YunhaoDu
YunhaoDu
> 我发现第6章的models中resnet结构错误可能错误 > self.layer1 = self.make_layer(64, 64, 3) > self.layer2 = self.make_layer(64, 128, 4, stride=2) > self.layer3 = self.make_layer(128, 256, 6, stride=2) > self.layer4 = self.make_layer(256, 512, 3, stride=2) >...
> 这里写的没有问题，但是Resnet34写的不是正常的代码，正常代码层数为3.4.6.3层结构，作者这里写成了4.5.7.4层结构， > for i in rang(1,block_num) > 应该是block_num-1才对，因为之前layers.append了一次。 您对range的理解是错的
@liqb-a 经过测试，发现batch_size
使用作者提供的权重，我和你得到了类似的结果： 
> 您好，怎么下载提供的权重呢 work文件夹下
just change the source code is OK 
> > just change the source code is OK > >  > > so basically you mean to just change at line 85 in /home/ant/anaconda3/lib/python3.8/site-packages/tensorwatch/model_graph/hiddenlayerhiddenlayer/summary_graph.py i.e. > > ```...
Yes, I also hope you the author can give a more detailed README.md. Thank you!
@XiaoBingCQY I'm sorry but I didn't try to run it.