whyu

icon company South China Normal University icon location Foshan Guangdong icon location Prospective graduate student (pre-admission) at the Institute of Microelectronics, University of Chinese Academy of Sciences.

Results 2 comments of whyu

有大佬知道cuda:0 device type tensor to numpy怎么解决

> i changed it in lines 120-121 : > > ``` > # Compute loss at each stage > loss_char = torch.sum(torch.stack([criterion_char(restored[j], target) for j in range(len(restored))])) > loss_edge =...

对resnet18的剪枝流程

在benchmark的main.py里面，不知道为什么，我写的卷积模型剪枝之后FLOPs几乎不变，而且明明参数只有150W，但纸面的FLOPs大小却比VGG还大