So I have this cnn in python. My data has 1000 training images and 100 validation images for each class. However my validation images are the same with my training data just less. I'm facing some accuracy problems so could this be one of the reasons?

CodePudding user response：

Yes, the validation data should be different (not a subset of) than the training data. That's because the validation data is to validate that the model isn't overtrained to the training data... if it were a subset of the training data, that obviously won't work.