dusty-nv / clip_trt
CLIP and SigLIP models optimized with TensorRT with a Transformers-like API
☆15Updated last month
Related projects ⓘ
Alternatives and complementary repositories for clip_trt
- A tool convert TensorRT engine/plan to a fake onnx☆37Updated last year
- ONNX-compatible LightGlue: Local Feature Matching at Light Speed☆17Updated last year
- Minimal code for Tapir model inference in Pytorch☆15Updated 3 months ago
- LightNet-TRT is a high-efficiency and real-time implementation of convolutional neural networks (CNNs) using Edge AI.☆73Updated last year
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.☆41Updated 7 months ago
- Script to check ONNX model compatibility against TensorRT versions using docker images☆12Updated 11 months ago
- Multi-Object Tracking with Uncertain Detections [ECCV 2024 UnCV]☆52Updated last month
- Starter code for the ICCV 2021 paper, 'Detecting Invisible People'☆31Updated 2 years ago
- ☆22Updated 3 years ago
- Provides a conversion flow for YOLACT_Edge to models compatible with ONNX, TensorRT, OpenVINO and Myriad (OAK). My own implementation of …☆27Updated 2 years ago
- Repository for the paper CenterPoly: real-time instance segmentation using bounding polygons☆49Updated 3 years ago
- Python scripts performing class agnostic object localization using the Object Localization Network model in ONNX.☆17Updated 2 years ago
- BoT-SORT + YOLOX implemented using only onnxruntime, Numpy and scipy, without cython_bbox and PyTorch. Fast human tracker. OSNet is not u…☆24Updated 9 months ago
- EfficientViT is a new family of vision models for efficient high-resolution vision.☆22Updated last year
- ☆47Updated 2 years ago
- Python scripts for performing monocular depth estimation using the SC_Depth model in ONNX☆29Updated 2 years ago
- Tensorrt codebase to inference in c++ for all major neural arch using onnx☆22Updated 2 months ago
- A practice for million-scale multi-domain universal object detection☆22Updated 5 months ago
- ☆35Updated last year
- Implementation of Tracking Every Thing in the Wild, ECCV 2022☆93Updated last month
- Simple tool to change the INPUT and OUTPUT shape of ONNX.☆14Updated 2 years ago
- EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Tracking☆13Updated 10 months ago
- ONNX-compatible DeDoDe 🎶 Detect, Don't Describe - Describe, Don't Detect, for Local Feature Matching. Supports TensorRT 🚀☆63Updated last year
- ☆32Updated this week
- Tracking with Bounding Polygons☆21Updated 2 years ago
- The real-time Instance Segmentation Algorithm Yolov7 running on TensoRT and ONNX☆21Updated 2 years ago
- ☆27Updated last year
- [IEEE Access - 2022] LMOT : Efficient Light-Weight Detection and Tracking in Crowds☆39Updated 2 years ago
- Tracking through Containers and Occluders in the Wild (CVPR 2023) - Official Implementation☆39Updated 5 months ago
- A faster implementation of OpenCV-CUDA that uses OpenCV objects, and more!☆42Updated 2 weeks ago