RickWang0412

I've got this problem in line 51 alpha = self.alpha.gather(0,labels.view(-1)) How can I solve it? thanks a lot.

Hello， Thanks for the amazing project~ I want to ask if you had occur that AP is larger than 1 before? Thanks~

Hello， Thanks for the amazing project~ I want to ask if you had occur that AP is larger than 1 before? Thanks~

An error with training on multiple GPUs

1

Hello author, Thanks for this research, I want to train vitlarge_clip_k400 on 4 V100 but when I use the command with "bash tools/dist_train.sh configs/recognition/vit/vitclip_large_k400.py 3 --test-last --validate --cfg-options model.backbone.pretrained=openaiclip work_dir=work_dirs_vit/k400_vitlarge/debug"....

The dimension of vit_clip and vit_imagenet

2

Hello, I want to ask the input dimension before multi head attention between vit_clip.py and vit_imagenet.py In vit_clip.py, the input dimension before T-MSA is t (b n) d, but in...

Train the ViT in 4 2080Ti

1

Hello, I try to train the model with 4x2080Ti server, I use the command below, bash tools/dist_train.sh ./configs/recognition/vit/vitclip_large_k400.py 4 --test-last --validate --cfg-options work_dir=./work_dirs but it runs the error : torch.distributed.elastic.multiprocessing.errors.ChildFailedError:...