张佳钰

Hi, where can I get res101h pretrained model

Trained D model

1

Hi, have you save net_Ds' ckpts. Like full D and patch D.

The given teacher checkpoint (vgg) doesn't fit with the current version of VGG in the repo.

2

``` size mismatch for loc.0.weight: copying a param with shape torch.Size([16, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 1024, 3, 3]). size mismatch for loc.1.weight:...

刚导入项目的时候报了这个错，请问哪里需要改动一下吗 ``` VM73:1 ./components/aotoo/templates/inner_templates.wxml unexpected attribute name, near `picture...` 478 | poster-for-crawler="{{props['poster-for-crawler']||''}}" 479 | show-casting-button="{{props['show-casting-button']||false}}" > 480 | picture-in-picture-mode="{{props['picture-in-picture-mode']||''}}" | ^ 481 | picture-in-picture-show-progress="{{props['picture-in-picture-show-progress']|| false }}" 482 | enable-auto-rotation="{{props['enable-auto-rotation']|| false...

请问openvino库是怎么导入的，pip install openvino没有找到openvino包，还是通过系统变量设置，求解答

How to train on 2 gpus, and change batch size to 2 It seems that the size of the model is fixed.