rhysdg / vision-at-a-clipLinks
Low-latency ONNX and TensorRT based zero-shot classification and detection with contrastive language-image pre-training based prompts
☆43Updated last year
Alternatives and similar repositories for vision-at-a-clip
Users that are interested in vision-at-a-clip are comparing it to the libraries listed below
Sorting:
- Code from the paper "Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models"☆98Updated last month
- Accelerate segment anything model inference using Tensorrt 8.6.1.6☆101Updated 2 years ago
- Exporting Segment Anything, MobileSAM, and Segment Anything 2 into ONNX format for easy deployment☆368Updated last year
- ContourFormer:Real-Time Contour-Based End-to-End Instance Segmentation Transformer☆25Updated 6 months ago
- Zero-label image classification via OpenCLIP knowledge distillation☆137Updated 2 years ago
- ☆128Updated 2 years ago
- DeepStream Libraries offer CVCUDA, NvImageCodec, and PyNvVideoCodec modules as Python APIs for seamless integration into custom framewor…☆70Updated 2 months ago
- ☆193Updated 5 months ago
- Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection☆93Updated 8 months ago
- Deploy RT-EDTR with onnx from paddlepaddle framwork and graph cut☆31Updated 2 years ago
- Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models☆83Updated 6 months ago
- Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"☆44Updated 2 years ago
- The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoi…☆24Updated 2 years ago
- (CVPR 2024) Point, Segment and Count: A Generalized Framework for Object Counting☆118Updated last year
- This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point …☆174Updated 2 years ago
- MobileSAM already integrated into Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆41Updated 2 years ago
- The Go-To Choice for CV Data Visualization, Annotation, and Model Analysis.☆257Updated last year
- It is a simple library to speed up CLIP inference up to 3x (K80 GPU)☆225Updated 2 years ago
- [ICCV2023] TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance☆115Updated last year
- Code for replicating Roboflow 100 benchmark results and programmatically downloading benchmark datasets☆283Updated last year
- An ONNX-based implementation of the CLIP model that doesn't depend on torch or torchvision.☆75Updated last year
- ☆79Updated 2 years ago
- Quick exploration into fine tuning florence 2☆334Updated last year
- Codebase for the Recognize Anything Model (RAM)☆87Updated last year
- ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection (CVPR2023)☆54Updated 2 years ago
- Grounding DINO module for use with Autodistill.☆22Updated last year
- Train InternViT-6B in MMSegmentation and MMDetection with DeepSpeed☆105Updated last year
- [ICCV2025] Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark☆172Updated last month
- Rex-Thinker: Grounded Object Refering via Chain-of-Thought Reasoning☆127Updated 4 months ago
- Combining "segment-anything" with MOT, it create the era of "MOTS"☆155Updated 2 years ago