Errors in converting Tensorflow Model to Tensorflow Lite Model - tensorflow

Question

I wanted to use yolov4-tiny in the Tensorflow lite framework to count objects that cross a virtual line in a video.
I converted my darknet weights trained from AlexeyAB's repo using these commands:
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
You can find the convert_tflite.py here
The first command is successful using numpy==1.19.0. However, the second one shows these errors:
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
I have tried other versions of Tensorflow (2.2, 2.3, 2.4) but I had no luck. What should I do?
There is a similar issue raised here: Tensorflow Issue 44790
Here are my system details:
Windows 10, x64
GeForce GTX 1060
NVIDIA Driver 460.89
CUDA 11.0.3
CuDNN 8.0.5.39
Python 3.7.2

Answer 1

pip install tensorflow==2.3.0rc0
and restart runtime before starting conversion

Answer 2

I resolved the problem by following a thread on Github issues.
In google colab, I had this issue if I used the default TF version, which was 2.4.0 or above.
Running !pip install tensorflow==2.3.0 and restarting the runtime, then converting corrected the issue.

Answer 3

For me this solved my problem :
import tensorflow as tf
if tf.__version__ != '2.3.0-rc0':
!pip uninstall -y tensorflow
!pip install tensorflow-gpu==2.3.0rc0
And restart runtime, in order to use newly installed versions.