vlfeat/matconvnet

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1430 stars · 740 forks observed · 2026-08-28

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

MatConvNet is a MATLAB toolbox implementing convolutional neural networks (CNNs) for computer vision applications. It supports training and running state-of-the-art CNNs with GPU acceleration via CUDA, and includes pretrained example networks for image classification and feature encoding.

Use cases

• train a cnn in matlab
• run pretrained image classification models
• extract image features with a deep network
• implement custom convolutional neural network layers
• gpu-accelerated deep learning without python
• computer vision research prototyping in matlab

When to choose

• your workflow is already MATLAB-based
• you need a simple, self-contained CNN framework for vision research
• you want to modify network internals at the MATLAB level

When to avoid

• you need a modern actively developed framework like PyTorch or TensorFlow
• you work outside MATLAB
• you need large ecosystem support, deployment tooling, or recent model architectures

Facets

library · maturity maintenance

deep-learning machine-learning image-processing computer-vision gpu-computing deep-learning machine-learning computer-vision image-processing windows cnn matlab-toolbox cuda neural-networks computer-vision matlab gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vlfeat/matconvnet")