# Captain1986/CaptainBlackboard

船长关于机器学习、计算机视觉和工程技术的总结和分享

Repository: https://github.com/Captain1986/CaptainBlackboard
Canonical: https://ross.abutalabs.com/products/captainblackboard
Language: C++
License: MIT
License Family: permissive
Topics: deep-learning, computer-vision, convolutional-neural-networks, optimization-algorithms, summary
Last push: 2023-04-28T07:37:48+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2773, "days_push": 1223, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1269, forks 200 (observed 2026-08-28T04:04:11.710541+00:00)

## What it is
A collection of technical notes and tutorials (in Chinese) covering machine learning, deep learning, computer vision, and C++ engineering topics, written as a series of 'blackboard' articles. It includes worked explanations of CNNs, loss functions, SVM, kNN, dimensionality reduction, and practical engineering tricks.

## Use cases
- learn deep learning fundamentals with worked examples
- understand why cross-entropy is used as a classification loss
- study depthwise separable convolutions in MobileNet
- find tips for tuning deep learning hyperparameters
- learn common methods for handling imbalanced samples
- review machine learning basics like SVM and kNN
- learn C++ engineering tricks like embedding git commit SHA into binaries

## When to choose
- you want concise Chinese-language explanations of ML/CV theory and practice
- you prefer article-style notes over full courses or textbooks
- you need quick refreshers on classic algorithms and loss functions

## When to avoid
- you need up-to-date content on modern LLMs or recent architectures
- you want runnable, maintained code libraries rather than written notes
- you need English-language material

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing, nlp, math, developer-tools
- domain: deep-learning, computer-vision, machine-learning, tutorials, developer-tools
- platform: cross-platform
- tags: technical-blog, chinese-language, notes, cnn, optimization, engineering-tips, algorithms

## Member repositories
- Captain1986/CaptainBlackboard (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:11.710541+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 2026-08-30T05:03:29.564271+00:00, confidence not recorded.
  - readme: https://github.com/Captain1986/CaptainBlackboard (fetched 2026-08-28T04:04:11.710541+00:00, sha c8cbb69d3786)
- Data as of 2026-08-30T08:39:29.467469+00:00.