ViTAE-Transformer/ViTPose issues and pull requests

#37 - Question about the file vitpose-l-simple.pth.

Issue - State: open - Opened by mls1999725 about 2 years ago - 1 comment

#36 - How to edit number of transformer blocks?

Issue - State: closed - Opened by gsrujana about 2 years ago - 1 comment

#35 - AttributeError: 'ConfigDict' object has no attribute 'data'

Issue - State: open - Opened by shiny-apricot about 2 years ago

#34 - Test with a resolution different from 256x192

Issue - State: closed - Opened by linjing7 about 2 years ago - 1 comment

#33 - ViTAE-G config

Issue - State: open - Opened by Alpha-X-95 about 2 years ago

#32 - Bottom up vs top down model

Issue - State: open - Opened by gsrujana about 2 years ago - 2 comments

#31 - Video demo with VitPose Base

Issue - State: closed - Opened by gsrujana about 2 years ago - 7 comments

#30 - KeyError: 'ViT is not in the models registry'

Issue - State: closed - Opened by ajktym94 about 2 years ago - 4 comments

#29 - Model in video demo

Issue - State: open - Opened by gsrujana about 2 years ago - 1 comment

#28 - What is the pretrain model of MAE huge?

Issue - State: closed - Opened by zengwang430521 about 2 years ago - 1 comment

#27 - Fix for docker file throwing NVIDIA GPG key error

Pull Request - State: open - Opened by tornikeo over 2 years ago

#26 - How to do inference on video by scripts?

Issue - State: open - Opened by sylyt62 over 2 years ago

#25 - about the code of the transformer block

Issue - State: open - Opened by Smallwhite999 over 2 years ago - 1 comment

#24 - Training on test images when using CrowdPose?

Issue - State: closed - Opened by 1281167 over 2 years ago - 5 comments

#23 - Demo codes.

Issue - State: open - Opened by mls1999725 over 2 years ago

#22 - Config path

Issue - State: open - Opened by ghost over 2 years ago

#21 - Speed of Detection

Issue - State: open - Opened by cheesezoella over 2 years ago

#20 - Running video demo

Issue - State: open - Opened by rmhiri-gpsw over 2 years ago - 4 comments

#19 - Running the project

Issue - State: closed - Opened by cheesezoella over 2 years ago - 1 comment

#18 - add web demo on Hugging Face

Pull Request - State: closed - Opened by AK391 over 2 years ago

#17 - About multitask log

Issue - State: closed - Opened by EEWenbinWu over 2 years ago - 2 comments

#16 - pretrain model

Issue - State: closed - Opened by EEWenbinWu over 2 years ago - 3 comments

#15 - Code for multi task training.

Issue - State: closed - Opened by mariolew over 2 years ago - 2 comments

#14 - Training device?

Issue - State: open - Opened by mariolew over 2 years ago - 3 comments

#13 - config question

Issue - State: closed - Opened by MikuuGithub over 2 years ago - 2 comments

#12 - where is optimize attention block ?

Issue - State: open - Opened by www516717402 over 2 years ago

#11 - Config / weights for ViTPose-G

Issue - State: open - Opened by changt over 2 years ago - 3 comments

#10 - How to load pre-trained model?

Issue - State: closed - Opened by jhxing over 2 years ago - 2 comments

#9 - Reproduce the video results in README

Issue - State: closed - Opened by ykk648 over 2 years ago - 3 comments

#8 - What's the batchsize used in the configuration?

Issue - State: closed - Opened by orashi over 2 years ago - 1 comment

#7 - about OmniPose-Lite

Issue - State: closed - Opened by chenj133 over 2 years ago - 1 comment

#6 - configure the environment

Issue - State: closed - Opened by MikuuGithub over 2 years ago

#5 - Testing on CPU

Issue - State: open - Opened by ahmadmustafaanis over 2 years ago - 4 comments

Ecosyste.ms: Issues

GitHub / ViTAE-Transformer/ViTPose issues and pull requests