mangwaier
Results
2
comments of
mangwaier
weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss') tf.add_to_collection('losses', weight_decay) As the code say, there is a weight decay based on L2.
Hi,@warmspringwinds. I get this error:"logits and labels must be same size: logits_size=[168960,2] labels_size=[187500,2]". Hope you can review this problem I'm having. Thank you!!!!!