أداة تأليف TFLite

عرض على TensorFlow.org تشغيل في Google Colab عرض المصدر على جيثب تحميل دفتر

يوفر TensorFlow لايت التأليف API وسيلة للحفاظ على الخاص tf.function نماذج Compatibile مع TensorFlow لايت.

يثبت

import tensorflow as tf

مشكلة توافق TensorFlow مع TensorFlow Lite

إذا كنت ترغب في استخدام نموذج TF الخاص بك على الأجهزة ، فأنت بحاجة إلى تحويله إلى نموذج TFLite لاستخدامه من مترجم TFLite. أثناء التحويل ، قد تواجه خطأ في التوافق بسبب عمليات TensorFlow غير المدعومة بواسطة مجموعة العمليات المدمجة TFLite.

هذا نوع من القضايا المزعجة. كيف يمكنك اكتشافه في وقت سابق مثل وقت تأليف النموذج؟

علما بأن ستفشل التعليمة البرمجية التالية على converter.convert() المكالمة.

@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 = ""}

استخدام بسيط للتأليف المدرك للهدف

قدمنا ​​Authoring API لاكتشاف مشكلة توافق TensorFlow Lite أثناء وقت تأليف النموذج.

تحتاج فقط إلى إضافة @tf.lite.experimental.authoring.compatible الديكور التفاف بك tf.function نموذج للتحقق من توافق TFLite.

بعد ذلك ، سيتم التحقق من التوافق تلقائيًا عند تقييم النموذج الخاص بك.

@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 = ""}

إذا وجدت أي مشكلة التوافق TensorFlow لايت، وسوف تظهر COMPATIBILITY WARNING أو COMPATIBILITY ERROR مع المكان المحدد من المرجع إشكالية. في هذا المثال، فإنه يدل على موقع tf.Cosh المرجع في نموذج tf.function الخاص بك.

يمكنك أيضا التحقق من سجل التوافق مع <function_name>.get_compatibility_log() الأسلوب.

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

رفع استثناء لعدم التوافق

يمكنك توفير الخيار لل @tf.lite.experimental.authoring.compatible الديكور. و raise_exception الخيار يتيح لك استثناء عندما كنت في محاولة لتقييم نموذج مزينة.

@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 = ""}

تحديد استخدام "تحديد TF ops"

إذا كنت على علم حدد TF التقاط الاستخدام، ويمكن أن أقول لكم هذا لAPI التأليف من خلال وضع converter_target_spec . انها نفس tf.lite.TargetSpec الكائن الذي سوف استخدامه ل 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

التحقق من توافق وحدة معالجة الرسومات

إذا كنت ترغب في التأكد من النموذج الخاص بك هو Compatibile مع مندوب GPU من TensorFlow لايت، يمكنك تعيين experimental_supported_backends من tf.lite.TargetSpec .

يوضح المثال التالي كيفية ضمان توافق مفوض GPU للنموذج الخاص بك. لاحظ أن هذا النموذج به مشكلات توافق نظرًا لأنه يستخدم موترًا ثنائي الأبعاد مع مشغل tf.slice وعامل tf.cosh غير مدعوم. سترى اثنين من COMPATIBILITY WARNING مع معلومات الموقع.

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.

اقرأ أكثر

لمزيد من المعلومات ، يرجى الرجوع إلى: