Bantuan melindungi Great Barrier Reef dengan TensorFlow pada Kaggle Bergabung Tantangan

Tanda tangan di TensorFlow Lite

Lihat di TensorFlow.org Jalankan di Google Colab Lihat sumber di GitHub Unduh buku catatan

TensorFlow Lite mendukung konversi spesifikasi input/output model TensorFlow ke model TensorFlow Lite. Spesifikasi input/output disebut "tanda tangan". Tanda tangan dapat ditentukan saat membangun SavedModel atau membuat fungsi konkret.

Tanda tangan di TensorFlow Lite menyediakan fitur berikut:

  • Mereka menentukan input dan output dari model TensorFlow Lite yang dikonversi dengan menghormati tanda tangan model TensorFlow.
  • Izinkan satu model TensorFlow Lite untuk mendukung beberapa titik masuk.

Tanda tangan terdiri dari tiga bagian:

  • Input: Memetakan input dari nama input dalam tanda tangan ke tensor input.
  • Keluaran: Petakan pemetaan keluaran dari nama keluaran dalam tanda tangan ke tensor keluaran.
  • Signature Key: Nama yang mengidentifikasi titik masuk grafik.

Mempersiapkan

import tensorflow as tf

Contoh model

Katakanlah kita memiliki dua tugas, misalnya, encoding dan decoding, sebagai model TensorFlow:

class Model(tf.Module):

  @tf.function(input_signature=[tf.TensorSpec(shape=[None], dtype=tf.float32)])
  def encode(self, x):
    result = tf.strings.as_string(x)
    return {
         "encoded_result": result
    }

  @tf.function(input_signature=[tf.TensorSpec(shape=[None], dtype=tf.string)])
  def decode(self, x):
    result = tf.strings.to_number(x)
    return {
         "decoded_result": result
    }

Dari segi tanda tangan, model TensorFlow di atas dapat diringkas sebagai berikut:

  • Tanda tangan

    • Kunci: enkode
    • Masukan: {"x"}
    • Keluaran: {"encoded_result"}
  • Tanda tangan

    • Kunci: memecahkan kode
    • Masukan: {"x"}
    • Keluaran: {"decoded_result"}

Mengonversi model dengan Tanda Tangan

API konverter TensorFlow Lite akan membawa informasi tanda tangan di atas ke dalam model TensorFlow Lite yang dikonversi.

Fungsionalitas konversi ini tersedia di semua API konverter mulai dari TensorFlow versi 2.7.0. Lihat contoh penggunaan.

Dari Model Tersimpan

model = Model()

# Save the model
SAVED_MODEL_PATH = 'content/saved_models/coding'

tf.saved_model.save(
    model, SAVED_MODEL_PATH,
    signatures={
      'encode': model.encode.get_concrete_function(),
      'decode': model.decode.get_concrete_function()
    })

# Convert the saved model using TFLiteConverter
converter = tf.lite.TFLiteConverter.from_saved_model(SAVED_MODEL_PATH)
converter.target_spec.supported_ops = [
    tf.lite.OpsSet.TFLITE_BUILTINS,  # enable TensorFlow Lite ops.
    tf.lite.OpsSet.SELECT_TF_OPS  # enable TensorFlow ops.
]
tflite_model = converter.convert()

# Print the signatures from the converted model
interpreter = tf.lite.Interpreter(model_content=tflite_model)
signatures = interpreter.get_signature_list()
print(signatures)
2021-11-15 12:17:48.388332: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
INFO:tensorflow:Assets written to: content/saved_models/coding/assets
2021-11-15 12:17:48.727484: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:363] Ignored output_format.
2021-11-15 12:17:48.727522: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:366] Ignored drop_control_dependency.
WARNING:absl:Buffer deduplication procedure will be skipped when flatbuffer library is not properly loaded
2021-11-15 12:17:48.727529: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:372] Ignored change_concat_input_ranges.
2021-11-15 12:17:48.767576: W tensorflow/compiler/mlir/lite/flatbuffer_export.cc:1891] TFLite interpreter needs to link Flex delegate in order to run the model since it contains the following Select TFop(s):
Flex ops: FlexAsString, FlexStringToNumber
Details:
    tf.AsString(tensor<?xf32>) -> (tensor<?x!tf_type.string>) : {device = "", fill = "", precision = -1 : i64, scientific = false, shortest = false, width = -1 : i64}
    tf.StringToNumber(tensor<?x!tf_type.string>) -> (tensor<?xf32>) : {device = "", out_type = f32}
See instructions: https://www.tensorflow.org/lite/guide/ops_select
{'decode': {'inputs': ['x'], 'outputs': ['decoded_result']}, 'encode': {'inputs': ['x'], 'outputs': ['encoded_result']} }
INFO: Created TensorFlow Lite delegate for select TF ops.
INFO: TfLiteFlexDelegate delegate: 1 nodes delegated out of 1 nodes with 1 partitions.

Dari Keras Model

# Generate a Keras model.
keras_model = tf.keras.Sequential(
    [
        tf.keras.layers.Dense(2, input_dim=4, activation='relu', name='x'),
        tf.keras.layers.Dense(1, activation='relu', name='output'),
    ]
)

# Convert the keras model using TFLiteConverter.
# Keras model converter API uses the default signature automatically.
converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
tflite_model = converter.convert()

# Print the signatures from the converted model
interpreter = tf.lite.Interpreter(model_content=tflite_model)

signatures = interpreter.get_signature_list()
print(signatures)
INFO:tensorflow:Assets written to: /tmp/tmplhr7j714/assets
INFO:tensorflow:Assets written to: /tmp/tmplhr7j714/assets
2021-11-15 12:17:49.368226: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:363] Ignored output_format.
2021-11-15 12:17:49.368264: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:366] Ignored drop_control_dependency.
WARNING:absl:Buffer deduplication procedure will be skipped when flatbuffer library is not properly loaded
{'serving_default': {'inputs': ['x_input'], 'outputs': ['output']} }

Dari Fungsi Beton

model = Model()

# Convert the concrete functions using TFLiteConverter
converter = tf.lite.TFLiteConverter.from_concrete_functions(
    [model.encode.get_concrete_function(),
     model.decode.get_concrete_function()], model)
converter.target_spec.supported_ops = [
    tf.lite.OpsSet.TFLITE_BUILTINS,  # enable TensorFlow Lite ops.
    tf.lite.OpsSet.SELECT_TF_OPS  # enable TensorFlow ops.
]
tflite_model = converter.convert()

# Print the signatures from the converted model
interpreter = tf.lite.Interpreter(model_content=tflite_model)
signatures = interpreter.get_signature_list()
print(signatures)
INFO:tensorflow:Assets written to: /tmp/tmpc14_l70o/assets
INFO:tensorflow:Assets written to: /tmp/tmpc14_l70o/assets
2021-11-15 12:17:49.538814: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:363] Ignored output_format.
2021-11-15 12:17:49.538850: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:366] Ignored drop_control_dependency.
WARNING:absl:Buffer deduplication procedure will be skipped when flatbuffer library is not properly loaded
{'decode': {'inputs': ['x'], 'outputs': ['decoded_result']}, 'encode': {'inputs': ['x'], 'outputs': ['encoded_result']} }
2021-11-15 12:17:49.572773: W tensorflow/compiler/mlir/lite/flatbuffer_export.cc:1891] TFLite interpreter needs to link Flex delegate in order to run the model since it contains the following Select TFop(s):
Flex ops: FlexAsString, FlexStringToNumber
Details:
    tf.AsString(tensor<?xf32>) -> (tensor<?x!tf_type.string>) : {device = "", fill = "", precision = -1 : i64, scientific = false, shortest = false, width = -1 : i64}
    tf.StringToNumber(tensor<?x!tf_type.string>) -> (tensor<?xf32>) : {device = "", out_type = f32}
See instructions: https://www.tensorflow.org/lite/guide/ops_select

Jalankan Tanda Tangan

API inferensi TensorFlow mendukung eksekusi berbasis tanda tangan:

  • Mengakses tensor input/output melalui nama input dan output, yang ditentukan oleh tanda tangan.
  • Menjalankan setiap titik masuk grafik secara terpisah, yang diidentifikasi oleh kunci tanda tangan.
  • Dukungan untuk prosedur inisialisasi SavedModel.

Binding bahasa Java, C++ dan Python saat ini tersedia. Lihat contoh bagian di bawah ini.

Jawa

try (Interpreter interpreter = new Interpreter(file_of_tensorflowlite_model)) {
  // Run encoding signature.
  Map<String, Object> inputs = new HashMap<>();
  inputs.put("x", input);
  Map<String, Object> outputs = new HashMap<>();
  outputs.put("encoded_result", encoded_result);
  interpreter.runSignature(inputs, outputs, "encode");

  // Run decoding signature.
  Map<String, Object> inputs = new HashMap<>();
  inputs.put("x", encoded_result);
  Map<String, Object> outputs = new HashMap<>();
  outputs.put("decoded_result", decoded_result);
  interpreter.runSignature(inputs, outputs, "decode");
}

C++

SignatureRunner* encode_runner =
    interpreter->GetSignatureRunner("encode");
encode_runner->ResizeInputTensor("x", {100});
encode_runner->AllocateTensors();

TfLiteTensor* input_tensor = encode_runner->input_tensor("x");
float* input = input_tensor->data.f;
// Fill `input`.

encode_runner->Invoke();

const TfLiteTensor* output_tensor = encode_runner->output_tensor(
    "encoded_result");
float* output = output_tensor->data.f;
// Access `output`.

Python

# Load the TFLite model in TFLite Interpreter
interpreter = tf.lite.Interpreter(model_content=tflite_model)

# Print the signatures from the converted model
signatures = interpreter.get_signature_list()
print('Signature:', signatures)

# encode and decode are callable with input as arguments.
encode = interpreter.get_signature_runner('encode')
decode = interpreter.get_signature_runner('decode')

# 'encoded' and 'decoded' are dictionaries with all outputs from the inference.
input = tf.constant([1, 2, 3], dtype=tf.float32)
print('Input:', input)
encoded = encode(x=input)
print('Encoded result:', encoded)
decoded = decode(x=encoded['encoded_result'])
print('Decoded result:', decoded)
Signature: {'decode': {'inputs': ['x'], 'outputs': ['decoded_result']}, 'encode': {'inputs': ['x'], 'outputs': ['encoded_result']} }
Input: tf.Tensor([1. 2. 3.], shape=(3,), dtype=float32)
Encoded result: {'encoded_result': array([b'1.000000', b'2.000000', b'3.000000'], dtype=object)}
Decoded result: {'decoded_result': array([1., 2., 3.], dtype=float32)}

Batasan yang diketahui

  • Karena juru bahasa TFLite tidak menjamin keamanan utas, runner tanda tangan dari juru bahasa yang sama tidak akan dieksekusi secara bersamaan.
  • Dukungan untuk C/iOS/Swift belum tersedia.

Pembaruan

  • Versi 2.7
    • Fitur beberapa tanda tangan diimplementasikan.
    • Semua API konverter dari versi dua menghasilkan model TensorFlow Lite yang mendukung tanda tangan.
  • Versi 2.5
    • Signature fitur yang tersedia melalui from_saved_model converter API.