, the dimension is padded with zeros.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float values
fft_length tensor of 32-bit signless integer values

Results:

Result Description
output tensor of complex type with 32-bit float elements values

tfl.random_standard_normal (::mlir::TFL::RandomStandardNormalOp)

Outputs random values from a normal distribution.

The generated values will have mean 0 and standard deviation 1.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
seed ::mlir::IntegerAttr 64-bit signless integer attribute
seed2 ::mlir::IntegerAttr 64-bit signless integer attribute

Operands:

Operand Description
shape tensor of 32-bit signless integer values

Results:

Result Description
out tensor of 32-bit float values

tfl.random_uniform (::mlir::TFL::RandomUniformOp)

Outputs random values from a uniform distribution.

The generated values follow a uniform distribution in the range [0, 1) . The lower bound 0 is included in the range, while the upper bound 1 is excluded.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
seed ::mlir::IntegerAttr 64-bit signless integer attribute
seed2 ::mlir::IntegerAttr 64-bit signless integer attribute

Operands:

Operand Description
shape tensor of 32-bit signless integer values

Results:

Result Description
out tensor of 32-bit float values

tfl.range (::mlir::TFL::RangeOp)

Range operator

Returns a 1D tensor defined by a sequence from start to limit with a given delta .

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
start tensor of 32-bit signless integer or 32-bit float values
limit tensor of 32-bit signless integer or 32-bit float values
delta tensor of 32-bit signless integer or 32-bit float values

Results:

Result Description
result tensor of 32-bit signless integer or 32-bit float values

tfl.rank (::mlir::TFL::RankOp)

Rank operator.

Returns the rank of a tensor.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of any type values

Results:

Result Description
output tensor of any integer type

tfl.read_variable (::mlir::TFL::ReadVariableOp)

Reads variable value.

Read variable data identified by 'resource_id'.

Interfaces: TflRuntimeVerifyOpInterface

Operands:

Operand Description
resource_id tensor of resource values

Results:

Result Description
result tensor of 32-bit float or 64-bit float or 1-bit signless integer or 8-bit unsigned integer or 8-bit signless integer or QI8 type or QUI8 type or 32-bit signless integer or 64-bit signless integer or QI16 type or complex type with 32-bit float elements or complex type with 64-bit float elements values

tfl.real (::mlir::TFL::RealOp)

Returns the real part of a complex number.

Given a tensor input of complex numbers, this operation returns a tensor of type float that is the real part of each element in input . All elements in input must be complex numbers of the form \(a + bj\), where a is the real part returned by this operation and b is the imaginary part.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of complex type with 32-bit float elements or complex type with 64-bit float elements values

Results:

Result Description
output tensor of 32-bit float or 64-bit float values

tfl.reduce_all (::mlir::TFL::ReduceAllOp)

Computes the "logical and" of elements across dimensions of a tensor.

Reduces input along the dimensions given in axis . Unless keep_dims is true, the rank of the tensor is reduced by 1 for each entry in axis . If keep_dims is true, the reduced dimensions are retained with length 1.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 1-bit signless integer values
reduction_indices tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.reduce_any (::mlir::TFL::ReduceAnyOp)

Computes the "logical or" of elements across dimensions of a tensor.

Reduces input along the dimensions given in axis . Unless keep_dims is true, the rank of the tensor is reduced by 1 for each entry in axis . If keep_dims is true, the reduced dimensions are retained with length 1.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 1-bit signless integer values
reduction_indices tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 1-bit signless integer values

tfl.reduce_max (::mlir::TFL::ReduceMaxOp)

Max-reduction operator

Computes the max reduction along the specified axes

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
axes tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.reduce_min (::mlir::TFL::ReduceMinOp)

Min-reduction operator

Computes the min reduction along the specified axes

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
axes tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.reduce_prod (::mlir::TFL::ReduceProdOp)

Prod-reduction operator

Computes the product along the specified axes

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
axes tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.relu_0_to_1 (::mlir::TFL::Relu0To1Op)

Relu0To1 operator

Element-wise Relu0To1 operator x -> max(0, min(1, x))

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or QUI8 type or QI8 type values

Results:

Result Description
y tensor of 32-bit float or QUI8 type or QI8 type values

tfl.relu_n1_to_1 (::mlir::TFL::Relu1Op)

Relu1 operator

Element-wise Relu1 operator x -> max(-1, min(1, x))

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or QUI8 type or QI8 type values

Results:

Result Description
y tensor of 32-bit float or QUI8 type or QI8 type values

tfl.relu6 (::mlir::TFL::Relu6Op)

Relu6 operator

Element-wise Relu6 operator x -> max(0, min(6, x))

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or QUI8 type or QI8 type values

Results:

Result Description
y tensor of 32-bit float or QUI8 type or QI8 type values

tfl.relu (::mlir::TFL::ReluOp)

Relu operator

Element-wise Relu operator x -> max(0, x)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or QUI8 type or QI8 type or QI16 type values

Results:

Result Description
y tensor of 32-bit float or QUI8 type or QI8 type or QI16 type values

tfl.reshape (::mlir::TFL::ReshapeOp)

Reshape operator

Produces a tensor with the same values but different static shape defined by the output type.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of any type values
shape tensor of 32-bit signless integer values

Results:

Result Description
output tensor of any type values

tfl.resize_bilinear (::mlir::TFL::ResizeBilinearOp)

ResizeBilinear Op

Resize images to size using bilinear interpolation.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
align_corners ::mlir::BoolAttr bool attribute
half_pixel_centers ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or TFLite quint8 type or QUI8 type or QI8 type or QI16 type values
size tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or TFLite quint8 type or QUI8 type or QI8 type or QI16 type values

tfl.resize_nearest_neighbor (::mlir::TFL::ResizeNearestNeighborOp)

ResizeNearestNeighbor Op

Resize images to size using nearest neighbor interpolation.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
align_corners ::mlir::BoolAttr bool attribute
half_pixel_centers ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or TFLite quint8 type or QUI8 type or QI8 type or QI16 type values
size tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or TFLite quint8 type or QUI8 type or QI8 type or QI16 type values

tfl.reverse_sequence (::mlir::TFL::ReverseSequenceOp)

Reverses variable length slices.

This op first slices input along the dimension batch_dim , and for each slice i , reverses the first seq_lengths[i] elements along the dimension seq_dim .

The elements of seq_lengths must obey seq_lengths[i] <= input.dims[seq_dim] , and seq_lengths must be a vector of length input.dims[batch_dim] .

The output slice i along dimension batch_dim is then given by input slice i , with the first seq_lengths[i] slices along dimension seq_dim reversed.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
seq_dim ::mlir::IntegerAttr 32-bit signless integer attribute whose value is non-negative
batch_dim ::mlir::IntegerAttr 32-bit signless integer attribute whose value is non-negative

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI16 type or QUI8 type or TFLite quint8 type values
seq_lengths tensor of 32/64-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI16 type or QUI8 type or TFLite quint8 type values

tfl.reverse_v2 (::mlir::TFL::ReverseV2Op)

ReverseV2 Operator

Reverses specific dimensions of a tensor.

Given a tensor, and a int32/int64 tensor axis representing the set of dimensions of tensor to reverse. This operation reverses each dimension i for which there exists j st axis[j] == i.

Args: tensor: A Tensor. Must be one of the following types: uint8, int8, int16, int32, int64, float32, bool Up to 8-D.

axis: A Tensor. Must be one of the following types: int32, int64. with only 1 element which is the axis index. TODO: Add support for multiple elements.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 8-bit unsigned integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI16 type or QUI8 type or QI8 type or TFLite quint8 type or 1-bit signless integer values
axis tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 8-bit unsigned integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI16 type or QUI8 type or QI8 type or TFLite quint8 type or 1-bit signless integer values

tfl.round (::mlir::TFL::RoundOp)

Round operator

Rounds the values of a tensor to the nearest integer, element-wise.

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float values

Results:

Result Description
y tensor of 32-bit float values

tfl.rsqrt (::mlir::TFL::RsqrtOp)

Reciprocal of square root operator

Computes element-wise reverse square root of input

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or QI8 type or QI16 type values

Results:

Result Description
y tensor of 32-bit float or QI8 type or QI16 type values

tfl.svdf (::mlir::TFL::SVDFOp)

Single value decomposition filter operator

The SVDF op is a decomposition of a densely connected op into low rank filters. For details: https://research.google.com/pubs/pub43813.html https://arxiv.org/abs/1812.02802

Traits: QuantizableResult, quant::AccumulatorUniformScale<3, 2, 4>

Interfaces: DynamicRangeQuantizedOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
rank ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or QI8 type values
feature_weights tensor of 32-bit float or QI8 type or QUI8 type values
time_weights tensor of 32-bit float or QI16 type values
input_gate_bias tensor of any type values or none type
activation_state stateful tensor

Results:

Result Description
output tensor of 32-bit float or QI8 type values

tfl.scatter_nd (::mlir::TFL::ScatterNdOp)

Scatter_nd operator

Scatter updates into a new tensor according to indices

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
indices tensor of 32-bit signless integer values
updates tensor of 32-bit float or 8-bit signless integer or 64-bit signless integer or 32-bit signless integer or 8-bit unsigned integer or 1-bit signless integer values
shape 1D tensor of any type values

Results:

Result Description
output tensor of 32-bit float or 8-bit signless integer or 64-bit signless integer or 32-bit signless integer or 8-bit unsigned integer or 1-bit signless integer values

tfl.segment_sum (::mlir::TFL::SegmentSumOp)

SegmentSum operator

Computes the sum along segments of a tensor.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer values

tfl.select (::mlir::TFL::SelectOp)

Select operator

Select values of 'x' if the corresponding value of 'condition' is true or the value of 'y' if false. There are valid condition input sizes:

  1. Either the same shape (in which case the select is elementwise), or
  2. condition must be Rank 1 and match over the first dimension.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
condition tensor of 1-bit signless integer values
x tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values
y tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.select_v2 (::mlir::TFL::SelectV2Op)

SelectV2 operator

Select values of 'x' if the corresponding value of 'condition' is true or the value of 'y' if false. There are valid condition input sizes:

  1. Either the same shape (in which case the select is elementwise), or
  2. Broadcastable shapes between 'condition', 'x' and 'y'.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
condition tensor of 1-bit signless integer values
x tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values
y tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.shape (::mlir::TFL::ShapeOp)

Shape operator

Returns the shape of a tensor.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
out_type ::mlir::Attribute derived attribute

Operands:

Operand Description
input tensor of any type values

Results:

Result Description
output tensor of 32-bit signless integer or 64-bit signless integer values

tfl.sign (::mlir::TFL::SignOp)

Sign operation

Returns NaN if x is NaN, 0 if x is 0, -1 if x < 0 and 1 if x > 0.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultElementType, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float or 64-bit float or 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 64-bit float or 32-bit signless integer values

tfl.sin (::mlir::TFL::SinOp)

Sine operator

Computes element-wise Sine of input

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float values

Results:

Result Description
y tensor of 32-bit float values

tfl.slice (::mlir::TFL::SliceOp)

Return a slice from 'input'.

The output tensor is a tensor with dimensions described by 'size' whose values are extracted from 'input' starting at the offsets in 'begin'.

begin is zero-based; size is one-based. If size[i] is -1, all remaining elements in dimension i are included in the slice. In other words, this is equivalent to setting: size[i] = input.dim_size(i) - begin[i]

Requirements : 0 <= begin[i] <= begin[i] + size[i] <= Di for i in [0, n)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 1-bit signless integer or TFLite string type or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
begin tensor of 32/64-bit signless integer values
size tensor of 32/64-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 1-bit signless integer or TFLite string type or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.softmax (::mlir::TFL::SoftmaxOp)

Softmax operator

Computes element-wise softmax activations with the following formula

exp(input) / tf.reduce_sum(exp(input * beta), dim)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
beta ::mlir::FloatAttr 32-bit float attribute

Operands:

Operand Description
input tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

Results:

Result Description
output tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.space_to_batch_nd (::mlir::TFL::SpaceToBatchNdOp)

SpaceToBatchNd operator

This operation reshapes space dimensions into the "batch" dimension 0

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type values
block_shape tensor of 32-bit signless integer values
paddings tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type values

tfl.space_to_depth (::mlir::TFL::SpaceToDepthOp)

SpaceToDepth operator

Rearranges blocks of spatial data, into depth. More specifically, this op outputs a copy of the input tensor where values from the height and width dimensions are moved to the depth dimension. block_size indicates the input block size.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
block_size ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type values

tfl.pseudo_sparse_const (::mlir::TFL::SparseConstOp)

Sparse constant pseudo op.

Represents a sparse constant value in TensorFlow Lite dialect. This is not an actual operation and it will be lowered to buffer instead.

Traits: AlwaysSpeculatableImplTrait, FirstAttrDerivedResultType, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
value ::mlir::ElementsAttr constant vector/tensor attribute
s_param ::mlir::TFL::SparsityParameterAttr Sparsity parameter.
compressed_data ::mlir::ElementsAttr constant vector/tensor attribute

Results:

Result Description
output tensor of any type values

tfl.pseudo_sparse_qconst (::mlir::TFL::SparseQConstOp)

Sparse quantized constant pseudo op

Represents a sparse quantized constant value in TensorFlow Lite dialect. This is not an actual operation and it will be lowered to buffer instead. The quantization parameters are stored as a type attribute in this constant.

Traits: AlwaysSpeculatableImplTrait, FirstAttrDerivedResultType

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
qtype ::mlir::TypeAttr Tensor type attribute
value ::mlir::ElementsAttr constant vector/tensor attribute
s_param ::mlir::TFL::SparsityParameterAttr Sparsity parameter.
compressed_data ::mlir::ElementsAttr constant vector/tensor attribute

Results:

Result Description
output tensor of QUI8 type or QI8 type or QI16 type or QUI16 type or TFLite quint8 type values

tfl.sparse_to_dense (::mlir::TFL::SparseToDenseOp)

Converts a sparse representation into a dense tensor.

Builds an array dense with shape output_shape such that

# If sparse_indices is scalar
dense[i] = (i == sparse_indices ? sparse_values : default_value)

# If sparse_indices is a vector, then for each i
dense[sparse_indices[i]] = sparse_values[i]

# If sparse_indices is an n by d matrix, then for each i in [0, n)
dense[sparse_indices[i][0], ..., sparse_indices[i][d-1]] = sparse_values[i]

All other values in dense are set to default_value . If sparse_values is a scalar, all sparse indices are set to this single value.

Indices should be sorted in lexicographic order, and indices must not contain any repeats. If validate_indices is true, these properties are checked during execution.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
sparse_indices tensor of 32/64-bit signless integer values
output_shape tensor of 32/64-bit signless integer values
sparse_values tensor of 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or TFLite quint8 type or 32-bit float values
default_value tensor of 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or TFLite quint8 type or 32-bit float values

Results:

Result Description
dense tensor of 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or TFLite quint8 type or 32-bit float values

tfl.split (::mlir::TFL::SplitOp)

Splits a tensor into num_split tensors along one dimension.

Splits the value tensor along split_dim into a number of sub-tensors with same shape as the original one, except for split_dim . Same as tf.Split.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
num_splits ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive

Operands:

Operand Description
split_dim tensor of 32-bit signless integer values
value tensor of 32-bit float or 16-bit signless integer or 32-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values

Results:

Result Description
outputs tensor of any type values

tfl.split_v (::mlir::TFL::SplitVOp)

Splits a tensor into num_split tensors along one dimension.

Splits the value tensor along split_dim into a number of sub-tensors with same shape as the original one, except for split_dim . The grouping of the resultant sub-tensors is decided by size-splits . Same as tf.SplitV.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
num_splits ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive

Operands:

Operand Description
value tensor of 32-bit float or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values
size_splits 1D tensor of 32-bit signless integer values
split_dim 0D tensor of 32-bit signless integer values

Results:

Result Description
outputs tensor of any type values

tfl.sqrt (::mlir::TFL::SqrtOp)

Square root operator

Computes element-wise Square root of input

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float values

Results:

Result Description
y tensor of 32-bit float values

tfl.square (::mlir::TFL::SquareOp)

Square operator

Computes element-wise Square of input

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
x tensor of 32-bit float values

Results:

Result Description
y tensor of 32-bit float values

tfl.squared_difference (::mlir::TFL::SquaredDifferenceOp)

Squared difference operator

Element-wise squared difference operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer or QI8 type values
rhs tensor of 32-bit float or 32-bit signless integer or QI8 type values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or QI8 type values

tfl.squeeze (::mlir::TFL::SqueezeOp)

Removes dimensions of size 1 from the shape of a tensor.

Given a tensor input , this operation returns a tensor of the same type with all dimensions of size 1 removed. If you don't want to remove all size 1 dimensions, you can remove specific size 1 dimensions by specifying squeeze_dims .

For example:

# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
shape(squeeze(t)) ==> [2, 3]

Or, to remove specific size 1 dimensions:

# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
shape(squeeze(t, [2, 4])) ==> [1, 2, 3, 1]

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
squeeze_dims ::mlir::ArrayAttr 64-bit integer array attribute whose size is at most 8

Operands:

Operand Description
input tensor of any type values

Results:

Result Description
output tensor of any type values

tfl.strided_slice (::mlir::TFL::StridedSliceOp)

StridedSlice Op

Return a strided slice from input .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
begin_mask ::mlir::IntegerAttr 32-bit signless integer attribute
end_mask ::mlir::IntegerAttr 32-bit signless integer attribute
ellipsis_mask ::mlir::IntegerAttr 32-bit signless integer attribute
new_axis_mask ::mlir::IntegerAttr 32-bit signless integer attribute
shrink_axis_mask ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or 1-bit signless integer or 16-bit signless integer or QI16 type or TFLite quint8 type or TFLite string type values
begin tensor of 32-bit signless integer values
end tensor of 32-bit signless integer values
strides tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or 1-bit signless integer or 16-bit signless integer or QI16 type or TFLite quint8 type or TFLite string type values

tfl.sub (::mlir::TFL::SubOp)

Subtraction operator

Element-wise subtraction operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand Description
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type values

tfl.sum (::mlir::TFL::SumOp)

Sum operator

Computes the sum reduction along the specified axes

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
axes tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.tanh (::mlir::TFL::TanhOp)

Hyperbolic tangent operator

Computes element-wise Hyperbolic tangent of input

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result Description
output tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.tile (::mlir::TFL::TileOp)

Tile operator.

Constructs a tensor by tiling a given tensor.

This operation creates a new tensor by replicating input multiples times. The output tensor's i'th dimension has input.dims(i) * multiples[i] elements, and the values of input are replicated multiples[i] times along the 'i'th dimension. For example, tiling [abcd] by [2] produces [abcdabcd].

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 1-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite string type values
multiples tensor of 32/64-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 1-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite string type values

tfl.topk_v2 (::mlir::TFL::TopKV2Op)

TopK operator

Returns the top k largest element along each last dimensional slice of input and the indices of values within the last dimension of the input tensor.

Results are always sorted in the descending order.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 8-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type values
k tensor of 32-bit signless integer values

Results:

Result Description
values tensor of 32-bit float or 8-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type values
indices tensor of 32-bit signless integer values

tfl.transpose_conv (::mlir::TFL::TransposeConvOp)

Transpose convolution operator

Performs transpose convolution operation on input.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, quant::AccumulatorUniformScale<3, 1, 2>, quant::AffineOpCoefficient<0, 1>

Interfaces: AffineQuantizedOpInterface, ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TFL_SparseOp, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
padding ::mlir::StringAttr string attribute whose value is SAME, or VALID
stride_h ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive
stride_w ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive

Operands:

Operand Description
output_shape tensor of 32-bit signless integer values
weights tensor of 32-bit float or QI8 type or QUI8 type or QI16 type values
input tensor of 32-bit float or QI8 type or QUI8 type or QI16 type values
bias tensor of any type values or none type

Results:

Result Description
output tensor of 32-bit float or QI8 type or QUI8 type or QI16 type values

tfl.transpose (::mlir::TFL::TransposeOp)

Transpose operator

Returns the Transpose of x

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit signless integer or 32-bit float or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type or 1-bit signless integer or 64-bit signless integer or QI16 type values
perm tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit signless integer or 32-bit float or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type or 1-bit signless integer or 64-bit signless integer or QI16 type values

tfl.unidirectional_sequence_lstm (::mlir::TFL::UnidirectionalSequenceLSTMOp)

Unidirectional sequence lstm operator

A recurrent neural network specified by an LSTM cell. This Op supports unrolling the input along the time or batch dimensions, and implements the following operation for each element in the sequence s = 1...sequence_length: outputs[s] = state = activation(LSTMOp(inputs[s]))

where LSTMOp is LSTM TF Lite Op and the “activation” is the function passed as the “fused_activation_function” argument (if not “NONE”).

Traits: QuantizableResult

Interfaces: DynamicRangeQuantizedOpInterface, InferTypeOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
cell_clip ::mlir::FloatAttr 32-bit float attribute whose value is non-negative
proj_clip ::mlir::FloatAttr 32-bit float attribute whose value is non-negative
time_major ::mlir::BoolAttr bool attribute
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute
input_to_input_intermediate ::mlir::TypeAttr any type attribute
input_to_forget_intermediate ::mlir::TypeAttr any type attribute
input_to_cell_intermediate ::mlir::TypeAttr any type attribute
input_to_output_intermediate ::mlir::TypeAttr any type attribute
effective_hidden_scale_intermediate ::mlir::TypeAttr any type attribute

Operands:

Operand Description
input tensor of 32-bit float values
input_to_input_weights tensor of any type values or none type
input_to_forget_weights tensor of 32-bit float or QI8 type values
input_to_cell_weights tensor of 32-bit float or QI8 type values
input_to_output_weights tensor of 32-bit float or QI8 type values
recurrent_to_input_weights tensor of any type values or none type
recurrent_to_forget_weights tensor of 32-bit float or QI8 type values
recurrent_to_cell_weights tensor of 32-bit float or QI8 type values
recurrent_to_output_weights tensor of 32-bit float or QI8 type values
cell_to_input_weights tensor of any type values or none type
cell_to_forget_weights tensor of any type values or none type
cell_to_output_weights tensor of any type values or none type
input_gate_bias tensor of any type values or none type
forget_gate_bias tensor of 32-bit float values
cell_bias tensor of 32-bit float values
output_gate_bias tensor of 32-bit float values
projection_weights tensor of any type values or none type
projection_bias tensor of any type values or none type
input_activation_state stateful tensor
input_cell_state stateful tensor
input_layer_norm_coefficients tensor of any type values or none type
forget_layer_norm_coefficients tensor of any type values or none type
cell_layer_norm_coefficients tensor of any type values or none type
output_layer_norm_coefficients tensor of any type values or none type

Results:

Result Description
output tensor of 32-bit float or QI8 type values

tfl.unidirectional_sequence_rnn (::mlir::TFL::UnidirectionalSequenceRNNOp)

Unidirectional sequence rnn operator

A recurrent neural network specified by an RNN cell. This Op takes in input in a format {batch_size, seq_len, input_size} or {seq_len, batch_size, input_size} if it's time-majored.

It implements the following operation for each element in the sequence s = 1...sequence_length: outputs[s] = state = activation(RNNOp(inputs[s]))

where RNNOp is RNNOp TF Lite Op and the “activation” is the function passed as the “fused_activation_function” argument (if not “NONE”).

Traits: QuantizableResult

Interfaces: DynamicRangeQuantizedOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
time_major ::mlir::BoolAttr bool attribute
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of 32-bit float values
input_to_input_weights tensor of 32-bit float or QI8 type values
recurrent_to_input_weights tensor of 32-bit float or QI8 type values
input_gate_bias tensor of 32-bit float values
hidden_state stateful tensor

Results:

Result Description
output tensor of 32-bit float values

tfl.unique (::mlir::TFL::UniqueOp)

Unique Op.

This operation returns a tensor output containing all of the unique elements of input sorted in the same order that they occur in input . This operation also returns a tensor idx the same size as x that contains the index of each value of input in the unique output output . In other words:

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
idx_out_type ::mlir::Attribute derived attribute

Operands:

Operand Description
input tensor of 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or 16-bit signless integer or QI16 type or 32-bit signless integer or 64-bit signless integer or 32-bit float values

Results:

Result Description
output tensor of 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or 16-bit signless integer or QI16 type or 32-bit signless integer or 64-bit signless integer or 32-bit float values
idx tensor of 32/64-bit signless integer values

tfl.unpack (::mlir::TFL::UnpackOp)

Unpacks a tensor along a dimension into multiple tensors

Unpacks a given dimension of a rank- R tensor into num rank- (R-1) tensors.

Unpacks num tensors from value by chipping it along the axis dimension. For example, given a tensor of shape (A, B, C, D) ;

If axis == 0 then the i'th tensor in output is the slice value[i, :, :, :] and each tensor in output will have shape (B, C, D) . (Note that the dimension unpacked along is gone, unlike split ).

If axis == 1 then the i'th tensor in output is the slice value[:, i, :, :] and each tensor in output will have shape (A, C, D) . Etc.

This is the opposite of pack .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultElementType

Interfaces: ConditionallySpeculatable, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type Description
num ::mlir::IntegerAttr 32-bit signless integer attribute whose value is non-negative
axis ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand Description
input tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 32-bit signless integer or QI8 type or QUI8 type or 16-bit signless integer or QI16 type values

Results:

Result Description
outputs tensor of any type values

tfl.unsorted_segment_max (::mlir::TFL::UnsortedSegmentMaxOp)

UnsortedSegmentMax operator

Computes the maximum value along segments of a tensor such that output[i] = max(data[j....]) where segment_ids[j...] = i if the maximum is empty for a given segment ID i, it outputs the smallest possible value for the specific numeric type, output[i] = numeric_limits::lowest(). Note the values of segment_ids are always validated to be less than num_segments and an error is thrown for out-of-bound indices.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values
num_segments tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer values

tfl.unsorted_segment_min (::mlir::TFL::UnsortedSegmentMinOp)

UnsortedSegmentMin operator

Computes the minimum value along segments of a tensor such that output[i] = min(data[j....]) where segment_ids[j...] = i if the minimum is empty for a given segment ID i, it outputs the largest possible value for the specific numeric type, output[i] = numeric_limits::max(). Note the values of segment_ids are always validated to be less than num_segments and an error is thrown for out-of-bound indices.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values
num_segments tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer values

tfl.unsorted_segment_prod (::mlir::TFL::UnsortedSegmentProdOp)

UnsortedSegmentProd operator

Computes the product along segments of a tensor.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values
num_segments tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer values

tfl.unsorted_segment_sum (::mlir::TFL::UnsortedSegmentSumOp)

UnsortedSegmentSum operator

From a tensor segmentation, computes the output resulting from summing together elements mapped to the same segment_id. Ie output[i] is equal to the tensor sum of all elements from the input tensor mapped to segment_id i . If no tensors are mapped to a particular included segment_id, the output at that indice will be a zero tensor with the appropriate shape. Note the values of segment_ids are always validated to be less than num_segments and an error is thrown for out-of-bound indices

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values
num_segments tensor of 32-bit signless integer values

Results:

Result Description
output tensor of 32-bit float or 32-bit signless integer values

tfl.var_handle (::mlir::TFL::VarHandleOp)

Returns a handle to a variable resource from its name.

Returns a handle for a variable resource from its name. container: the container this variable is placed in. shared_name: the name by which this variable is referred to.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
container ::mlir::StringAttr string attribute
shared_name ::mlir::StringAttr string attribute

Results:

Result Description
resource_handle tensor of resource values

tfl.where (::mlir::TFL::WhereOp)

Returns locations of nonzero / true values in a tensor.

This operation returns the coordinates of true elements in condition . The coordinates are returned in a 2-D tensor where the first dimension (rows) represents the number of true elements, and the second dimension (columns) represents the coordinates of the true elements. Keep in mind, the shape of the output tensor can vary depending on how many true values there are in condition . Indices are output in row-major order.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
condition tensor of 1-bit signless integer or 32-bit float or 32/64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 32-bit unsigned integer values

Results:

Result Description
index tensor of 64-bit signless integer values

tfl.while (::mlir::TFL::WhileOp)

While loop

output = input; while (cond(output)) { output = body(output) }

While loop where all values are passes through arguments with implicit capture.

input: A list of input tensors whose types are T. output: A list of output tensors whose types are T. cond: A region that takes 'input' and returns a boolean scalar tensor. body: A region that takes a list of tensors and returns another list of tensors. Both lists have the same types.

Traits: SingleBlockImplicitTerminator

Interfaces: LoopLikeOpInterface, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type Description
is_stateless ::mlir::BoolAttr bool attribute

Operands:

Operand Description
input tensor of any type values

Results:

Result Description
output tensor of any type values

tfl.yield (::mlir::TFL::YieldOp)

Yield operation

The "yield" operation represents a return operation within the conditional and body of structured control flow (eg, while), and a terminator for ControlNodeOp. The operation takes a variable number of operands and produces no results. The operand number and types must match the signature of the region that contains the operation.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, Terminator

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
operands any type

tfl.zeros_like (::mlir::TFL::ZerosLikeOp)

ZerosLike operator

Returns a tensor of zeros with the same shape and type as the input tensor.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand Description
input tensor of 64-bit signless integer or 32-bit signless integer or 32-bit float values

Results:

Result Description
output tensor of 64-bit signless integer or 32-bit signless integer or 32-bit float values

Attribute definition

DimensionMetadataAttr

Dimension metadata.

Syntax:

!tfl.dimension_metadata<
  ::mlir::TFL::DimensionTypeAttr,   # format
  int32_t,   # dense_size
  ::llvm::ArrayRef<int32_t>,   # segments
  ::llvm::ArrayRef<int32_t>   # indices
>

Parameters:

Parameter C++ type Description
format ::mlir::TFL::DimensionTypeAttr dimension_type
dense_size int32_t
segments ::llvm::ArrayRef<int32_t>
indices ::llvm::ArrayRef<int32_t>

SparsityParameterAttr

Sparsity parameter.

Syntax:

!tfl.sparsity_parameter<
  ::llvm::ArrayRef<int32_t>,   # traversal_order
  ::llvm::ArrayRef<int32_t>,   # block_map
  ::llvm::ArrayRef<DimensionMetadataAttr>   # dim_metadata
>

Parameters:

Parameter C++ type Description
traversal_order ::llvm::ArrayRef<int32_t>
block_map ::llvm::ArrayRef<int32_t>
dim_metadata ::llvm::ArrayRef<DimensionMetadataAttr>

ConstBytesAttr

A string attribute representation of compiled bytes

Syntax Examples:

#tfl<const_bytes : "0xDEADBEEF">

Parameters:

Parameter C++ type Description
value ::llvm::StringRef

DimensionTypeAttr

dimension_type

Syntax:

!tfl.dimension_type_attr<
  ::mlir::TFL::DimensionType   # value
>

Parameters:

Parameter C++ type Description
value ::mlir::TFL::DimensionType an enum of type DimensionType

LSTMKernelTypeAttr

lstm_kernel_type

Syntax:

!tfl.lstm_kernel_type_attr<
  ::mlir::TFL::LSTMKernelType   # value
>

Parameters:

Parameter C++ type Description
value ::mlir::TFL::LSTMKernelType an enum of type LSTMKernelType

MirrorPaddingTypeAttr

mirror_pad_enum

Syntax:

!tfl.mirror_pad_attr<
  ::mlir::TFL::MirrorPaddingType   # value
>

Parameters:

Parameter C++ type Description
value ::mlir::TFL::MirrorPaddingType an enum of type MirrorPaddingType