facebookresearch/pytorchvideo
A deep learning library for video understanding research.
PythonApache-2.0
Issues
- 0
- 4
Error importing libraries (Python 3.12.1)
#261 opened by dinihanafi - 1
- 0
- 1
The torchvision.transforms.functional_tensor module is deprecated in 0.15 and will be **removed in 0.17**.
#251 opened by jnj256 - 4
Import error with torchvision 0.17
#258 opened by jramapuram - 0
Protocol to match Decord / VideoReader
#259 opened by johndpope - 0
Error in functional.uniform_temporal_subsample when the input tensor has non-default device type
#256 opened by michaelnny - 0
Issue in MVIT2 architecture
#255 opened by visin109 - 1
Is anyone working on this project anymore?
#252 opened by bschreck - 0
Bug| x3d | Head Without Batch Normalization
#254 opened by MoH-assan - 0
Add custom object detecting in video through custom feature of enabling, disabling fature
#250 opened by rajveer43 - 0
video is none when using get_clip
#246 opened by Physical-Chemist - 0
Can you please provide video transformation code in pytorchvideo for rev-MViT and MViTv1?
#245 opened by Balakishan77 - 2
- 0
ImportError: cannot import name 'cached_property' from 'functools' in 'video_detection_inference_tutorial '
#240 opened by Pinocchio2018 - 0
- 0
Transform randaug is returning black video
#238 opened by ganzobtn - 0
Why does this Pytorch video tutorial (and others) only work with uniform clip sample lengths?
#236 opened by KevinJMcEntee - 1
- 0
- 5
Pretrained Models
#200 opened by Hepta-Col - 3
Convert x3d model to torchscript
#210 opened by hongsamvo - 0
- 1
ETA for next release?
#198 opened by fcakyon - 0
Pls Fix AttributeError: module 'torch.testing' has no attribute 'assert_close'
#232 opened by dralmadani - 0
Test failing `TestFuseBN`
#231 opened by RR-28023 - 0
shape do not match in slowfast
#230 opened by xwjBupt - 0
- 1
I3D Transform
#223 opened by Camillo4eyes - 0
The installation of “Stable Diffusion web UI” natively on FreeBSD fails because can’t install torch and torchvision
#228 opened by Marietto2008 - 1
In pytorchvideo.data.labeled_video_dataset, is transform is wrongly defined? or am I using it wrongly?
#225 opened by Tenglon - 0
- 3
Slowfast model with Kinetics data: RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 2 but got size 4 for tensor number 1 in the list.
#224 opened by ccapontep - 1
RoI head for Vision Transformer
#202 opened by yuxin212 - 0
Fine tuning video classifier on multiple GPU's: File exists: '/root/.cache/torch/hub' on download pretrained model
#222 opened by enrico310786 - 1
About num_frames for UniformTemporalSubsample
#220 opened by enrico310786 - 0
Perform Validation to Reproduce Results
#219 opened by ChristophReich1996 - 0
- 0
- 2
Multiple output against a video
#205 opened by talhaanwarch - 2
- 1
may you upadte a AVA dataset tutorial for newbie?
#193 opened by Hammer-888 - 3
How to finetune SlowFast pretrained model on custom AVA dataset in PytorchVideo?
#197 opened by Balakishan77 - 1
Why does `UniformClipSampler` prevent stride from being greater than duration?
#201 opened by dasturge - 1
- 1
Training models with output activation
#211 opened by dibgerge - 3
使用pytorchvideo的main最新代码 torch1.8,error:-->module 'torch' has no attribute 'fx'
#213 opened by liuyang77886 - 4
- 6
load mvit pretrained model,some error occurred
#206 opened by aiot-tech