liyang
ae28d55f81
Source: RGB-D -> Dyn-HaMR -> L20 retargeting -> FoundationPose -> reference repair -> SPIDER, documented in docs/PIPELINE_LATEST.md and docs/SETUP_AND_WEIGHTS.md. Adds FoundationPose and nvdiffrast upstream snapshots, requirements/pipeline_venv.txt and the FoundationPose weight manifest/downloader. Assets (Git LFS): weights/ (WiLoR detector, HandFlow denoiser, UniDepth-L), FoundationPose checkpoints, HaMeR checkpoint, Dyn-HaMR HMP model and BMC constraints, L20 URDF/meshes, the 20260915_171525 D405 recording and the two box CADs. MANO models are not redistributed (third_party/hamer/_DATA/data/mano/README.txt). Environments, caches and run outputs excluded. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
48 lines
1.4 KiB
Plaintext
48 lines
1.4 KiB
Plaintext
# Main environment (.venv) for the RGB-D pipeline: FoundationPose, RGB-D preprocessing, hand/object registration,
|
|
# collision fix / audits / rendering, Dyn-HaMR launcher and playback. Observed versions on the reference machine
|
|
# (Python 3.11.15, Ubuntu 22.04, CUDA 12.8) — pins, not a cross-platform lock.
|
|
#
|
|
# Install order:
|
|
# 1. torch==2.7.1 torchvision==0.22.1 --index-url https://download.pytorch.org/whl/cu128 (must match driver/CUDA)
|
|
# 2. pip install -r requirements/pipeline_venv.txt
|
|
# 3. pip install --no-build-isolation git+https://github.com/facebookresearch/pytorch3d.git@stable (needs nvcc; observed 0.7.9)
|
|
# 4. pip install --no-build-isolation --no-deps ./third_party/nvdiffrast (needs nvcc; snapshot 0.4.0)
|
|
# 5. build FoundationPose mycpp (see docs/SETUP_AND_WEIGHTS.md)
|
|
numpy==2.4.4
|
|
scipy==1.17.1
|
|
opencv-python==5.0.0.93
|
|
trimesh==4.12.2
|
|
coacd==1.0.14
|
|
open3d==0.19.0
|
|
kornia==0.8.3
|
|
omegaconf==2.3.1
|
|
hydra-core==1.3.2
|
|
imageio==2.37.3
|
|
imageio-ffmpeg==0.6.0
|
|
pillow==12.2.0
|
|
matplotlib==3.11.0
|
|
pandas==3.0.5
|
|
scikit-learn==1.9.1
|
|
joblib==1.6.0
|
|
h5py==3.16.0
|
|
PyYAML==6.0.3
|
|
ruamel.yaml==0.19.1
|
|
transformations==2026.1.18
|
|
pyrender==0.1.45
|
|
PyOpenGL==3.1.0
|
|
PyOpenGL-accelerate==3.1.10
|
|
psutil==7.2.2
|
|
tqdm==4.68.3
|
|
requests==2.34.2
|
|
mujoco==3.5.0
|
|
mujoco-warp==3.5.0
|
|
warp-lang==1.14.0
|
|
glfw==2.10.0
|
|
smplx==0.1.28
|
|
einops==0.8.2
|
|
timm==1.0.29
|
|
huggingface-hub==0.28.1
|
|
safetensors==0.8.0
|
|
ninja==1.13.2
|
|
pybind11==3.1.0
|