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>
21 lines
830 B
Docker
21 lines
830 B
Docker
# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
|
|
#
|
|
# NVIDIA CORPORATION and its licensors retain all intellectual property
|
|
# and proprietary rights in and to this software, related documentation
|
|
# and any modifications thereto. Any use, reproduction, disclosure or
|
|
# distribution of this software and related documentation without an express
|
|
# license agreement from NVIDIA CORPORATION is strictly prohibited.
|
|
|
|
# Note: you should be able to use a newer image here:
|
|
FROM nvcr.io/nvidia/pytorch:25.06-py3
|
|
|
|
ENV PYTHONDONTWRITEBYTECODE=1
|
|
ENV PYTHONUNBUFFERED=1
|
|
|
|
RUN pip install ninja imageio imageio-ffmpeg
|
|
|
|
COPY csrc /tmp/nvdiffrast/csrc
|
|
COPY nvdiffrast /tmp/nvdiffrast/nvdiffrast
|
|
COPY *.py *.toml *.md *.txt /tmp/nvdiffrast
|
|
RUN TORCH_CUDA_ARCH_LIST="8.0 8.6 8.9 9.0" pip install /tmp/nvdiffrast --no-build-isolation
|