Issues
- 0
How to conduct zero-shot evaluations?
#125 opened by XuecWu - 0
- 1
How to convert .pth to .bin
#118 opened by fengzi456258 - 0
After obtaining the .pth file from training, how do I convert it into a .bin file for performing inference?
#123 opened by caojiehui - 0
ucf101,hmdb51
#122 opened by kffeng - 5
Issue Encountered When Loading the Model: "pretrain_videomae_base_patch16_224"
#105 opened by bbbdbbb - 1
KeyError: 'model'
#119 opened by fengjingchehu - 0
How to use VideoMAE for video regression task?
#121 opened by YuHoChau - 1
VideoMAE might not be a useful model for video reconstruction? Or perhaps it only learns the most generic distribution within patches?
#120 opened by apptcom1123 - 1
dist_init_required
#90 opened by Malitha123 - 1
TODO/videomae_pretrain_base_patch16_224_frame_16x4_tube_mask_ratio_0.9_e1600/checkpoint-1599.pth
#110 opened by xiaoli4881 - 0
How good model handle the different duration of clips?
#116 opened by hagonata - 0
- 4
- 0
AttributeError: module 'torch._C' has no attribute '_get_privateuse1_backend_name'
#114 opened by abhisheksushil2003 - 0
the numberi of rebuild images is too small
#113 opened by tsw123678 - 0
Rebuild Video
#112 opened by tsw123678 - 0
HMDB checkpoint
#111 opened by azabelo - 2
- 0
- 0
video xxx not correctly load during training
#108 opened by JinChow - 0
License of Kinetics-400
#107 opened by joaopaulq - 0
- 4
- 0
About the encoder layer output
#104 opened by Shar-01 - 0
- 0
Can I fine-tine it on a video dataset of 32 frames?
#102 opened by Ha0Tang - 0
- 0
Questions about performence on ssv2
#99 opened by wnzhyee - 5
- 0
BUG: Incorrect temporal indexing?
#97 opened by rosenfeldamir - 4
could you please provide me the weight of VideoMAE pre-trained on Kinetics-400,I want to use the the weight to extract the features of the thumos14
#95 opened by Value-Jack - 2
The dataset files in the link are not available
#96 opened by Sumutan - 3
How many videos are in your validation set?
#94 opened by Sumutan - 0
About pre-trained models
#91 opened by 972821054 - 0
ViT-S and ViT-H models on huggingface
#88 opened by sandstorm12 - 0
MoCoV3 Training Configuration
#87 opened by fmthoker - 0
Can VideoMAE be used to learn the motion characteristics and appearance characteristics of objects in videos?
#86 opened by summersnowfish - 1
- 1
learnable position embedding
#83 opened by kun-dragon - 2
ssv2 dataset acc
#75 opened by an1018 - 1
dataloader hinder the training speed
#81 opened by valencebond - 1
VIT-S initilization
#80 opened by G-JWLee - 0
why do not you use [CLS] token?
#78 opened by LinB203 - 0
- 1
- 1
Can't download SSv2 ViT-B pre-trained model
#74 opened by sunilhoho - 2
- 4
Reproducing Camera-Ready Improved Numbers
#72 opened by dfan - 1
About the testing accuracy of the model
#70 opened by WEIZHIHONG720