Training Error Epoch comprised more than `samples_per_epoch`

[ilyes495]

I have tried to train SSD300 in my dataset, I have 2119 training samples and 500 validation samples, but the when I started training, it takes 2112 samples and only 32 samples for validation, I didn't make any changes to the code. here is a screen shot of the problem

[fortunto2]

Hello, it worked out? And how much time do you spend on training? Do you use gpu?

[AloshkaD]

You aren't using any samples for validation, where do you see that you are validation on 32 samples?

[AloshkaD]

@fortunto2 It takes me to long to train on a Titan X! Approximately 1 second per image for a data set with 6 classes.