WZMIAOMIAO/deep-learning-for-image-processing resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

26359 stars · 8176 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Chinese-language educational repository of deep learning tutorials for image processing, covering classification, object detection, and segmentation networks. Each architecture (LeNet through Vision Transformer) is implemented and trained in both PyTorch and TensorFlow2, accompanied by Bilibili video lectures and PPT slides.

Use cases

• learn deep learning for image classification from scratch
• understand how ResNet or Vision Transformer works with code
• implement object detection networks in PyTorch and TensorFlow
• study classic CNN architectures like VGG and GoogLeNet
• find tutorial code for semantic segmentation models
• follow a video course on deep learning for computer vision

When to choose

• you want guided tutorials with video explanations alongside code
• you want to see the same network implemented in both PyTorch and TensorFlow2
• you are a student or beginner learning image classification, detection, or segmentation

When to avoid

• you need production-ready, maintained model implementations
• you need English-language documentation
• you need a packaged library with pip installation and stable APIs

Facets

learning-resource · maturity active

deep-learning machine-learning image-processing computer-vision deep-learning computer-vision image-processing tutorials python pytorch tensorflow2 image-classification object-detection semantic-segmentation bilibili-videos educational vision-transformer

Member repositories

For agents

markdown · JSON · MCP: product_card(name="WZMIAOMIAO/deep-learning-for-image-processing")