bug in resnet.py

Open zijunwei opened this issue 9 years ago • 1 comments

line 283 of resnet.py , should it be weight_decay=FC_WEIGHT_DECAY) ?

Also, it might be better for each variable_scope, for example: with tf.variable_scope('scale1'): add resue flag at the end with tf.variable_scope('scale1', resue = not is_training):

Oct 09 '16 21:10 zijunwei

line 283 of resnet.py , should it be weight_decay=FC_WEIGHT_DECAY) ?

I think so too

Jul 27 '17 21:07 ameliajimenez