LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

🔖🔄 | YOLO to VOC format <> VOC to YOLO format | Multiprocessing support

⚡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

This is the official repository for our recent work: PIDNet

📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

deep learning for image processing including classification and object-detection etc.

📚 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition (https://arxiv.org/pdf/2006.11538.pdf)

Simple Tensorflow implementation of "Squeeze and Excitation Networks" using Cifar10 (ResNeXt, Inception-v4, Inception-resnet-v2)

MMD and Relative MMD test

Caffe: a fast open framework for deep learning.

PyTorch 官方中文教程包含 60 分钟快速入门教程，强化教程，计算机视觉，自然语言处理，生成对抗网络，强化学习。欢迎 Star，Fork！

Synthesizing and manipulating 2048x1024 images with conditional GANs

Tensorflow Faster RCNN for Object Detection

Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/

Image-to-Image Translation in PyTorch

Image-to-image translation with conditional adversarial nets

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels, IEEE International Conference on Computer Vision (ICCV), 2019

Semi-Supervised Object Detection and Segmentation from Bounding Box Annotations.

Semi Supervised implementation of YOLOv3 for object detection using Pytorch

OCR, Scene-Text-Understanding, Text Recognition

A curated list of resources for text detection/recognition (optical character recognition ) with deep learning methods.

A curated list of resources dedicated to scene text localization and recognition

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

Convolutional Neural Networks

Complete YOLO v3 TensorFlow implementation. Support training on your own dataset.