堆糖素材网爬虫

梦弘浏览器 自主研发版本 - 完全自主研发，打破国外垄断，比 Chrome 快 600%。缺少上网功能。

梦弘浏览器 - 完全自主研发，打破国外垄断，比 Chrome 快 600%。

The fundamental package for scientific computing with Python.

OpenMMLab Detection Toolbox and Benchmark

[NeurIPS 2020] Semi-Supervision (Unlabeled Data) & Self-Supervision Improve Class-Imbalanced / Long-Tailed Learning

95.16% on CIFAR10 with PyTorch

PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MobileNet-V3/V2/V1, MNASNet, Single-Path NAS, FBNet, and more

Face Recognition Loss on Mnist, Pytorch implementation

An open-source headphone testing/analyzing tool

Class-Balanced Loss Based on Effective Number of Samples

An open library of computer vision algorithms

My implementation of paper: SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

A Richly Annotated Pedestrian Dataset for Person Retrieval in Real Surveillance Scenarios

My implementation of Spectral-Feature-Transformation-ReID, link to the paper: https://arxiv.org/abs/1811.11405

Layer-wise Adaptive Rate Scaling in PyTorch

Background subtraction using deep learning method.