 Voir sur TensorFlow.org |  Exécuter dans Google Colab |  Voir la source sur GitHub |  Télécharger le cahier |
Tensorflow API Lite Authoring fournit un moyen de maintenir vos tf.function modèles avec tensorflow Lite COMPATIBILE.
Installer
import tensorflow as tf
Problème de compatibilité entre TensorFlow et TensorFlow Lite
Si vous souhaitez utiliser votre modèle TF sur des appareils, vous devez le convertir en modèle TFLite pour l'utiliser à partir de l'interpréteur TFLite. Au cours de la conversion, vous pouvez rencontrer une erreur de compatibilité en raison d'opérations TensorFlow non prises en charge par l'ensemble d'opérations intégré TFLite.
C'est une sorte de problème ennuyeux. Comment pouvez-vous le détecter plus tôt comme l'heure de création du modèle ?
Notez que le code suivant échouera sur le converter.convert() appel.
@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 = ""}
Utilisation de la création simple et consciente de la cible
Nous avons introduit l'API de création pour détecter le problème de compatibilité TensorFlow Lite pendant la création du modèle.
Vous avez juste besoin d'ajouter @tf.lite.experimental.authoring.compatible décorateur pour envelopper votre tf.function modèle pour vérifier la compatibilité TFLite.
Après cela, la compatibilité sera vérifiée automatiquement lorsque vous évaluerez votre modèle.
@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 = ""}
Si tout problème de compatibilité tensorflow Lite se trouve, il affichera COMPATIBILITY WARNING ou COMPATIBILITY ERROR à l'emplacement exact de la problématique op. Dans cet exemple, il montre l'emplacement tf.Cosh op dans votre modèle tf.function.
Vous pouvez également consulter le journal de la compatiblité <function_name>.get_compatibility_log() méthode.
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
Lever une exception pour une incompatibilité
Vous pouvez fournir une option au @tf.lite.experimental.authoring.compatible décorateur. La raise_exception option vous donne une exception lorsque vous essayez d'évaluer le modèle décoré.
@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 = ""}
Spécification de l'utilisation de « Sélectionner les opérations TF »
Si vous êtes déjà au courant de Select TF ops utilisation, vous pouvez le dire à l'API Création en définissant converter_target_spec . Il est le même tf.lite.TargetSpec objet que vous allez l' utiliser pour 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
Vérification de la compatibilité GPU
Si vous voulez vous assurer que votre modèle est avec compatibile délégué GPU de tensorflow Lite, vous pouvez définir experimental_supported_backends de tf.lite.TargetSpec .
L'exemple suivant montre comment garantir la compatibilité des délégués GPU de votre modèle. Notez que ce modèle présente des problèmes de compatibilité car il utilise un tenseur 2D avec l'opérateur tf.slice et l'opérateur tf.cosh non pris en charge. Vous verrez deux COMPATIBILITY WARNING avec les informations de localisation.
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.
Lire la suite
Pour plus d'informations, veuillez vous référer à: