Scribd
Upload
69 views

Requirements

The document lists various Python package requirements for a project. It includes many deep learning and computer vision packages like PyTorch, OpenCV, Detectron2, PyTorch3D. It also lists requirements for 3D processing, visualization, mesh operations, and development tools.

Uploaded by

lee727124
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
69 views

Requirements

The document lists various Python package requirements for a project. It includes many deep learning and computer vision packages like PyTorch, OpenCV, Detectron2, PyTorch3D. It also lists requirements for 3D processing, visualization, mesh operations, and development tools.

Uploaded by

lee727124
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 3

# please install pip requirements using:

# cat requirements.txt | sed -e '/^\s*#.*$/d' -e '/^\s*$/d' | xargs -n 1 pip


install
# otherwise one single compilation error could eat away like 20 minutes for
nothing.
# pip install -e . --config-settings editable_mode=strict --no-build-isolation --
no-deps
# pip install -e . --no-build-isolation --no-deps

# other requirements
# for terminal image visualization
timg
tyro
yacs
yapf
tqdm
rich
shtab
sympy
pillow
addict
trimesh
imageio
termcolor
tensorboard
scikit-image
scikit-learn
pytorch_msssim
fast-autocomplete
torch-tb-profiler

# other requirements not available in conda


smplx
pymcubes
torchdiffeq
opencv-python

# dev requirements
h5py

# for plenoctree conversion


# svox # never used
ipdb
pdbr
ninja
lpips
ujson
pandas

# for unwrapping to get StVK properly


xatlas
kornia
msgpack
jupyter
openpyxl
autopep8
pyntcloud
pyturbojpeg
matplotlib
ruamel.yaml
commentjson

# to support visualization, we need:


git+https://github.com/wookayin/gpustat
# for winding_number_remesh
git+https://github.com/NVlabs/nvdiffrast
git+https://github.com/tatsy/torchmcubes
# git+https://github.com/dendenxu/cholespy
# installing from conda leads to just numerous problems...
# NOTE: IMPORTANT
git+https://github.com/facebookresearch/pytorch3d
git+https://github.com/facebookresearch/detectron2
# git+https://github.com/dendenxu/large-steps-pytorch # FIXME: FIX THIS
# git+https://github.com/dendenxu/bvh-ray-tracing # FIXME: FIX THIS
# git+https://github.com/YuliangXiu/bvh-distance-queries

# external dependency: easymocap-public (this repo is not publicly available yet)


# for easymocap's vposer: human_pose_prior, this looks like my DotDict
implementation... just way more complex
dotmap
# for easymocap loading of SMPL (maybe all pickle loading of SMPL?)
chumpy
mediapipe
func_timeout
pycocotools
tensorboardX
# git+https://github.com/mmatl/pyopengl # MARK: might not render
git+https://github.com/nghorbani/human_body_prior

# https://storage.googleapis.com/open3d-releases-master/python-wheels/open3d-
0.16.0-cp310-cp310-manylinux_2_27_x86_64.whl
# http://www.open3d.org/docs/latest/getting_started.html (install the development
version from here if the previsou link is expired and python is too new)
# python3.10 support for open3d finally here
# if failed to install open3d (even when installing from latest release?), try to
skip it using
# pip install $(grep -v '^ *#\|^open3d' requirements.txt | grep .)
# NOTE: IMPORTANT
open3d

# pip install $(grep -v '^ *#\|^.*open3d\|^torch-sparse\|^torch-geometric\|


^.*cholespy\|^.*pytorch3d\|^.*pyopengl' requirements.txt | grep .)
# cat requirements.txt | sed -e '/^\s*#.*$/d' -e '/^\s*$/d' | xargs -n 1 pip
install

# Blender utils
# bpy
memory-tempfile

# dearpygui # TOO SLOW


# imgui[glfw] # replaced with imgui_bundle
glfw
PyGLM
pyperclip
pyopengl
clang-format
imgui-bundle
opencv-contrib-python
# MARK: The torchvision version has a memory leak
# https://github.com/pytorch/vision/issues/4378
# pynvjpeg

# MARK: Requires some compiling and may easily fail, but not needed for most of the
implementations
git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch

# MARK: prone to change pytorch version, please install these on demand and
manually
# spconv-cu118
# functorch
torch-scatter
# torch-sparse
# torch-geometric

# pip install -e . --no-build-isolation --no-deps

# not needed unless you're using ali's implemenetation of VectorQuantize


einops
# not needed unless you're trying to debug torch memory usage using this package
directly
pytorch_memlab

# for ply file io


plyfile
# cuda driver for python, so nice for cuda opengl and pytorch interop, no hassle!
cuda-python

# For extracting meshes


pymeshlab

# For encode jpeg


pyturbojpeg

# For gaussian
git+https://gitlab.inria.fr/bkerbl/simple-knn
git+https://github.com/slothfulxtx/diff-gaussian-rasterization

You might also like