shanglianlm0525/PyTorch-Networks

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2055 stars · 481 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A collection of PyTorch implementations of classic and modern CNN architectures, covering classification, detection, segmentation, face, and pose estimation networks. It serves as a reference/learning resource for computer vision model implementations.

Use cases

• implement resnet or vgg in pytorch
• learn how yolov3 works by reading code
• find a lightweight mobilenet implementation
• pytorch code for semantic segmentation like fcn
• reference implementations of cnn architectures
• pytorch centernet or retinanet implementation

When to choose

• you want readable reference implementations of many CNN architectures in one place
• you are learning deep learning and want to study model code
• you need a quick starting point for a classic vision backbone

When to avoid

• you need production-ready, well-tested models with pretrained weights and an API
• you need a license-cleared dependency (the repo has no license)
• you need the latest SOTA architectures or active maintenance guarantees

Facets

library · maturity active

machine-learning deep-learning deep-learning computer-vision image-processing python pytorch cnn image-classification object-detection semantic-segmentation model-zoo educational

Member repositories

For agents

markdown · JSON · MCP: product_card(name="shanglianlm0525/PyTorch-Networks")