AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

A list of all named GANs!

A command-line tool to download photos from iCloud

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image …

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Object detection, 3D detection, and pose estimation using center point detection:

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Simple examples to introduce PyTorch

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes

pytorch implementation for "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" https://arxiv.org/abs/1612.00593

Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .

Pytorch implementation for few-shot photorealistic video-to-video translation.

🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)

CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Residual networks implementation using Keras-1.0 functional API

SemanticKITTI API for visualizing dataset, processing data, and evaluating results.

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

PyTorch Implementations for DeeplabV3 and PSPNet

Fully Convolutional Geometric Features: Fast and accurate 3D features for registration and correspondence.

Jittor implementation of PCT:Point Cloud Transformer

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.