peng-zhihui/DeepVision

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1942 stars · 399 forks observed · 2026-08-28

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

DeepVision is an Android-based computer vision algorithm inference and validation framework by peng-zhihui. It decouples data flow control, NN inference engines (SNPE, TensorFlow Lite), and UI layers, and ships model optimization tools for quantization, pruning, and conversion.

Use cases

• validate cv models on mobile devices
• run yolo or mtcnn inference on android
• quantize a tensorflow model to 8bit for mobile
• convert onnx models for snpe deployment
• test camera video stream against a deep learning model
• benchmark pretrained models on android

When to choose

• you need a ready-made Android app framework to validate CV models without writing app code
• you want integrated SNPE or TensorFlow Lite inference with camera and image pipelines
• you need bundled model quantization, pruning, and conversion tools

When to avoid

• you need an iOS or cross-platform deployment framework
• you want a maintained production inference server rather than a validation app
• you need a framework with active recent development and community support

Facets

framework · maturity maintenance

computer-vision machine-learning image-processing sdk developer-tools computer-vision machine-learning mobile-development deep-learning cpp jvm model-inference mobile-deployment snpe tensorflow-lite model-quantization model-pruning opencv model-zoo android-app android mobile

Member repositories

For agents

markdown · JSON · MCP: product_card(name="peng-zhihui/DeepVision")