3d-resnets-pytorch
Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.
- License 许可
- MIT
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- 3d-resnets-pytorch
- license
- MIT
- metadata
- { "disco-role": "operating" }
- description
- Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.
- disable-model-invocation
- true
02 资源文件 8
- 参考文档references/cli-reference.md2.2 KB
- 参考文档references/repo-provenance.md1.1 KB
- 参考文档references/repo-routing-metadata.json342 B
- 参考文档references/troubleshooting.md2.0 KB
- 脚本scripts/_torchvision_compat.py1.5 KB
- 脚本scripts/check_imports.py1.8 KB
- 脚本scripts/check_main_help.py1.3 KB
- 脚本scripts/run_main.py1.7 KB
03 SKILL.md 正文
3D ResNets PyTorch
Use this root skill when the user asks about the 3D ResNets PyTorch repository, its CLI flags, its dataset layouts, or its video action-recognition workflows.
Read first
references/cli-reference.mdreferences/troubleshooting.mdreferences/repo-provenance.mdscripts/check_imports.pyscripts/check_main_help.py
What this skill covers
- Training, validation, inference, and fine-tuning for video action recognition.
- Dataset preparation from raw videos into JPEG frame trees, RGB HDF5 files, and annotation JSONs.
- Checkpoint handling, model-family selection, and result evaluation.
- Common data-layout and runtime compatibility pitfalls.
Route to a sub-skill
training-and-inference
Use this route for:
- Fresh training runs, resume flows, and pretrained fine-tuning.
- Validation-only runs and sliding-window inference.
- Result scoring and DataParallel checkpoint cleanup.
- Questions about model families, class counts,
ft_begin_module, orresume_path/pretrain_pathbehavior.
Read:
sub-skills/training-and-inference/SKILL.mdsub-skills/training-and-inference/references/workflows.mdsub-skills/training-and-inference/references/model-catalog.mdsub-skills/training-and-inference/references/troubleshooting.mdsub-skills/training-and-inference/scripts/evaluate_results.pysub-skills/training-and-inference/scripts/strip_dataparallel.py
data-preparation
Use this route for:
- Extracting JPEG frames or RGB HDF5 files from raw videos.
- Building Kinetics, UCF101, HMDB51, MIT, or ActivityNet JSON metadata.
- Adding ActivityNet
fpsfields. - Questions about class directories, split files, HDF5 manifests, or
jpgversushdf5layout.
Read:
sub-skills/data-preparation/SKILL.mdsub-skills/data-preparation/references/workflows.mdsub-skills/data-preparation/references/data-formats.mdsub-skills/data-preparation/references/troubleshooting.mdsub-skills/data-preparation/scripts/extract_video_frames.pysub-skills/data-preparation/scripts/extract_video_hdf5.pysub-skills/data-preparation/scripts/build_annotation_json.py
Quick runtime helpers
scripts/check_imports.pyverifies that the core source modules import from a checkout and applies the temporary legacyScalealias when needed.scripts/check_main_help.pyprints the fullmain.pyCLI help through the same compatibility shim.scripts/run_main.pyforwards into the repository CLI after preparing the checkout and compatibility shim.
Shared environment facts
This repo expects a Python environment with PyTorch, torchvision, pandas, h5py, scikit-learn, joblib, and FFmpeg/FFprobe available on PATH.
A modern torchvision wheel may not expose torchvision.transforms.Scale. If that happens, use the compatibility shim in scripts/_torchvision_compat.py or a legacy torchvision release that still ships Scale.
Route selection guidance
- If the user already has prepared videos and annotation JSONs, start with
training-and-inference. - If the user still needs frames, HDF5 files, or split JSONs, start with
data-preparation. - If the request mentions both, do data preparation first unless the videos and labels are already ready.
- If the user only wants command discovery or environment checks, use the root helpers and the sub-skill references rather than reopening the source repo.
Common handoff sequence
- Prepare or verify the dataset layout with
data-preparation. - Verify the environment with
scripts/check_imports.py. - Inspect the CLI with
scripts/check_main_help.py. - Run the desired training or inference command with
scripts/run_main.py. - Score or clean outputs with the training-and-inference helpers.
Don’t do this
- Do not point future agents back to the original checkout paths.
- Do not use
flowwith JPEG inputs. - Do not assume resume checkpoints can change architecture.
- Do not score
--inference_no_averageJSON with the result evaluator before aggregating segment outputs.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).