GuideWsp's starred repositories
lite.ai.toolkit
🛠 A lite C++ toolkit of awesome AI models, support ONNXRuntime, MNN. Contains YOLOv5, YOLOv6, YOLOX, YOLOR, FaceDet, HeadSeg, HeadPose, Matting etc. Engine: ONNXRuntime, MNN.
PINTO_model_zoo
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
Awesome-Deblurring
A curated list of resources for Image and Video Deblurring
MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
involution
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
Transformer-in-Vision
Recent Transformer-based CV and related works.
CoordAttention
Code for our CVPR2021 paper coordinate attention
Low-Level-Vision-Paper-Record
记录近期的 1) 图像/视频的超分增强等low level vision任务; 2) 图像生成 等任务相关论文, 主要为18年以后的DL based方法.
DiverseBranchBlock
Diverse Branch Block: Building a Convolution as an Inception-like Unit
Neighbor2Neighbor
Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
halonet-pytorch
Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones