act-plus-plus Public

Imitation Learning algorithms with Co-traing for Mobile ALOHA: ACT, Diffusion Policy, VINN

mobile-aloha Public

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

EmotiVoice Public

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

PETR Public

[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection

cam-notes Public

My Cambridge Lecture Notes

MonoScene Public

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

Fast-BEV Public

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

mmclassification Public

OpenMMLab Image Classification Toolbox and Benchmark

mmdetection3d Public

OpenMMLab's next-generation platform for general 3D object detection.

mmsegmentation Public

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

pytorch-GAT Public

My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entr...

NAB Public

The Numenta Anomaly Benchmark

tpu-mlir Public

Machine learning compiler based on MLIR for Sophgo TPU.

mmyolo Public

OpenMMLab YOLO series toolbox and benchmark

flannel Public

flannel is a network fabric for containers, designed for Kubernetes

yolov5 Public

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

yolov3 Public

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

second.pytorch Public

SECOND for KITTI/NuScenes object detection

5gc-manifests Public

Kubernetes manifest files for 5G network

darknet Public

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

CLUT-Net Public

比香港理工20年自适应3DLUT高效压缩99%参数量,一个轻量型图像增强方案

faceswap Public

Deepfakes Software For All

Grid-Anchor-based-Image-Cropping-Pytorch Public

PyTorch implementation of "Grid anchor based image cropping"

FCOS_PLUS Public

Some improvements (center sample) about FCOS (FCOS: Fully Convolutional One-Stage Object Detection).

FCOS Public

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

Image-Adaptive-3DLUT Public

Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time

EssayTopicPredict Public

高考作文题目预测模型 v1.0

ColossalAI Public

Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training

StyleGAN-Human Public

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

GAT Public

Graph Attention Networks (https://arxiv.org/abs/1710.10903)