megvii-model WeightNet issues - Githubissues

megvii-model / WeightNet

MIT License

173 stars 24 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Is this actually attention of different channels for different kernels?

#10 Haus226 opened 2 months ago
0
in the WeightNet_DW，is that "x_w = x_w.reshape(-1, 1, 1, self.ksize, self.ksize)"wrong？why the input and output channel is 1?

#9 kairenchen123 opened 1 year ago
0
5-D tensors as weight for Conv2d?

#8 ruiyuanlu closed 4 years ago
1
pytorch version

#7 czy112 closed 4 years ago
4
error with distributed training

#6 jmkim0309 closed 4 years ago
2
如何迁移学习自己的数据集

#5 hehaiyang111 closed 4 years ago
1
RetinaNet-WeightNet can not convergence ，with loss = 1.72

#4 convolutionROC closed 4 years ago
1
fix a bug when inference

#3 wkcn closed 4 years ago
4
Should the standard pointwise convolution in the skip path of Resblock (upsample/downsample=True) be kept or also replaced by WeightNet?

#2 ZhouYuxuanYX closed 4 years ago
2
Why is the bias of wn_fc2 of class WeightNet in weightnet.py set to be false?

#1 ZhouYuxuanYX closed 4 years ago
2