Guocode
Guocode
I have tried your code on my training set,however i found that the convergence rate is very slow.I wonder whether you have the same problem.And do you have achieved the...
I find a issue in function generate_proposals, there should be ` valid_wh = torch.tensor([W, H], dtype=torch.float32, device=device) ` it may unvalid some area uncorrectly, but it should not affect the...
Not implemented yet.It's a basic version and I will improve it tomorrow or next year : ),looking forward to the official release.
@SidHard I find it's essential to pretrain for 3DCNN on imagenet, is your test of I3D and slowfastnet both trained from scratch?
For some reasons, I can't download that dataset. But I will eval the net on something-somethingv2, it hasn't be finished but the result seems not so well compared with resnet3d-50.
同求，pytorch转onnx没问题，但是用ncnn的网页转换工具会报错如下： 转换遇到了一些错误，不过某些情况下你可以下载模型并 手工修复。错误信息如下： Unknown data type 0 Unsupported Resize scales and sizes are all empty! Unsupported split axis ! Shape not supported yet! Expand not supported yet! Shape not supported...
> > It seems some boxes outside of the image are not filtered and the projection is from boxes behind the image plane. Do you locate the bug successfully? If...
same problem, error occurred on win11
> same problem, error occurred on win11 @Liumh-01 I think it's because of joblib cannot parse chinese char of temp dir, you can manually change temp dir to normal path