The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many mo…

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.

Useful tensorrt plugin. For pytorch and mmdetection model conversion.

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP & Whisper - Automatically Detect , Segment and Generate Anything with Image, Text, and Speech Inputs

OpenMMLab Detection Toolbox and Benchmark

Torchreid: Deep learning person re-identification in PyTorch.

SOTA Re-identification Methods and Toolbox

Map handling framework for automated driving

[CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

Lidar-Monocular Visual Odometry

Convert KITTI dataset to ROS bag file the easy way!

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

A multi-gpu implementation of the self-organizing map in TensorFlow