Why don't you validate during trainning?

anuragmishracse / caption_generator

A modular library built on top of Keras and TensorFlow to generate a caption in natural language for any input image.

MIT License

265 stars 120 forks source link

Why don't you validate during trainning? #3

Open hipoglucido opened 7 years ago

hipoglucido commented 7 years ago

Hello, I was wonder why is it that you don't add a validation generator during training. How do you control that the model doesn't overfit too much/it is able to generalize? Thanks in advance

anuragmishracse commented 6 years ago

@hipoglucido Good point, this can and should be done; mind sending a pull request?