Hi Reza: Thanks for sharing your good work on github.
Looks like you're referencing files on your desktop. Not sure if these files are on github as well.
df = pd.read_csv(f'{path}/metadata.csv')
Hope I'm not missing something.
Are you looking to share this work for others to build on?

Hi Reza - The training model's taking forever. What parameters can I change to speed up the process ?

print("[INFO] training new model ...")
results = model.fit_generator(
trainAug.flow(trainX, trainY),
# steps_per_epoch=len(trainX) // batch_size,
validation_data=(validX, validY),
# validation_steps=len(testX) // batch_size,
callbacks = [early_stopping],
epochs=epochs,
# class_weight = class_weights
)