Input 0 of layer "model" is incompatible with the layer

[Matteo-0]

Hello,
I am trying to use this code to be able to implement a neural network capable to recognize standing and laying down positions.
I have gathered my dataset of images with their bounding box but when I try to use this code I get the following error:

"ValueError: Input 0 of layer "model" is incompatible with the layer: expected shape=(None, None, None, 3), found shape=(1, 3, 416, 554)"

I do not understand what is the problem with the shapes since they both have length four. Does anyone encountered this problem before and was able to solve it?

Any help is appreciated, Thanks!

[h-arslan]

Hello, I don't know how related they are but I solved the same kind of error by rebuilding the environment. I was using python 3.10 and latest versions of tensorflow and keras. After getting error I downgraded python to 3.6 and downgraded tensorflow to version 1.14.0 and keras to 2.1.6, problem gone.
Hope it works!

[imon134]

Hello, I don't know how related they are but I solved the same kind of error by rebuilding the environment. I was using python 3.10 and latest versions of tensorflow and keras. After getting error I downgraded python to 3.6 and downgraded tensorflow to version 1.14.0 and keras to 2.1.6, problem gone. Hope it works!

how did you downgrade tensorflow to that version

[h-arslan]

Running the commands pip uninstall tensorflow, pip uninstall keras
and pip install tensorflow==1.14.0 and pip install keras==2.1.6