# TommyZihao/Train_Custom_Dataset

标注自己的数据集，训练、评估、测试、部署自己的人工智能算法

Repository: https://github.com/TommyZihao/Train_Custom_Dataset
Canonical: https://ross.abutalabs.com/products/train_custom_dataset
Language: Jupyter Notebook
License Family: other
Last push: 2026-01-07T14:44:51+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 61, release rhythm 35, longevity 100
- inputs: {"age_days": 1502, "days_push": 238, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4096, forks 764 (observed 2026-08-28T04:08:34.688382+00:00)

## What it is
A free open-source Chinese tutorial collection (Jupyter Notebooks plus videos) teaching how to annotate your own datasets and train, evaluate, test, and deploy AI models, primarily with PyTorch. It covers image classification, transfer learning, object tracking, OCR, style transfer, and LLM summarization, aimed at helping students complete AI graduation projects.

## Use cases
- learn to train a custom image classification model with pytorch
- annotate my own dataset for machine learning
- fine-tune a pretrained imagenet model on my images
- evaluate a classifier with confusion matrix and roc curves
- visualize model features with tsne and umap
- do an ai graduation project in two days
- learn ocr text recognition and cyclegan style transfer

## When to choose
- you are a student or beginner wanting guided, video-backed tutorials in Chinese for training custom vision models
- you need end-to-end coverage from dataset annotation to deployment for a course or thesis project

## When to avoid
- you need production-grade, maintained library code rather than educational notebooks
- you require a permissively licensed dependency - the repo has no license and restricts use to non-commercial teaching and research

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, image-processing, computer-vision, ocr, data-science
- domain: deep-learning, computer-vision, education, tutorials, artificial-intelligence
- platform: python, cross-platform
- tags: pytorch, jupyter-notebook, transfer-learning, image-classification, dataset-annotation, chinese, graduation-project, model-deployment, tsne, cyclegan, gpu

## Member repositories
- TommyZihao/Train_Custom_Dataset (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.688382+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:18.904223+00:00, confidence not recorded.
  - readme: https://github.com/TommyZihao/Train_Custom_Dataset (fetched 2026-08-28T04:08:34.688382+00:00, sha 1706a64dd12e)
- Data as of 2026-08-30T08:39:29.467469+00:00.