Timer-x

Timer-x's Stars

• Thinklab-SJTU/Bench2Drive

  Cloased-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

  Language:Python1.1k78

• Thinklab-SJTU/Bench2DriveZoo

  BEVFormer, UniAD, VAD in Closed-Loop CARLA Evaluation with World Model RL Expert Think2Drive

  Language:Python1136

• NVlabs/OmniDrive

  Language:Python1956

• LLaVA-VL/LLaVA-NeXT

  Language:Python2.4k166

• hustvl/VAD

  [ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

  Language:Python61960

• XiaoMi/CGNet

  The official implementation of the ECCV 2024 paper: Continuity Preserving Online CenterLine Graph Learning

  Language:Python172

• intelligent-machine-learning/dlrover

  DLRover: An Automatic Distributed Deep Learning System

  Language:Python1.2k147

• binary-husky/gpt_academic

  为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

  Language:Python64k7.9k

• hustvl/LaneGAP

  [ECCV 2024] Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

  1192

• BlinkDL/RWKV-LM

  RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

  Language:Python12.4k838

• aassxun/Equiangular-Basis-Vectors

  Language:Python488

• open-mmlab/mmcv

  OpenMMLab Computer Vision Foundation

  Language:Python5.8k1.6k

• hieubkset/keras-image-super-resolution

  EDSR, RCAN, SRGAN, SRFEAT, ESRGAN

  Language:Python23140

• sanghyun-son/EDSR-PyTorch

  PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

  Language:Python2.4k669

• Mrmoore98/VectorMapNet_code

  This is the official code base of VectorMapNet (ICML 2023)

  Language:Python40155

• solidsea98/Neural-Corpus-Indexer-NCI

  Language:Python14919

• fundamentalvision/BEVFormer

  [ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

  Language:Python3.2k524

• OpenDriveLab/PersFormer_3DLane

  [ECCV 2022 Oral] Perspective Transformer on 3D Lane Detection

  Language:Python42675

• IDEA-Research/DN-DETR

  [CVPR 2022 Oral] Official implementation of DN-DETR

  Language:Python53761

• Tsinghua-MARS-Lab/HDMapNet

  Language:Python681123

• Megvii-BaseDetection/BEVDepth

  Official code for BEVDepth.

  Language:Python70698

• hustvl/MapTR

  [ICLR'23 Spotlight & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

  Language:Python1.1k161

• megvii-research/RealFlow

  The official implementation of the ECCV 2022 Oral paper: RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos

  Language:Python9311

• open-mmlab/mmdetection

  OpenMMLab Detection Toolbox and Benchmark

  Language:Python29.1k9.4k

• princeton-vl/RAFT

  Language:Python3.2k623

• aleju/imgaug

  Image augmentation for machine learning experiments.

  Language:Python14.3k2.4k

• coolbeam/UPFlow_pytorch

  PyTorch implementation of UPFlow (unsupervised optical flow learning)

  Language:Python12514

• palletone/go-palletone

  Official Go implementation of PalletOne

  Language:Go8624