ciwei123

RuntimeError: The size of tensor a (109) must match the size of tensor b (71) at non-singleton dimension 2

3

@tencent-adm RuntimeError: The size of tensor a (109) must match the size of tensor b (71) at non-singleton dimension 2

bad distributed

2

@zhaoyue-zephyrus @loveunk @lindahua @acrophile @yjxiong When I test the I3D model, I found that the name of the data read by each GPU is the same. Have you encountered the...

@Qidian213 @bensloane @bensloane @ChaplinHao Hi, I found that the runtime does not calculate 'the time which spend in reading images'.why about it , we should calculate the reading image (frame)...

Could you share the Lite-HRNet model pretrianed on ImageNet?

1

@ycszen Could you share the Lite-HRNet model pretrianed on ImageNet by Baidu Netdisk? Thank you very much!!

@yitutech-opensource Hi, thanks for your sharing. Could you share the MobileNeXt-0.75 model trained on ImageNet?Thank you very much!!

@zhyever Thanks for your sharing. Could you share the BinsFormer‘s config and model on Kitii ? I want to train my model on Kitii, but I don't konw the config...

Anet1.3 feature format

1

@VividLe Hi，thanks for your sharing, I have download the ActivityNett1.3 feature.And how do you get 'cls_label', 'reg_label'? Could you share me the preprocess script? Thank you very much!!

@jrebut Thanks for your sharing. Could you tell me how to modify the PIXOR code so that it can use RA data as input？Thank you!!

Why 352*1216？

5

@zhyever Thanks for your sharing. The input of the model is only the best when it is 352*1216, and the performance of other sizes becomes worse. Could you tell me...

torch.roll、torch.lgamma are not suportted?

2

@nihui Thanks for your sharing. I want to convert [https://github.com/photosynthesis-team/piq/blob/master/piq/brisque.py](url) to ncnn ,and I get some errors: 1.ONNX export failed on ATen operator group_norm because torch.onnx.symbolic.roll does not exist 2.ONNX...