seominseok

Did you solve the problem?

> Were you able to reproduce the baseline results? I tried with the same hyper-parameters indicated in the supplementary material but sill no luck. I can reach at most 25%...

> @adricarda Same question. Have you solved it successfully? I have trained the Seg model source only and got ~24-25 mIoU accuracy. Thanks. The hyperparameters were all the same. But...

I'll share our code. (soon)

Thank you so much for your kind reply. However, the meta file does not open. So I couldn't check things like LR, BATCH SIZE, EPOCH, etc. I'm really sorry. Can...

ex ) class Conv3d(nn.Conv3d): def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True): super(Conv2d, self).__init__(in_channels, out_channels, kernel_size, stride, padding, dilation, groups, bias) def forward(self, x): weight = self.weight weight_mean...

Thank you very much for your kind reply.

First of all, I would like to say thank you. Thanks to you, my research is progressing well. Thanks a lot for your code. Best

The author doesn't seem to have uploaded the full code. The author who maintains the code is not in good health, so I'm reorganizing the code and it's taking some...

I got 92.83, 91.99 and 92.07. We will check the code and get back to you.