将saved_model.pb 转换为model.tflite [英] Converting saved_model.pb to model.tflite

问题描述

TensorFlow 版本:2.2.0

Tensorflow Version: 2.2.0

操作系统:Windows 10

OS: Windows 10

我正在尝试将 saved_model.pb 转换为 tflite 文件.

I am trying to convert a saved_model.pb to a tflite file.

这是我正在运行的代码:

Here is the code I am running:

import tensorflow as tf

# Convert
converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir='C:\Data\TFOD\models\ssd_mobilenet_v2_quantized')
tflite_model = converter.convert()


fo = open("model.tflite", "wb")
fo.write(tflite_model)
fo.close

此代码在转换时出错:

  File "C:\Users\Mr.Ace\AppData\Roaming\Python\Python38\site-packages\tensorflow\lite\python\convert.py", line 196, in toco_convert_protos
    model_str = wrap_toco.wrapped_toco_convert(model_flags_str,
  File "C:\Users\Mr.Ace\AppData\Roaming\Python\Python38\site-packages\tensorflow\lite\python\wrap_toco.py", line 32, in wrapped_toco_convert
    return _pywrap_toco_api.TocoConvert(
Exception: <unknown>:0: error: loc("Func/StatefulPartitionedCall/input/_0"): requires all operands and results to have compatible element types
<unknown>:0: note: loc("Func/StatefulPartitionedCall/input/_0"): see current operation: %1 = "tf.Identity"(%arg0) {device = ""} : (tensor<1x?x?x3x!tf.quint8>) -> tensor<1x?x?x3xui8>


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "c:/Data/TFOD/convert.py", line 13, in <module>
    tflite_model = converter.convert()
  File "C:\Users\Mr.Ace\AppData\Roaming\Python\Python38\site-packages\tensorflow\lite\python\lite.py", line 1076, in convert
    return super(TFLiteConverterV2, self).convert()
  File "C:\Users\Mr.Ace\AppData\Roaming\Python\Python38\site-packages\tensorflow\lite\python\lite.py", line 899, in convert
    return super(TFLiteFrozenGraphConverterV2,
  File "C:\Users\Mr.Ace\AppData\Roaming\Python\Python38\site-packages\tensorflow\lite\python\lite.py", line 629, in convert
    result = _toco_convert_impl(
  File "C:\Users\Mr.Ace\AppData\Roaming\Python\Python38\site-packages\tensorflow\lite\python\convert.py", line 569, in toco_convert_impl
    data = toco_convert_protos(
  File "C:\Users\Mr.Ace\AppData\Roaming\Python\Python38\site-packages\tensorflow\lite\python\convert.py", line 202, in toco_convert_protos
    raise ConverterError(str(e))
tensorflow.lite.python.convert.ConverterError: <unknown>:0: error: loc("Func/StatefulPartitionedCall/input/_0"): requires all operands and results to have compatible element types
<unknown>:0: note: loc("Func/StatefulPartitionedCall/input/_0"): see current operation: %1 = "tf.Identity"(%arg0) {device = ""} : (tensor<1x?x?x3x!tf.quint8>) -> tensor<1x?x?x3xui8>

推荐答案

好的，我终于解决了！

我所做的是使用 tf-nightly 并使用以下 Python 脚本:

What I did is use tf-nightly and use the following Python Script:

import tensorflow as tf

saved_model_dir = "C:/Data/TFOD/models/ssd_mobilenet_v2_quantized/tflite"
converter = tf.lite.TFLiteConverter.from_saved_model(
    saved_model_dir, signature_keys=['serving_default'])
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.experimental_new_converter = True
converter.target_spec.supported_ops = [
    tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
tflite_model = converter.convert()

fo = open(
    "C:/Data/TFOD/models/ssd_mobilenet_v2_quantized/tflite/model.tflite", "wb")
fo.write(tflite_model)
fo.close

这解决了问题，您可以转换为 .tflite

This fixes the problem and you can convert to .tflite

这篇关于将saved_model.pb 转换为model.tflite的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！