Machine Learning · GitHub

Awesome-ComputerVision

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

"A neural algorithm of Artistic style" in tensorflow

A deep learning library built from scratch with complex neural networks examples built on top for learning purposes.

Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

因为我当时正在用 fast.ai 的 ULMfit 做自然语言分类任务（还专门写了《如何用 Python 和深度迁移学习做文本分类？》一文分享给你）。ULMfit 和 BERT 都属于预训练语言模型（Pre-trained Language Modeling），具有很多的相似性。

PyTorch code for "PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer" (CVPR 2020 Oral)

Curated list of tools and resources related to the use of machine learning for cyber security

A simple effective ToolKit for short text matching

Next RecSys Library

• Cross platform - run on any operating system with the available Docker images;
• State-of-the-art - 33 neural recommender models available out of the box;

Yolov5+SlowFast: Realtime Action Detection Based on PytorchVideo

A powerful baseline for image classification, face recognition and image retrieval with Pytorch

• Training engine: Unified training flow for classification and embedding-based recognition tasks.
• Optimization algorithms: SGD, Adam, SAM, layer-specific learning rates, and related training strategies.

face recognition algorithms in pytorch framework, including arcface, cosface, sphereface and so on

局部监督驱动的有界增量融合人脸伪造检测（LBIF）

End-to-end Lane Detection for Self-Driving Cars (ICCV 2019 Workshop)

Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st place on KITTI) [MVA 2019]