Reference github repository for the paper "Defocus Deblurring Using Dual-Pixel Data". We introduce a deep neural network (DNN) architecture that uses the dual-pixel (DP) sub-aperture views to reduc…

DAIN, Depth-Aware Video Frame Interpolation implemented with ncnn library

Mobile-LPR 是一个面向移动端的准商业级车牌识别库，以NCNN作为推理后端，使用DNN作为算法核心，支持多种车牌检测算法，支持车牌识别和车牌颜色识别。

train mxnet unet, then run it in ncnn

yoloface大礼包 使用pytroch实现的基于yolov3的轻量级人脸检测（包含关键点）

Real-time pose estimation and action recognition

Person segmentation with Keras (SegNet, Unet, etc.)

3D Unet biomedical segmentation model for BraTS2019

loss for medical image segmentation use keras(python)

Object Detection and Multi-Object Tracking

onnx-tensorrt for yolov3

TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.

unet for image segmentation

Convert yolov4-tiny darknet weights to the bp model of TensorFlow

This repo under development to convert keras-yolov3 model to OpenVINO.

a baseline for baidu dog classification competition.

Keras 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation

基于CNN的验证码整体识别

Automatic Liver Segmentation of CT Volumes Using 2D Attention-UNet

Unet, ResUnet, DenseUnet, SE-ResUnet, Dual Attention ResUnet, Attention Gates ResUnet

Binary semantic segmentation with UNet based on MobileNetV2 encoder

Official implementation of DoubleU-Net for Semantic Image Segmentation in TensorFlow & Pytorch (Nominated for Best Paper Award (IEEE CBMS))

Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai

Keras implementation of Holistically-nested edge detection

Holistically-Nested Edge Detection in Keras

residual attention unet for tumor segmentation (liver and brain)

An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"

Build keras models for 9 Tasks in AI-Benchmark: Object Detection: Mobile-v2, Inception-v3, Face Recognition: Inception-Resnet-v1, Super Resolution: SRCNN, VDSR, SRGAN, Resnet-12+GAN, and Semantic S…

OpenCV practical exercise