-
Notifications
You must be signed in to change notification settings - Fork 176
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
增加卷积层性能下降 #31
Comments
同学你好,关于convolution stem的使用需要考虑到两点:
你可以做以下实验来验证一下:
另外额外补充一下,我们近期的工作表明,patch embed里面bn+relu是帮助vit训练的关键,conv层作用反而不是那么大,可以参考我们最近的论文:Scaled ReLU Matters for Training Vision Transformers |
个人一点点分析 |
请问如果想在ImageNet重新预训练模型,有官方教程地址吗?感谢感谢 |
可以用timm库,很多人都用这个。 |
您好!
很抱歉打扰到您,我想请问一下为什么我在PatchEmbed_overlap块增加convolution了以后性能大幅下降,我没有更改其他代码,只是将卷积层增加到了四层。这是我的部分代码:
self.conv1 = nn.Conv2d(in_chans, 128, kernel_size=7, stride=2, padding=3, bias=False)
self.bn1 = nn.BatchNorm2d(128)
self.relu = nn.ReLU(inplace=True)
self.proj = nn.Conv2d(128, embed_dim, kernel_size=new_patch_size, stride=new_patch_size)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
The text was updated successfully, but these errors were encountered: