princewen/tensorflow_practice

a bug in dis.py

Opened this issue · 1 comments

wdyxwzyh commented 
 emm  in dis.py.131, the L2 regr has been add to calculate D loss , and maybe the equation is wrong?
    self.loss = tf.reduce_mean(losses) + self.l2_reg_lambda + self.l2_loss
it should be:
    self.loss = tf.reduce_mean(losses) + self.l2_reg_lambda * self.l2_loss
wdyxwzyh commented

also in train.py.110, there should be generator.pgen_loss_adv instead of generator.gen_loss_adv