dzy

here:https://github.com/666DZY666/pytorch-cifar/blob/master/models/resnet.py Model：resnet18 ResNet(BasicBlock, [2,2,2,2]) Layer： def forward(self, x): out = F.relu(self.bn1(self.conv1(x))) out = self.layer1(out) out = self.layer2(out) out = self.layer3(out) out = self.layer4(out) out = F.avg_pool2d(out, 4) out = out.view(out.size(0),...

and I have another problem~ I have prued the resnet164,when I compute flops and parameters,there is error: "RuntimeError: Given groups=1, weight of size 16 14 1 1, expected input[1, 16,...

1、what this means?the resnet164 use bottleneck but the number of its residual stages is also 3,it is same to this resnet18 that use basicblock .and why the parameters are not...

1、the resnet18's first layer don't have shortcut(it use basicblock,not bottleneck)，so they are both 3 stages in total 2、yeah,you got it,so can you show me how do you compute flops and...

so as for the first question, I think the reason may be the "channel_selection" make it slower

1、my means is that the first layer's block's input and output are same,so there is no 1*1conv~see "****" (layer1): Sequential( 0.286 GMac, 26.026% MACs, (0): BasicBlock( 0.143 GMac, 13.013% MACs,...

int 1/2/3/4/5/6/7/8

谢谢回复。 有没有比较好的混合精度搜索论文推荐？HAWQ？ 之前ppq里的这部分似乎去掉了？

okok，这种屡试不爽的方法有完整example或test吗(误差分析+bits 分配)？ 误差用哪种最好('cosine', 'snr', and 'mse')？有啥经验吗？

okok~