B站PPT和代码 , 请先查看README以获取提示.

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Papers on 3D Object Detection for Autonomous Driving

Code for https://boxy-dataset.com

MonoLayout: Amodal Scene Layout from a single image

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

High-Fidelity Pluralistic Image Completion with Transformers (ICCV 2021)

Pytorch implementation of "Enhance Image as You Like with Unpaired Learning" (IJCAI 2021)

2.4" 2.8"3.2" 3.5" 5.0" 7.0" TFT LCD driver for the Raspberry PI 3B+/A/A+/B/B+/PI2/ PI3/ZERO/ZERO W

this is the official code for the paper "Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement"

使用 Docker 部署 Shadowsocks 服务端，包含内核参数调优和开启 BBR 算法。

Animation engine for explanatory math videos

服务于极市平台开发者的项目，提供SDK接口文件规范与常见问题示例代码。欢迎所有开发者一起参与示例代码编写。

Me and my Advisors' 3 Months of Research and Project about Fatigue Voice Analysis using Transfer Learning and Convolutional Neural Networks

The Chinese abstract of Cambridge IGCSE Computer Science book.

Python implementation of "A New Image Contrast Enhancement Algorithm Using Exposure Fusion Framework", CAIP2017

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

A simple and accurate method to fool deep neural networks

Count the MACs / FLOPs of your PyTorch model.

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

A simple, fully convolutional model for real-time instance segmentation.

Awesome Crowd Counting

a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results

Generic and easy-to-use serving service for machine learning models

Tensorflow implementation for FreeAnchor: Learning to Match Anchors for Visual Object Detection, support for training your own dataset.

An open-source PyTorch code for crowd counting