ih-lab / stork Goto Github PK

While running the predict.py file we are running into this Type error issue.

**If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:

1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).**

Please guide us with a solution.

The trained model directory is not getting stored in the save_path.

File "C:\Users\mathe\Downloads\STORK-master\STORK-master\scripts\slim\predict.py", line 79, in
init_fn(session)
File "C:\Users\mathe\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\contrib\framework\python\ops\variables.py", line 761, in callback
saver.restore(session, model_path)
File "C:\Users\mathe\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\training\saver.py", line 1277, in restore
raise ValueError("Can't load save_path when it is None.")
ValueError: Can't load save_path when it is None.

Kindly guide us to resolve this issue.

Hello! Firstly, thank you for developing this software. I've encountered some compatibility issues while using TensorFlow 2 with your software. I was wondering if you could advise me on the most appropriate version of TensorFlow to use with your software. Thank you!