songyonger
songyonger
when i run the cifar10 experient, 3conv+ode_layer+fc_layer achieves the accuracy of 85.84%, but the structure 3conv+fc_layer's accuracy is only 79.07%, that doesn't seem to be in line with your statement...
Have you solved this problem?
I replaced the conv in the resblock in the super resolution model "edsr" with involution, and i used the gradient method, but the loss is still inf.
还没有
I replace the standard conv with involution and added bn, then the loss seems normal.But the final result is worse than edsr baseline with bn layer,even though i added the...
> @yassouali I have the same problem as you, have you figured out how to achieve it now?
@1187697147 请问--decay这个参数在哪里呢？option.py里只有parser.add_argument('--lr_decay', type=int, default=300, help='learning rate decay per N epochs')，我resume的时候将get_lr() 改成了get_last_lr()，但是学习率也还总是乘了0.5，请问您上面说的改变--decay这个方法是怎么做的呢？
好的，谢谢！
我也有这个问题，3.3 Stochastic precision节没有找到对应的代码。