Zobacz na TensorFlow.org | Uruchom w Google Colab | Wyświetl źródło na GitHub | Pobierz notatnik |
TensorFlow Lite Authoring API zapewnia sposób utrzymać tf.function
modele kompatybilne z TensorFlow Lite.
Ustawiać
import tensorflow as tf
Problem ze zgodnością TensorFlow z TensorFlow Lite
Jeśli chcesz używać swojego modelu TF na urządzeniach, musisz przekonwertować go na model TFLite, aby użyć go z interpretera TFLite. Podczas konwersji możesz napotkać błąd zgodności z powodu nieobsługiwanych operacji TensorFlow przez wbudowany zestaw operacji TFLite.
To rodzaj irytującego problemu. Jak można to wcześniej wykryć, np. czas tworzenia modelu?
Należy pamiętać, że poniższy kod nie powiedzie się na converter.convert()
rozmowy.
@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 = ""}
Użycie prostego tworzenia z uwzględnieniem celu
Wprowadziliśmy Authoring API, aby wykryć problem ze zgodnością TensorFlow Lite podczas tworzenia modelu.
Trzeba tylko dodać @tf.lite.experimental.authoring.compatible
dekoratora owinąć tf.function
modelu, aby sprawdzić kompatybilność TFLite.
Następnie zgodność zostanie automatycznie sprawdzona podczas oceny modelu.
@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 = ""}
Jeżeli którykolwiek TensorFlow Lite kompatybilność problem został znaleziony, to pokaże COMPATIBILITY WARNING
lub COMPATIBILITY ERROR
z dokładnym położeniem problematycznego op. W tym przykładzie pokazuje lokalizację tf.Cosh
op w modelu tf.function.
Można również sprawdzić dziennik Kompatybilność z <function_name>.get_compatibility_log()
metody.
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
Zgłoś wyjątek za niezgodność
Można przewidywać opcję na @tf.lite.experimental.authoring.compatible
dekoratora. raise_exception
opcja daje wyjątek, gdy starasz się ocenić zdobione model.
@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 = ""}
Określanie użycia opcji „Wybierz TF ops”
Jeśli jesteś już świadomy Wybierz TF ops użytkowania, można powiedzieć to API Authoring ustawiając converter_target_spec
. To samo tf.lite.TargetSpec obiekt będzie można używać go na 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
Sprawdzanie zgodności GPU
Jeśli chcesz, aby zapewnić, że model jest kompatybilny z delegatem GPU z TensorFlow Lite można ustawić experimental_supported_backends
z tf.lite.TargetSpec .
Poniższy przykład pokazuje, jak zapewnić zgodność delegata GPU modelu. Zauważ, że ten model ma problemy ze zgodnością, ponieważ używa tensora 2D z operatorem tf.slice i nieobsługiwanym operatorem tf.cosh. Zobaczysz dwa COMPATIBILITY WARNING
z informacji o lokalizacji.
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.
Czytaj więcej
Aby uzyskać więcej informacji, zapoznaj się z: