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):
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 endwith tf.variable_scope('scale1', resue = not is_training):