training-and-inference
Routes training, fine-tuning, validation, checkpoint, and inference workflows for 3D ResNets PyTorch.
- License 许可
- MIT
- 最近更新
- 2026-10-08
- Stars
- ★ 11
- Forks
- 3
01 前言 Front Matter
- name
- training-and-inference
- license
- MIT
- metadata
- { "disco-role": "operating" }
- description
- Routes training, fine-tuning, validation, checkpoint, and inference workflows for 3D ResNets PyTorch.
- disable-model-invocation
- true
02 资源文件 3
- 参考文档references/model-catalog.md3.3 KB
- 参考文档references/troubleshooting.md3.1 KB
- 参考文档references/workflows.md7.1 KB
03 SKILL.md 正文
training-and-inference
Use this sub-skill when you need to train, fine-tune, validate, resume, or run inference for this repository's main.py-style workflows without reopening the source checkout.
Use this route for
- Fresh training runs and stage-wise fine-tuning.
- Checkpoint save/resume, optimizer state recovery, and milestone handling.
- Loading pretrained weights with a different final class count.
- Validation, multi-clip inference, and result scoring.
- DataParallel checkpoint cleanup before reuse or inspection.
Do not use this route for
- Raw video extraction or annotation JSON creation. Use data-preparation.
- Repo-wide routing or root skill selection. Use the root router.
- Model conversion or export outside the
main.pytraining loop.
Read first
references/workflows.mdreferences/model-catalog.mdreferences/troubleshooting.md- the root router
- the root run helper
- data-preparation when dataset layout is not ready
Skill-owned scripts
scripts/evaluate_results.py— score top-k recognition results against a ground-truth JSON.scripts/strip_dataparallel.py— removemodule.prefixes from checkpoint state dicts.
Typical flow
- Confirm the dataset tree and annotation JSON already exist.
- Pick a model family and depth from
references/model-catalog.md. - Choose scratch train, resume, or fine-tune flags in
references/workflows.md. - Run the root-level
main.pywrapper from the repo skill tree. - Evaluate results with
scripts/evaluate_results.pyor clean checkpoints withscripts/strip_dataparallel.pywhen needed.
Cross-links
- Dataset preparation and layout prerequisites: data-preparation
- Repo-level routing: root router
- Root
main.pywrapper: run_main helper
04 同仓库更多 Skills
obsidian-clipper-template-creator
Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.
obsidian-clipper-template-creator
Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.
python-api
Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP/mAP semantics, and source-style import diagnostics.
file-evaluation
Folder-based PASCAL VOC AP/mAP evaluation from ground-truth and detection text files.
object-detection-metrics
Guides legacy Object-Detection-Metrics PASCAL VOC AP/mAP evaluation from detection text folders and direct Python API classes.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.