$ show opencv/opencv_zoo
OpenCV Zoo is a curated collection of pre-trained computer vision models optimized for OpenCV's DNN module, accompanied by inference demo scripts (Python and C++), benchmarking harness, evaluation tools, and quantization utilities. The repository serves as a practical resource for deploying models on a wide range of hardware (x86, ARM, RISC-V, NPUs) by providing ready-to-run code for tasks such as face detection/recognition, object detection, segmentation, text detection/recognition, pose estimation, and more. While primarily an application-oriented model zoo, it also includes research-grade evaluation metrics (e.g., LFW, WIDERFace) and quantization workflows, giving it a hybrid character that bridges model deployment and performance characterization. The benchmarking framework and quantization tools are the most architecturally coherent parts; model-specific demos are utilitarian but tightly coupled to their respective ONNX graphs.
The LLM identified 1 files worth highlighting for reuse:
A standalone Python script that performs block-wise quantization of Conv, Gemm, and MatMul weights in ONNX models. It traverses the model graph, extracts weight tensors, applies block partitioning and quantization (supporting 8/16-bit), and writes the quantized ONNX model. The script is fully independent (only depends on `onnx` and `argparse`) and can be extracted and applied to any ONNX model without modification, representing a non-trivial utility for model compression.