vid2avatar-colab's Introduction

🐣 Please follow me for new updates https://twitter.com/camenduru
🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
🥳 Please join my patreon community https://patreon.com/camenduru

🚦 WIP 🚦

🦒 Colab

Colab	Info
	vid2avatar_colab (>16GB VRAM 🦒 Pro Colab)

Training

Before training, make sure that the metaninfo in the data config file /code/confs/dataset/video.yaml does match the expected training video. You can also continue the training by changing the flag is_continue in the model config file code/confs/model/model_w_bg. And then run:

cd code
python train.py

The training usually takes 24-48 hours. The validation results can be found at outputs/.

Main Repo

https://github.com/MoyGcc/vid2avatar

Page

https://moygcc.github.io/vid2avatar/

Paper

https://arxiv.org/abs/2302.11566

License

https://github.com/MoyGcc/vid2avatar/blob/main/LICENSE

Output

dasdsa.mp4

For python 3.8 (lambdalabs, runpod ...)

%cd /home/ubuntu
!pip install chumpy hydra-core wandb aitviewer trimesh simple-romp pytorch-lightning==1.6.5 #1.8.6

!pip install -q https://huggingface.co/camenduru/pytorch3d-build/resolve/main/pytorch3d-0.7.4-cp38-cp38-linux_x86_64.whl
from pytorch3d import ops
!pip install -q https://huggingface.co/camenduru/pytorch3d-build/resolve/main/kaolin-0.14.0a0-cp38-cp38-linux_x86_64.whl
import kaolin

!git clone -b dev https://github.com/camenduru/vid2avatar
%cd /home/ubuntu/vid2avatar

!wget https://huggingface.co/camenduru/vid2avatar/resolve/main/parkinglot.zip
!unzip -y parkinglot.zip -d /home/ubuntu/vid2avatar/data

!mkdir /home/ubuntu/vid2avatar/code/lib/smpl/smpl_model
!wget https://huggingface.co/camenduru/vid2avatar/resolve/main/models/SMPL_FEMALE.pkl -O /home/ubuntu/vid2avatar/code/lib/smpl/smpl_model/SMPL_FEMALE.pkl
!wget https://huggingface.co/camenduru/vid2avatar/resolve/main/models/SMPL_MALE.pkl -O /home/ubuntu/vid2avatar/code/lib/smpl/smpl_model/SMPL_MALE.pkl

%cd /home/ubuntu/vid2avatar/code
!sudo python setup.py develop

%cd /home/ubuntu/vid2avatar/code
# !python train.py
!python test.py

vid2avatar-colab's People

Contributors

Stargazers

Watchers

vid2avatar-colab's Issues

Run Colab have a bug

%cd /content/vid2avatar/code
!python setup.py develop

/content/vid2avatar/code
running develop
/usr/local/lib/python3.10/dist-packages/setuptools/command/develop.py:40: EasyInstallDeprecationWarning: easy_install command is deprecated.
!!

        ********************************************************************************
        Please avoid running ``setup.py`` and ``easy_install``.
        Instead, use pypa/build, pypa/installer, pypa/build or
        other standards-based tools.

        See https://github.com/pypa/setuptools/issues/917 for details.
        ********************************************************************************

!!
  easy_install.initialize_options(self)
/usr/local/lib/python3.10/dist-packages/setuptools/_distutils/cmd.py:66: SetuptoolsDeprecationWarning: setup.py install is deprecated.
!!

        ********************************************************************************
        Please avoid running ``setup.py`` directly.
        Instead, use pypa/build, pypa/installer, pypa/build or
        other standards-based tools.

        See https://blog.ganssle.io/articles/2021/10/setup-py-deprecated.html for details.
        ********************************************************************************

!!
  self.initialize_options()
running egg_info
writing UNKNOWN.egg-info/PKG-INFO
writing dependency_links to UNKNOWN.egg-info/dependency_links.txt
writing top-level names to UNKNOWN.egg-info/top_level.txt
reading manifest file 'UNKNOWN.egg-info/SOURCES.txt'
writing manifest file 'UNKNOWN.egg-info/SOURCES.txt'
running build_ext
Creating /usr/local/lib/python3.10/dist-packages/UNKNOWN.egg-link (link to .)
UNKNOWN 0.0.0 is already the active version in easy-install.pth

Installed /content/vid2avatar/code
Processing dependencies for UNKNOWN==0.0.0
Finished processing dependencies for UNKNOWN==0.0.0

What is UNKNOWN library?

Readme Asset

dasdsa.mp4

Running with Custom Data?

Runs fine with the sample parkinglot data, but when I use my own image sequence and masks, It still runs but ignores what's in /content/vid2avatar/data/ and runs the parkinglot even though I comment it out the wget. Nothing else is in the data folder and can't find any other source for the parkinglot data.

Recommend Projects

camenduru / vid2avatar-colab Goto Github PK