Classic D Liu

> 分析了一下，推理速度是ok的，感觉问题出在forward_eval 里 return torch.cat( # 目标是(1,8400,85) [ pred_bboxes, # torch.ones((b, pred_bboxes.shape[1], 1), device=pred_bboxes.device, dtype=pred_bboxes.dtype), cls_score_list.permute(0, 2, 1) ], axis=-1) torch.ones((b, pred_bboxes.shape[1], 1), device=pred_bboxes.device, dtype=pred_bboxes.dtype),我怀疑是这行导致每个结果都要计算所以在走cocoeval的时候要花较多的时间

For APRCP HRNet you can get our prtrain model in : https://drive.google.com/file/d/1-EXl9dSatzmUSGpWGuBFlcPPM9T8Gcfr/view?usp=drivesdk For a purned model, there are two main file: pruneXXX.txt // to build model XXXXXXXX.pth // weight of...

CPU is work, The effect of GPU is not obvious because of parallel computing, but I am trying to speed up GPU by pruning without skipping fusion layer (another reason...

Some new work will open after cvpr2021, and we will response you as soon as possible.

We prune 2 bn layer in one basic modules, so self.bnindex += 2. If you only prune 1 bn layer self.bnindex += 1. You can add a breakpoint on the...

> BTW, Have you ever taking not only the percent, but also the absolute sum value of the all the weights in each channel? It could be more reasonable. Thx,...

1、新版本有的，但是在投CVPR出于保密的原因没有开源 2、maxpool应该没有问题，xx.append('M')的话是我参考的源码保留的，具体可以删掉，这版代码需要进一步精简，等文章结果下来我会立刻更新最新的版本，抱歉啊，可以私聊我qq：3357816826