The following code block shows how to fit the model on the training dataset. Let's use 20k images from the training dataset to train the VGG-16 model and 5k images as validation dataset to evaluate the model while training. The weights=None parameter value must be passed to the VGG16() function to ensure that the network is trained from scratch. Note, this will take a long time if not run on a GPU, so a GPU is recommended.
For installing TensorFlow with a GPU, refer to this article: https://medium.com/@raza.shahzad/setting-up-tensorflow-gpu-keras-in-conda-on-windows-10-75d4fd498198.
With 20 epochs, the accuracy achieved on the validation dataset is 78.38%. We can tune the hyperparameters to increase the accuracy of the model ...
