haoly

Hello! I find images and gt have the same random indices, so the random sampling of the features should be same when the inputs are same. def _random_pooling(feats, output_1d_size=100): single_input...

I also have a question. In the function forward(self, x) of VGG_Model.py: def forward(self, x): for index, layer in enumerate(self.vgg_model): x = layer(x) if index in self.listen: self.features[vgg_layer_inv[index]] = x...

在这里，作者直接根更新BN层的gamma参数，类似于权重的L1正则化： https://github.com/coldlarry/YOLOv3-complete-pruning/blob/90c5869d265a632829ba7798598aa2798e4f5227/train.py#L323-L327 https://github.com/coldlarry/YOLOv3-complete-pruning/blob/90c5869d265a632829ba7798598aa2798e4f5227/utils/prune_utils.py#L121-L129 不过我也有一个疑惑，在更新BN层gamma参数的时候，作者加上了L1函数导数值，我觉得应该是减去？

I think it should be: out = (in - mean * 255) / sigma, according to author's codes, if input images are at 0 ~ 255. So the final range...

I have the same question. The L1 loss and GAN loss of generator increase dramaticlly , and the GAN loss of discriminator drops to a small value. The results are...