As we all know Keras backend uses Tensorflow and so it should give out samesome kind of results when we provide the same parameters, hyper-parameters, weights, and biases initialisationinitialization at each layer, but still, the accuracy is different.
This maybemay be because of the batches of images whichthat are fed at each step in both the models are not identical and as it getsget shuffled randomly.
Is there any way in which we can make sure that the same batch of images areis fed into the model while eliminating the randomness?
I have tried using all the same parameters, hyperparameters, same weights, and biases initialization with seed values.
The accuracy of both the models areis not the same.