 Посмотреть на TensorFlow.org |  Запускаем в Google Colab |  Посмотреть исходный код на GitHub |  Скачать блокнот |
TensorFlow Lite Authoring API предоставляет возможность поддерживать ваше tf.function модель с TensorFlow совместит Lite.
Настраивать
import tensorflow as tf
Проблема совместимости TensorFlow с TensorFlow Lite
Если вы хотите использовать свою модель TF на устройствах, вам необходимо преобразовать ее в модель TFLite, чтобы использовать ее из интерпретатора TFLite. Во время преобразования вы можете столкнуться с ошибкой совместимости из-за неподдерживаемых операций TensorFlow встроенным набором операций TFLite.
Это своего рода неприятная проблема. Как можно обнаружить это раньше, как время разработки модели?
Обратите внимание , что следующий код будет терпеть неудачу на converter.convert() вызова.
@tf.function(input_signature=[
tf.TensorSpec(shape=[None], dtype=tf.float32)
])
def f(x):
return tf.cosh(x)
# Evaluate the tf.function
result = f(tf.constant([0.0]))
print (f"result = {result}")
result = [1.]
# Convert the tf.function
converter = tf.lite.TFLiteConverter.from_concrete_functions(
[f.get_concrete_function()], f)
try:
fb_model = converter.convert()
except Exception as e:
print(f"Got an exception: {e}")
Got an exception: /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:746:0: error: 'tf.Cosh' op is neither a custom op nor a flex op
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py:2538:0: note: called from
/tmp/ipykernel_11095/885400331.py:5:0: note: called from
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py:1125:0: note: called from
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py:672:0: note: called from
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py:1143:0: note: called from
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py:3402:0: note: called from
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py:3557:0: note: called from
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py:3157:0: note: called from
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py:781:0: note: called from
/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:746:0: note: Error code: ERROR_NEEDS_FLEX_OPS
<unknown>:0: error: failed while converting: 'main':
Some ops are not supported by the native TFLite runtime, you can enable TF kernels fallback using TF Select. See instructions: https://www.tensorflow.org/lite/guide/ops_select
TF Select ops: Cosh
Details:
tf.Cosh(tensor<?xf32>) -> (tensor<?xf32>) : {device = ""}
2021-11-15 12:14:34.777684: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:363] Ignored output_format.
2021-11-15 12:14:34.777724: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:366] Ignored drop_control_dependency.
loc(callsite("Cosh"("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py":746:0) at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py":2538:0 at callsite("/tmp/ipykernel_11095/885400331.py":5:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1125:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":672:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1143:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3402:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3557:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3157:0 at "/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":781:0)))))))))): error: 'tf.Cosh' op is neither a custom op nor a flex op
error: failed while converting: 'main':
Some ops are not supported by the native TFLite runtime, you can enable TF kernels fallback using TF Select. See instructions: https://www.tensorflow.org/lite/guide/ops_select
TF Select ops: Cosh
Details:
tf.Cosh(tensor<?xf32>) -> (tensor<?xf32>) : {device = ""}
Использование Simple Target Aware Authoring
Мы представили Authoring API для обнаружения проблемы совместимости с TensorFlow Lite во время разработки модели.
Вам просто нужно добавить @tf.lite.experimental.authoring.compatible декоратора обернуть tf.function модель для проверки совместимости TFLite.
После этого совместимость будет проверяться автоматически при оценке вашей модели.
@tf.lite.experimental.authoring.compatible
@tf.function(input_signature=[
tf.TensorSpec(shape=[None], dtype=tf.float32)
])
def f(x):
return tf.cosh(x)
# Evaluate the tf.function
result = f(tf.constant([0.0]))
print (f"result = {result}")
COMPATIBILITY WARNING: op 'tf.Cosh' require(s) "Select TF Ops" for model conversion for TensorFlow Lite. https://www.tensorflow.org/lite/guide/ops_select
Op: tf.Cosh
- /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:746
- /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py:2538
- /tmp/ipykernel_11095/885400331.py:5
result = [1.]
2021-11-15 12:14:34.816991: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:363] Ignored output_format.
2021-11-15 12:14:34.817023: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:366] Ignored drop_control_dependency.
loc(callsite("Cosh"("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py":746:0) at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py":2538:0 at callsite("/tmp/ipykernel_11095/885400331.py":5:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1125:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":672:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1143:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3402:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3557:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3157:0 at "/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":781:0)))))))))): error: 'tf.Cosh' op is neither a custom op nor a flex op
error: failed while converting: 'main':
Some ops are not supported by the native TFLite runtime, you can enable TF kernels fallback using TF Select. See instructions: https://www.tensorflow.org/lite/guide/ops_select
TF Select ops: Cosh
Details:
tf.Cosh(tensor<?xf32>) -> (tensor<?xf32>) : {device = ""}
Если какая - либо проблема совместимости TensorFlow Lite будет найден, он будет показывать COMPATIBILITY WARNING или COMPATIBILITY ERROR с точным расположением проблемного цит. В этом примере показано расположение tf.Cosh оп в модели tf.function.
Вы также можете проверить журнал Совместимость с <function_name>.get_compatibility_log() метод.
compatibility_log = '\n'.join(f.get_compatibility_log())
print (f"compatibility_log = {compatibility_log}")
compatibility_log = COMPATIBILITY WARNING: op 'tf.Cosh' require(s) "Select TF Ops" for model conversion for TensorFlow Lite. https://www.tensorflow.org/lite/guide/ops_select Op: tf.Cosh - /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:746 - /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py:2538 - /tmp/ipykernel_11095/885400331.py:5
Поднимите исключение из-за несовместимости
Вы можете предоставить возможность на @tf.lite.experimental.authoring.compatible декоратора. raise_exception вариант дает исключение , когда вы пытаетесь оценить декорированную модель.
@tf.lite.experimental.authoring.compatible(raise_exception=True)
@tf.function(input_signature=[
tf.TensorSpec(shape=[None], dtype=tf.float32)
])
def f(x):
return tf.cosh(x)
# Evaluate the tf.function
try:
result = f(tf.constant([0.0]))
print (f"result = {result}")
except Exception as e:
print(f"Got an exception: {e}")
COMPATIBILITY WARNING: op 'tf.Cosh' require(s) "Select TF Ops" for model conversion for TensorFlow Lite. https://www.tensorflow.org/lite/guide/ops_select
Op: tf.Cosh
- /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:746
- /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py:2538
- /tmp/ipykernel_11095/885400331.py:5
Got an exception: CompatibilityException at <tensorflow.python.eager.def_function.Function object at 0x7ff2e016fc50>
2021-11-15 12:14:34.863629: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:363] Ignored output_format.
2021-11-15 12:14:34.863657: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:366] Ignored drop_control_dependency.
loc(callsite("Cosh"("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py":746:0) at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py":2538:0 at callsite("/tmp/ipykernel_11095/885400331.py":5:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1125:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":672:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1143:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3402:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3557:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3157:0 at "/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":781:0)))))))))): error: 'tf.Cosh' op is neither a custom op nor a flex op
error: failed while converting: 'main':
Some ops are not supported by the native TFLite runtime, you can enable TF kernels fallback using TF Select. See instructions: https://www.tensorflow.org/lite/guide/ops_select
TF Select ops: Cosh
Details:
tf.Cosh(tensor<?xf32>) -> (tensor<?xf32>) : {device = ""}
Указание использования "Select TF ops"
Если вы уже в курсе Выберите TF ОПС использования, вы можете сказать , что это к API Authoring установки converter_target_spec . Это тот же tf.lite.TargetSpec объект , который вы будете использовать его для tf.lite.TFLiteConverter API.
target_spec = tf.lite.TargetSpec()
target_spec.supported_ops = [
tf.lite.OpsSet.TFLITE_BUILTINS,
tf.lite.OpsSet.SELECT_TF_OPS,
]
@tf.lite.experimental.authoring.compatible(converter_target_spec=target_spec, raise_exception=True)
@tf.function(input_signature=[
tf.TensorSpec(shape=[None], dtype=tf.float32)
])
def f(x):
return tf.cosh(x)
# Evaluate the tf.function
result = f(tf.constant([0.0]))
print (f"result = {result}")
2021-11-15 12:14:34.921628: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:363] Ignored output_format.
WARNING:absl:Buffer deduplication procedure will be skipped when flatbuffer library is not properly loaded
result = [1.]
2021-11-15 12:14:34.921661: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:366] Ignored drop_control_dependency.
2021-11-15 12:14:34.934915: 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: FlexCosh
Details:
tf.Cosh(tensor<?xf32>) -> (tensor<?xf32>) : {device = ""}
See instructions: https://www.tensorflow.org/lite/guide/ops_select
Проверка совместимости GPU
Если вы хотите, чтобы ваша модель совместим с GPU делегатом от TensorFlow Lite, вы можете установить experimental_supported_backends из tf.lite.TargetSpec .
В следующем примере показано, как обеспечить совместимость вашей модели с делегированием графического процессора. Обратите внимание, что у этой модели есть проблемы с совместимостью, поскольку она использует двумерный тензор с оператором tf.slice и неподдерживаемым оператором tf.cosh. Вы увидите два COMPATIBILITY WARNING с информацией о местоположении.
target_spec = tf.lite.TargetSpec()
target_spec.supported_ops = [
tf.lite.OpsSet.TFLITE_BUILTINS,
tf.lite.OpsSet.SELECT_TF_OPS,
]
target_spec.experimental_supported_backends = ["GPU"]
@tf.lite.experimental.authoring.compatible(converter_target_spec=target_spec)
@tf.function(input_signature=[
tf.TensorSpec(shape=[4, 4], dtype=tf.float32)
])
def func(x):
y = tf.cosh(x)
return y + tf.slice(x, [1, 1], [1, 1])
result = func(tf.ones(shape=(4,4), dtype=tf.float32))
'tfl.slice' op is not GPU compatible: SLICE supports for 3 or 4 dimensional tensors only, but node has 2 dimensional tensors.
- /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py:1096
- /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/util/traceback_utils.py:150
- /tmp/ipykernel_11095/3833138856.py:13
'tf.Cosh' op is not GPU compatible: Not supported custom op FlexCosh
- /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:746
- /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py:2538
- /tmp/ipykernel_11095/3833138856.py:12
COMPATIBILITY WARNING: op 'tf.Cosh, tfl.slice' aren't compatible with TensorFlow Lite GPU delegate. https://www.tensorflow.org/lite/performance/gpu
2021-11-15 12:14:34.998044: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:363] Ignored output_format.
2021-11-15 12:14:34.998077: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:366] Ignored drop_control_dependency.
2021-11-15 12:14:35.012457: 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: FlexCosh
Details:
tf.Cosh(tensor<4x4xf32>) -> (tensor<4x4xf32>) : {device = ""}
See instructions: https://www.tensorflow.org/lite/guide/ops_select
loc(callsite("Cosh"("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py":746:0) at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py":2538:0 at callsite("/tmp/ipykernel_11095/3833138856.py":12:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1125:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":672:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1143:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3402:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3557:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3157:0 at "/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":781:0)))))))))): error: 'tf.Cosh' op is not GPU compatible: Not supported custom op FlexCosh
loc(callsite("Slice"("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py":1096:0) at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/util/traceback_utils.py":150:0 at callsite("/tmp/ipykernel_11095/3833138856.py":13:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1125:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":672:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py":1143:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3402:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3557:0 at callsite("/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/function.py":3157:0 at "/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py":781:0)))))))))): error: 'tfl.slice' op is not GPU compatible: SLICE supports for 3 or 4 dimensional tensors only, but node has 2 dimensional tensors.
Читать далее
Для получения дополнительной информации, пожалуйста, обратитесь к: