search

pumpikano / tf-dann

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

Need explain about model #23

Closed omg777 closed 6 years ago

omg777 commented 6 years ago

Hi, Thanks for you nice code! Im trying to re-implement this codes to pytorch. but I cant understand the models 'label_predictor' and 'domain_predictor

            W_fc0 = weight_variable([7 * 7 * 48, 100])
            b_fc0 = bias_variable([100])
            h_fc0 = tf.nn.relu(tf.matmul(classify_feats, W_fc0) + b_fc0)

            W_fc1 = weight_variable([100, 100])
            b_fc1 = bias_variable([100])
            h_fc1 = tf.nn.relu(tf.matmul(h_fc0, W_fc1) + b_fc1)

            W_fc2 = weight_variable([100, 10])
            b_fc2 = bias_variable([10])
            logits = tf.matmul(h_fc1, W_fc2) + b_fc2

In label_predictor, It looks there is no conv or FC layer. Can you explain about this network?

omg777 commented 6 years ago

resolved