facebookresearch/mae_st
Official Open Source code for "Masked Autoencoders As Spatiotemporal Learners"
PythonNOASSERTION
Issues
- 1
Difference with VideoMAE
#25 opened by MLDeS - 1
t_patch_size issue
#14 opened by Vincent6896 - 1
'_OpNamespace' 'video_reader' object has no attribute 'probe_video_from_memory'
#22 opened by DaBaiTuu - 0
Finetuned checkpoints
#24 opened by YingtianDt - 0
Issue for generating output.
#23 opened by kimsekeun - 7
what is torch.fb.rendezvous.zeus responsible for?
#15 opened by R2D2oid - 1
Can you please give the ViT-B pre-trained model checkpoint on K400, K600, K700?
#16 opened by JananiKugaa - 3
load model issue
#13 opened by Vincent6896 - 1
test.csv format
#19 opened by XinyangHan - 5
- 1
- 1
Colab demo
#10 opened by Jiawei-Yang - 0
RuntimeError: can't start new thread
#21 opened by Liu-arch - 0
what is path_to_video_1 represents for? Does it mean the path to find the video in the folder? Eg. /dataset/video/video1.mp4
#18 opened by XinyangHan - 3
Dataset and actually running issues
#6 opened by Vincent6896 - 1
Can you give the finetune model checkpoint on K400?
#11 opened by zsz00 - 1
Can you give the pre-trained model on IG-uncurated
#12 opened by zsz00 - 0
Epoch number and warmup epoch number
#9 opened by Huiimin5 - 3
Encoder
#8 opened by Vincent6896 - 3
- 1
How to start multi-gpu training?
#4 opened by jinga-lala - 1
- 2