OpenGVLab/VideoMAEv2

Issues

• TAD timm版本

  #72 opened 2 months ago by yubo200526
  4

• Inquiry About Downloading Kinetics and SSV2 Datasets due to Missing data

  #71 opened 2 months ago by linwk20
  1

• FineAction的annotations在哪里？

  #70 opened 3 months ago by Marydsy
  0

• Unable to load the distilled model weights provided in the model zoo

  #24 opened 2 years ago by druefena
  2

• The TAD Features download link is broken

  #69 opened 3 months ago by LHX0303
  4

• The model download link is broken

  #64 opened 3 months ago by Bazinga699
  2

• Checkpoint link broken

  #67 opened 3 months ago by hamzakhalil798
  2

• on the tad features extraction, is image normalization required?

  #62 opened 7 months ago by auzxb
  3

• 预训练阶段收敛问题

  #65 opened 4 months ago by hanfeng0409
  2

• code for post-pretraining

  #66 opened 4 months ago by baoxiaoyi
  0

• Model Weights

  #63 opened 4 months ago by SamHSHS
  5

• Zero-shot evaluations on downstream datasets

  #60 opened 6 months ago by XuecWu
  0

• Knowledge distillation code

  #61 opened 7 months ago by rixejzvdl649
  1

• Pretrained Action Detection on AVA-Kinetics model weights

  #29 opened 10 months ago by girmaji08
  19

• CLS token

  #59 opened 7 months ago by Alsalivan
  0

• Finetuning with more than 16 frames

  #58 opened 7 months ago by CSLR-research
  0

• Where to find the script of finetuning on 'Temporal action detection' task?

  #51 opened a year ago by Leo-Yuyang
  6

• Code implementation of model inference

  #57 opened 8 months ago by XuecWu
  0

• Impact of Something Something and Kinetics during Unlabeled Pre-training

  #56 opened 8 months ago by edessa
  0

• fine-tuning AVA dataset for spatiotemporal detection

  #55 opened 9 months ago by Young-eng
  0

• Visualization Script

  #36 opened 10 months ago by kfirgoldberg
  2

• (Feature request) Batched feature extraction

  #20 opened 10 months ago by christian-matroid
  18

• Request for the training script for VideoMAE-V2-Base

  #34 opened 10 months ago by qinghuannn
  3

• Apply for the model weight of 'vit_g_hybrid_pt_1200e_k710_it_k400_ft'

  #35 opened 10 months ago by jinyucn
  1

• Pre-train Action recognition videoMAE model on UCF101

  #37 opened 10 months ago by Mr-MeerMoazzam
  12

• Error when running runclass_finetuning.py

  #39 opened 10 months ago by Ravindu-Yasas-Nagasinghe
  3

• Turning VideoMAEv2 into a next-frame prediction model

  #40 opened a year ago by IoSonoMarco
  1

• Extracting Features from Frame Level Data

  #43 opened 10 months ago by n1791348200
  1

• VideoMAEv2-L Weights/Checkpoints

  #44 opened 10 months ago by CarrotPeeler
  1

• Pretrained smaller models availability

  #45 opened 10 months ago by ganzobtn
  1

• Initialize student model's weights

  #46 opened 10 months ago by duytue-kite
  3

• Apply VideoMAEV2 to other directions.

  #47 opened 10 months ago by dufan175
  2

• Finetuned smaller models

  #48 opened 10 months ago by vpfuentealba
  1

• Could you provide features for ActivityNet 1.2 and ActivityNet 1.3 features extracted by videomaev2 ?

  #49 opened 10 months ago by Value-Jack
  0

• Could you provide ActivityNet 1.2 and ActivityNet 1.3 features extracted by videomaev2 ?

  #50 opened 10 months ago by Value-Jack
  1

• What should I do if I want to get the features of ActivityNet-1.3?

  #52 opened 10 months ago by hongminglin08
  7

• The parameter grad_norm appears to be inf and then nan when input resolution is 112*112 during the pre-training on VIT-Small backbone

  #53 opened a year ago by DragonWang-cell
  1

• 2333

  #54 opened 10 months ago by justzhanghong
  0

• How to train my own dataset?

  #30 opened a year ago by wang9danzuishuai
  2

• Failed to achieve claimed accuracy using vit-b on K400 dataset

  #38 opened a year ago by HaoRanLyu
  6

• Starting the pretraining from checkpoint..

  #33 opened a year ago by SushantGautam
  2

• could you please provide the weights of VideoMAEv2 pre-trained on Kinetics-400?

  #25 opened a year ago by fmthoker
  2

• Clarification on published logs.

  #32 opened a year ago by SushantGautam
  1

• No module named 'petrel_client'

  #31 opened a year ago by SeeeeShiwei
  1

• In datasets/build.py > def build_dataset > should the "anno_path" for mode = 'test' be (args.data_path, 'test.csv') instead of what it is currently (args.data_path, 'val.csv')?

  #27 opened a year ago by yerx
  1

• Could you provide the "misc/label_710to710.json" file?

  #26 opened a year ago by yerx
  1

• 预训练的大模型下载地址希望给一个国内能访问的

  #28 opened a year ago by bimver
  2

• I find that there seems to be some strange things in the evaluation of model.

  #23 opened 2 years ago by leexinhao
  7

• Do you have the finetuned checkpoints for UCF101?

  #22 opened 2 years ago by yerx
  2

• The hyperparameter Settings in the script seem to be inconsistent with those in the paper

  #21 opened 2 years ago by leexinhao
  4