Each time I am trying to call training function, It’s showing some broadcasting error. I checked the data_generator function also final_model layers but didn’t find any error.
Please suggest that hidden mistake.
https://colab.research.google.com/drive/10seKwt3mqe7Tn3eRnnhJNld5ErFHPwD_
Hey @nuts2021, try printing shape of x1, x2, x3 before yield([[np.array(X1), np.array(X2)], np.array(y)]) and check if satisfies the model input parameters shape
Please visit the same link, I have printed the shapes now. It should not show any errors but still showing.
No, I made the dictionary with image name without .jpg extension as key value.
Error is something else
Hey @nuts2021, it seems fine but there is some little mistake in the code somewhere, It would be not feasible at my end to debug the complete code, Plz take reference from here and run this code, your compare your code line by line.
Happy Learning 
Hi, I found this on google. https://community.drivendata.org/t/error-running-benchmark-with-nano/1617
but not able to execute this on google colab.
can you suggest me exact commands to uninstall keras then install new version ? I am confused, should uninstall keras or tensorflow.keras or tensorflow.python.keras
Hey @nuts2021 you should uninstall keras only
pip uninstall keras
pip install keras==2.0.8
to install the specific version.
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.