Bantuan melindungi Great Barrier Reef dengan TensorFlow pada Kaggle Bergabung Tantangan

Alat Penulisan TFLite

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

TensorFlow Lite Authoring API menyediakan cara untuk menjaga Anda tf.function model compatibile dengan TensorFlow Lite.

Mempersiapkan

import tensorflow as tf

Masalah kompatibilitas TensorFlow ke TensorFlow Lite

Jika Anda ingin menggunakan model TF pada perangkat, Anda perlu mengonversinya menjadi model TFLite untuk menggunakannya dari juru bahasa TFLite. Selama konversi, Anda mungkin mengalami kesalahan kompatibilitas karena operasi TensorFlow yang tidak didukung oleh set operasi bawaan TFLite.

Ini adalah semacam masalah yang mengganggu. Bagaimana Anda bisa mendeteksinya lebih awal seperti waktu pembuatan model?

Perhatikan bahwa kode berikut akan gagal pada converter.convert() panggilan.

@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 = ""}

Penggunaan Penulisan Sadar Target Sederhana

Kami memperkenalkan Authoring API untuk mendeteksi masalah kompatibilitas TensorFlow Lite selama waktu pembuatan model.

Anda hanya perlu menambahkan @tf.lite.experimental.authoring.compatible dekorator untuk membungkus Anda tf.function Model untuk memeriksa kompatibilitas TFLite.

Setelah ini, kompatibilitas akan diperiksa secara otomatis saat Anda mengevaluasi model Anda.

@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 = ""}

Jika ada masalah kompatibilitas TensorFlow Lite ditemukan, ia akan menampilkan COMPATIBILITY WARNING atau COMPATIBILITY ERROR dengan lokasi yang tepat dari op bermasalah. Dalam contoh ini, itu menunjukkan lokasi tf.Cosh op dalam model tf.function Anda.

Anda juga dapat memeriksa log kompatibilitas dengan <function_name>.get_compatibility_log() metode.

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

Naikkan pengecualian untuk ketidakcocokan

Anda dapat memberikan pilihan kepada @tf.lite.experimental.authoring.compatible dekorator. The raise_exception pilihan memberikan pengecualian ketika Anda mencoba untuk mengevaluasi model dihiasi.

@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 = ""}

Menentukan penggunaan "Pilih TF ops"

Jika Anda sudah menyadari Pilih TF ops penggunaan, Anda dapat memberitahu ini ke API Authoring dengan menetapkan converter_target_spec . Itu sama tf.lite.TargetSpec objek yang akan menggunakannya untuk 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

Memeriksa kompatibilitas GPU

Jika Anda ingin memastikan model Anda compatibile dengan GPU delegasi dari TensorFlow Lite, Anda dapat mengatur experimental_supported_backends dari tf.lite.TargetSpec .

Contoh berikut menunjukkan cara memastikan kompatibilitas delegasi GPU model Anda. Perhatikan bahwa model ini memiliki masalah kompatibilitas karena menggunakan tensor 2D dengan operator tf.slice dan operator tf.cosh yang tidak didukung. Anda akan melihat dua COMPATIBILITY WARNING dengan informasi lokasi.

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.

Baca lebih lajut

Untuk informasi lebih lanjut, silakan merujuk ke: