# What if my validation set is worse than my training?

I am running a CNN, on the 1st epoch my training set accuracy is 15% and validation set is 12%, by the 51st epoch my training accuracy is 87% and validation set is 13%. What is happening? What does it mean if my validation set is lower or greater than my training set ?? (my test set gives 12%)

• It means you training set isn't a random sample from the union of training and validation sets. Resample and try again. Apr 17 '18 at 16:06
• Can you show us the plots you get using the history object in Keras such that we can see what is happening. Either its what @Spacedman said, or you are over-training and thus over-fitting. Apr 17 '18 at 16:25
• Its the usual sign of gross overfit. Apr 17 '18 at 19:35