Using ResNet50 pre-trained Weights I am trying to build a classifier. The code base is fully implemented in Keras high-level Tensorflow API. The complete code is posted in t
I was getting the same error and i tried setting os.environment flag...but it didn't work out.
Then i went ahead and reduced my batch size from 16 to 8, and it started to work fine after then. As it is because, the train method takes into account the batch size...i feel, reducing the image size would also work..as mentioned above as well.