alibaba-mmai-research/TAdaConv

Issues

• RuntimeError: Error(s) in loading state_dict for BaseVideoModel: size mismatch for head.out.weight: copying a param with shape torch.Size([400, 768]) from checkpoint, the shape in current model is torch.Size([5, 768]). size mismatch for head.out.bias: copying a param with shape torch.Size([400]) from checkpoint, the shape in current model is torch.Size([5]).

  #24 opened 2 months ago by lyxlplhy
  1

• Applying TAdaConv3d to Timesformer

  #17 opened a year ago by jinfu688
  2

• Question on reproducing the results on sthv2

  #23 opened 9 months ago by PeiqinZhuang
  0

• Feedback on the issue of ema coefficient.

  #22 opened 9 months ago by PeiqinZhuang
  5

• top1-5 accuracy did not achieve the expected effect（Mosi/Finetuned on UCF101/HMDB51 dataset）

  #18 opened 10 months ago by TJQdoIt9527
  12

• In Mosi, training on hmdb51 based on the pre trained checkpoint you provided cannot reproduce the results

  #21 opened 10 months ago by TJQdoIt9527
  1

• Enquiry on the batch size when using 32-frames

  #20 opened 10 months ago by PeiqinZhuang
  2

• TAdaConv2d needs in_channels to equal out_channels

  #19 opened 10 months ago by akanuasiegbu
  1

• Applying TadaConv

  #13 opened 2 years ago by yingqiluoCSDN
  1

• Frame description and temporal modeling

  #12 opened a year ago by Xiyu-AI
  1

• TAdaConvNeXt-T

  #11 opened a year ago by okojoalg
  3

• some questions about flops and inference time

  #10 opened a year ago by bendanzzc
  1

• I am curious about why the flops and parms of TAdaConvNeXt-T is one half of the ResNet50's, to my knowledge they should be similar.

  #15 opened a year ago by leexinhao
  2

• Batch-wise and Temporal-wise modeling

  #14 opened a year ago by hulianyuyy
  1

• apply AdaConv to P3D or SlowFast

  #16 opened a year ago by yan-ctrl
  1

• Use TAdaConv in Video Object Detection?

  #8 opened 2 years ago by urbaneman
  1

• How to use R(2+1)D with TAda?

  #9 opened 2 years ago by sja9527
  1

• features

  #6 opened 2 years ago by wolfworld6
  2

• Problems on loading imagenet weight

  #5 opened 2 years ago by jwfanDL
  1

• Issue on running on sthv2

  #4 opened 2 years ago by jwfanDL
  2

• Some questions on using _decode_image rather than _decode_video

  #3 opened 2 years ago by jwfanDL
  2

• EPIC-KITCHENS Action Features

  #2 opened 2 years ago by elias-work
  2

• code release

  #1 opened 3 years ago by haoranD
  2