OpenGVLab VideoMAEv2 issues

OpenGVLab / VideoMAEv2

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

https://arxiv.org/abs/2303.16727

MIT License

524 stars 63 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

upload : submodule

#73 Soooo-hong closed 1 day ago
3
TAD timm版本

#72 yubo200526 closed 2 weeks ago
4
Inquiry About Downloading Kinetics and SSV2 Datasets due to Missing data

#71 linwk20 closed 4 weeks ago
1
FineAction的annotations在哪里？

#70 Marydsy opened 1 month ago
0
The TAD Features download link is broken

#69 LHX0303 closed 1 month ago
4
[fix] Fix broken links

#68 yinanhe closed 1 month ago
1
Checkpoint link broken

#67 hamzakhalil798 closed 2 months ago
2
code for post-pretraining

#66 baoxiaoyi opened 2 months ago
0
预训练阶段收敛问题

#65 hanfeng0409 opened 2 months ago
2
The model download link is broken

#64 Bazinga699 closed 1 month ago
2
Model Weights

#63 SamHSHS closed 3 months ago
5
on the tad features extraction, is image normalization required?

#62 auzxb opened 5 months ago
3
Knowledge distillation code

#61 rixejzvdl649 opened 5 months ago
1
Zero-shot evaluations on downstream datasets

#60 XuecWu closed 4 months ago
0
CLS token

#59 Alsalivan opened 5 months ago
0
Finetuning with more than 16 frames

#58 CSLR-research opened 6 months ago
0
Code implementation of model inference

#57 XuecWu opened 6 months ago
0
Impact of Something Something and Kinetics during Unlabeled Pre-training

#56 edessa opened 7 months ago
0
fine-tuning AVA dataset for spatiotemporal detection

#55 Young-eng opened 8 months ago
0
2333

#54 justzhanghong closed 9 months ago
0
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 DragonWang-cell opened 10 months ago
1
What should I do if I want to get the features of ActivityNet-1.3?

#52 hongminglin08 closed 8 months ago
7
Where to find the script of finetuning on 'Temporal action detection' task?

#51 Leo-Yuyang closed 10 months ago
6
Could you provide ActivityNet 1.2 and ActivityNet 1.3 features extracted by videomaev2 ?

#50 Value-Jack closed 8 months ago
1
Could you provide features for ActivityNet 1.2 and ActivityNet 1.3 features extracted by videomaev2 ?

#49 Value-Jack closed 8 months ago
0
Finetuned smaller models

#48 vpfuentealba closed 8 months ago
1
Apply VideoMAEV2 to other directions.

#47 dufan175 closed 8 months ago
2
Initialize student model's weights

#46 duytue-kite closed 8 months ago
3
Pretrained smaller models availability

#45 ganzobtn closed 8 months ago
1
VideoMAEv2-L Weights/Checkpoints

#44 CarrotPeeler closed 8 months ago
1
Extracting Features from Frame Level Data

#43 n1791348200 closed 8 months ago
1
adjust of the dataset code.

#42 JerryFlymi closed 8 months ago
0
adjust the hybrid dataset code for pretrain.

#41 JerryFlymi closed 1 year ago
0
Turning VideoMAEv2 into a next-frame prediction model

#40 IoSonoMarco opened 1 year ago
1
Error when running runclass_finetuning.py

#39 Ravindu-Yasas-Nagasinghe closed 8 months ago
3
Failed to achieve claimed accuracy using vit-b on K400 dataset

#38 HaoRanLyu closed 1 year ago
6
Pre-train Action recognition videoMAE model on UCF101

#37 Mr-MeerMoazzam closed 8 months ago
12
Visualization Script

#36 kfirgoldberg closed 8 months ago
2
Apply for the model weight of 'vit_g_hybrid_pt_1200e_k710_it_k400_ft'

#35 jinyucn closed 8 months ago
1
Request for the training script for VideoMAE-V2-Base

#34 qinghuannn closed 8 months ago
3
Starting the pretraining from checkpoint..

#33 SushantGautam closed 1 year ago
2
Clarification on published logs.

#32 SushantGautam closed 1 year ago
1
No module named 'petrel_client'

#31 SeeeeShiwei closed 1 year ago
1
How to train my own dataset?

#30 wang9danzuishuai closed 1 year ago
2
Pretrained Action Detection on AVA-Kinetics model weights

#29 girmaji08 closed 8 months ago
19
预训练的大模型下载地址希望给一个国内能访问的

#28 bimver closed 1 year ago
2
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 yerx closed 1 year ago
1
Could you provide the "misc/label_710to710.json" file?

#26 yerx closed 1 year ago
1
could you please provide the weights of VideoMAEv2 pre-trained on Kinetics-400?

#25 fmthoker closed 1 year ago
2
Unable to load the distilled model weights provided in the model zoo

#24 druefena closed 1 year ago
2