search

pumpikano / tf-dann

Domain-Adversarial Neural Network in Tensorflow
MIT License
628 stars 224 forks source link

feeding domain value to the model #20

Closed sbmaruf closed 6 years ago

sbmaruf commented 6 years ago

I assume you want to transfer the label of the mnist image to the mnistm images given that you have only the label of mnist data. So when you create the generator you used,

    gen_target_batch = batch_generator(
        [mnistm_train, mnist.train.labels], batch_size / 2)

here you feed label data for the target domain. Why? Isn't it we are supposed to learn? Why are we feeding labeled data for target domain? Isn't it supposed to be empty? Please pardon me if I made any mistake while skimming through your code.

sbmaruf commented 6 years ago

I see you appoint condition to the model with model.train parameter. Thanks for the code. I understand now, what you did.