Object detection on raspberry pi - tensorflow

Question

I am trying to run the following project:
https://github.com/krishrustagi/Accident-Detection-System
I do not know what I am doing wrong.This project seems really interesting and I really want to learn more about it.
How do I get the github repository above to work.
Maybe a simple fix?
Here is the error code I get when executing the camera.py command:
(env) pi#raspberrypi:~/Project/Accident-Detection-System $ python3 camera.py Traceback
(most recent call last):
File "/home/pi/Project/Accident-Detection-System/camera.py", line 6, in <module>
model = AccidentDetectionModel("model.json", 'model_weights.h5')
File "/home/pi/Project/Accident-Detection-System/detection.py", line 15, in __init__
self.loaded_model.load_weights(model_weights_file)
File "/home/pi/Project/Accident-Detection-System/env/lib/python3.9/site-
packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/home/pi/Project/Accident-Detection-System/env/lib/python3.9/site-
packages/h5py/_hl/files.py", line 533, in __init__
fid = make_fid(name, mode, userblock_size, fapl, fcpl, swmr=swmr)
File "/home/pi/Project/Accident-Detection-System/env/lib/python3.9/site-
packages/h5py/_hl/files.py", line 226, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5f.pyx", line 106, in h5py.h5f.open
FileNotFoundError: [Errno 2] Unable to open file (unable to open file: name =
'model_weights.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags
= 0)

Answer 1

The error trace is telling you that the file model_weights.h5 does not exist anywhere in the project root directory.
After looking at the GitHub repo, it seems that model.json exists but model_weights.h5 does not, while both are supplied as arguments in camera.py Line 6:
model = AccidentDetectionModel("model.json", 'model_weights.h5')
The README mentioned this in Section 5:
accident-classification.ipynb: This is a jupyter notebook that generates a model to classify the above data. This file generates two important files model.json and model_weights.h5.
Hence you should run accident-classification.ipynb first before running camera.py.