search

diegoalejogm / gans

Generative Adversarial Networks implemented in PyTorch and Tensorflow
MIT License
824 stars 352 forks source link

How to test a trained discriminator separately??? #11

Closed anamika06jain closed 3 years ago

anamika06jain commented 4 years ago

I have a doubt, at the end of the training phase we have both generator and discriminator. Now i only want to test the discriminator... How can i do that?

diegoalejogm commented 3 years ago

You can store the discriminator on Pytorch or TensorFlow.

Once you have your model on a variable (e.g. discriminator) , and the data you want to test (fake_data) you can do: discriminator(fake_data)