Can't run flask --debug run .

[Tanstones630]

env:
macbook pro m1
python:3.10
flask:3.0.0

error info:

• Running on http://127.0.0.1:5000
  Press CTRL+C to quit
• Restarting with stat
• Debugger is active!
• Debugger PIN: 134-099-811
  Traceback (most recent call last):
  File "/Users/tanlei/IdeaProjects/NBA-Machine-Learning-Sports-Betting/main.py", line 9, in
  from src.Predict import NN_Runner, XGBoost_Runner
  File "/Users/tanlei/IdeaProjects/NBA-Machine-Learning-Sports-Betting/src/Predict/NN_Runner.py", line 12, in
  model = load_model('Models/NN_Models/Trained-Model-ML-1699315388.285516')
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/anaconda3/lib/python3.12/site-packages/keras/src/saving/saving_api.py", line 206, in load_model
  raise ValueError(
  ValueError: File format not supported: filepath=Models/NN_Models/Trained-Model-ML-1699315388.285516. Keras 3 only supports V3 .keras files and legacy H5 format files (.h5 extension). Note that the legacy SavedModel format is not supported by load_model() in Keras 3. In order to reload a TensorFlow SavedModel as an inference-only layer in Keras 3, use keras.layers.TFSMLayer(Models/NN_Models/Trained-Model-ML-1699315388.285516, call_endpoint='serving_default') (note that your call_endpoint might have a different name).
  127.0.0.1 - - [04/Dec/2024 11:50:10] "GET / HTTP/1.1" 500 -
  Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/flask/app.py", line 1478, in call
  return self.wsgi_app(environ, start_response)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/flask/app.py", line 1458, in wsgi_app
  response = self.handle_exception(e)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/flask/app.py", line 1455, in wsgi_app
  response = self.full_dispatch_request()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/flask/app.py", line 869, in full_dispatch_request
  rv = self.handle_user_exception(e)
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/flask/app.py", line 867, in full_dispatch_request
  rv = self.dispatch_request()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/flask/app.py", line 852, in dispatch_request
  return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
  File "/Users/tanlei/IdeaProjects/NBA-Machine-Learning-Sports-Betting/Flask/app.py", line 67, in index
  fanduel = fetch_fanduel(ttl_hash=get_ttl_hash())
  File "/Users/tanlei/IdeaProjects/NBA-Machine-Learning-Sports-Betting/Flask/app.py", line 13, in fetch_fanduel
  return fetch_game_data(sportsbook="fanduel")
  File "/Users/tanlei/IdeaProjects/NBA-Machine-Learning-Sports-Betting/Flask/app.py", line 27, in fetch_game_data
  stdout = subprocess.check_output(cmd, cwd="../").decode()
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/subprocess.py", line 421, in check_output
  return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
  File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/subprocess.py", line 526, in run
  raise CalledProcessError(retcode, process.args,
  subprocess.CalledProcessError: Command '['python', 'main.py', '-xgb', '-odds=fanduel']' returned non-zero exit status 1.

[nealmick]

The issue is that the model weights are saved in a format that is incompatible with your tensorflow version.
here is the important bit:
ValueError: File format not supported: filepath=Models/NN_Models/Trained-Model-ML-1699315388.285516. Keras 3 only supports V3 .keras files and legacy H5 format files (.h5 extension). Note that the legacy SavedModel format is not supported by load_model() in Keras 3. In order to reload a TensorFlow SavedModel as an inference-only layer in Keras 3, use keras.layers.TFSMLayer(Models/NN_Models/Trained-Model-ML-1699315388.285516, call_endpoint='serving_default') (note that your call_endpoint might have a different name).

The error may have to do with the checkpoint file name that has a . in it, which could cause it to think the file extension is wrong...
Trained-Model-ML-1699315388.285516 this may be processed as a file type of .285516 instead of .h5 or .json or another format.

I discussed the issue in my Flask-Upgrade branch below:
#452 (comment)

The updated file with fixes are below:
https://github.com/nealmick/NBA-Machine-Learning-Sports-Betting/blob/2ffd567bbb13702cf6b3ca9088bc18a559e91f74/src/Predict/NN_Runner.py

Ill also link the pr diff here:
https://github.com/kyleskom/NBA-Machine-Learning-Sports-Betting/pull/452/files#r1869839487

im not exactly certain what causes this error but i got it work by just reverting the nn runner to previous version.

[Tanstones630]

thanks so much! I pulled Flask-Upgrade branch , its works!
and l like the UI, so nice !

[Youngstud4321]

So can I delete the flask file and copy-paste the updated one, and it should work?

[nealmick]

yea well you have to replace src/Predict/NN_Runner.py

[Youngstud4321]

how do i replace the NN_Runner.py? wheres the older version located?

[nealmick]

The file is located at the path src/Predict/NN_Runner.py
to replace NN_Runner.py you can copy the fixed version and use an editor to paste it, or you can clone my repo fork and checkout the Flask-Upgrade branch which includes the fixes. Ill paste the link to fork below, make sure you get on the Flask-Upgrade branch which should say 1 commit ahead:
https://github.com/nealmick/NBA-Machine-Learning-Sports-Betting/tree/Flask-Upgrade