将 Tensorflow Model 转换为 Tensorflow Lite Model 时出错

Question

我想在 Tensorflow lite 框架中使用 yolov4-tiny 来计算视频中穿过虚拟线的对象。

我使用这些命令转换了从 AlexeyAB's repo 训练的暗网权重：

python save_model.py --weights yolov4-tiny.weights --output ./checkpoints/yolov4-tiny-608-tf --input_size 608 --model yolov4 --tiny --framework tflite

python convert_tflite.py --weights ./checkpoints/yolov4-tiny-608-tf --output ./checkpoints/yolov4-tiny-608.tflite

您可以找到 convert_tflite.py here

第一个命令使用 numpy==1.19.0 成功。但是，第二个显示这些错误：

loc("batch_normalization/moving_mean"): error: is not immutable, try running tf-saved-model-optimize-global-tensors to prove tensors are immutable
Traceback (most recent call last):
  File "C:\Python37\lib\site-packages\tensorflow\lite\python\convert.py", line 213, in toco_convert_protos
    enable_mlir_converter)
  File "C:\Python37\lib\site-packages\tensorflow\lite\python\wrap_toco.py", line 38, in wrapped_toco_convert
    enable_mlir_converter)
Exception: <unknown>:0: error: loc("batch_normalization/moving_mean"): is not immutable, try running tf-saved-model-optimize-global-tensors to prove tensors are immutable


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "convert_tflite.py", line 76, in <module>
    app.run(main)
  File "C:\Python37\lib\site-packages\absl\app.py", line 303, in run
    _run_main(main, args)
  File "C:\Python37\lib\site-packages\absl\app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "convert_tflite.py", line 71, in main
    save_tflite()
  File "convert_tflite.py", line 45, in save_tflite
    tflite_model = converter.convert()
  File "C:\Python37\lib\site-packages\tensorflow\lite\python\lite.py", line 762, in convert
    result = _convert_saved_model(**converter_kwargs)
  File "C:\Python37\lib\site-packages\tensorflow\lite\python\convert.py", line 648, in convert_saved_model
    enable_mlir_converter=True)
  File "C:\Python37\lib\site-packages\tensorflow\lite\python\convert.py", line 216, in toco_convert_protos
    raise ConverterError(str(e))
tensorflow.lite.python.convert.ConverterError: <unknown>:0: error: loc("batch_normalization/moving_mean"): is not immutable, try running tf-saved-model-optimize-global-tensors to prove tensors are immutable

我尝试过其他版本的 Tensorflow（2.2、2.3、2.4），但没有成功。 我该怎么办？

此处提出了类似的问题：Tensorflow Issue 44790

这是我的系统详细信息： Windows10，x64 GeForce GTX 1060 NVIDIA 驱动程序 460.89 CUDA 11.0.3 CuDNN 8.0.5.39 Python3.7.2

Answer 1

pip install tensorflow==2.3.0rc0

并在开始转换前重启运行时

Answer 2

我通过关注 Github 问题的帖子解决了这个问题。

在 google colab 中，如果我使用默认的 TF 版本，即 2.4.0 或更高版本，我会遇到这个问题。
运行 !pip install tensorflow==2.3.0 并重新启动运行时，然后转换更正了问题。

Answer 3

对我来说，这解决了我的问题：

import tensorflow as tf

if tf.__version__ != '2.3.0-rc0':
  !pip uninstall -y tensorflow
  !pip install tensorflow-gpu==2.3.0rc0

并重新启动运行时，以便使用新安装的版本。

将 Tensorflow Model 转换为 Tensorflow Lite Model 时出错

Errors in converting Tensorflow Model to Tensorflow Lite Model

object-detection

tensorflow

tensorflow-lite

yolo