Zhiqiang Wang

yolort. yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

sightseq. Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection

demonet. Yet another ssd, with its runtime stack for libtorch, onnx and specialized accelerators.

shufaCV. Python

simple-faster-rcnn. Object detection from torchvision, just make it more convenient to do some experiments.

huo. 🔥 日出江花红胜火，春来江水绿如蓝

zhiqwang.github.io. Codes and Notes

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

yir. yir

yolov5. YOLOv5 in PyTorch > ONNX > CoreML > TFLite

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

zhiqwang. 👋 🌎

nanodet. ⚡Super fast and lightweight anchor-free object detection model. 🔥Only 1.8MB and run 97FPS on cellphone🔥

vision. Datasets, Transforms and Models specific to Computer Vision

keras2ncnn. A keras h5df to ncnn model converter

TensorRT. TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

sightsee. Sightsee is a thin CLI wrapper around netron for opening model files in a browser.

detr. End-to-End Object Detection with Transformers

torchscript-example. Example CMake project for TorchScript

ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform