Keras uses GPU for first 2 epochs, then stops using it

Question

I prepare the dataset and save it as as hdf5 file. I have a custom data generator that subclasses Sequence from keras and generates batches from the hdf5 file.

Now, when

Answer 1

Same Error Here!!

Because when you install tensorflow-gpu along nivida tool kit it provide a limited amount of GPU memory (Here in my case 2GB) .Due to leak of memory it release GPU finally and turn to use CPU .

if you want to avoid such condition Use Google Colab which provide about 36.7GB GPU memory.