yangle15 / ranet-pytorch Goto Github PK

Thanks for sharing your code. I find some anomalous code In RANet.py#L322.
these three "if branch" will not be excuted.

    def _init_weights(self, m):
        if isinstance(m, nn.Conv2d):
            n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
            m.weight.data.normal_(0, math.sqrt(2. / n))
        elif isinstance(m, nn.BatchNorm2d):
            m.weight.data.fill_(1)
            m.bias.data.zero_()
        elif isinstance(m, nn.Linear):
            m.bias.data.zero_()

Hi, I am very interesting to your work!
Could you please provide the pretrained RANet models on ImageNet for our further research?
Thanks！

首先感谢您的简洁漂亮的代码！
line94判断条件包括了(epoch==299)。本人用CIFAR-10训练发现，最佳结果94.02出现在epoch 277。
但训练结束后，界面会出现：

可能是错误的信息提示哈~

Could you please provide the pretrained RANet models on ImageNet? Thanks.