CVHub520 / efficientvitLinks
EfficientViT is a new family of vision models for efficient high-resolution vision.
☆27Updated last year
Alternatives and similar repositories for efficientvit
Users that are interested in efficientvit are comparing it to the libraries listed below
Sorting:
- Official Pytorch implementation for "IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION" [ICLR 2025]☆57Updated 5 months ago
- [NeurIPS2022] This is the official implementation of the paper "Expediting Large-Scale Vision Transformer for Dense Prediction without Fi…☆85Updated last year
- Zero-label image classification via OpenCLIP knowledge distillation☆134Updated last year
- Official Training and Inference Code of Amodal Expander, Proposed in Tracking Any Object Amodally☆18Updated last year
- Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models☆78Updated 3 months ago
- Codebase for the Recognize Anything Model (RAM)☆82Updated last year
- SAM-CLIP module for use with Autodistill.☆15Updated last year
- HunyuanDiT with TensorRT and libtorch☆17Updated last year
- Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"☆101Updated 11 months ago
- Code of paper "A new baseline for edge detection: Make Encoder-Decoder great again"☆39Updated 2 months ago
- 4th place solution for the Google Universal Image Embedding Kaggle Challenge. Instance-Level Recognition workshop at ECCV 2022☆42Updated 2 years ago
- EdgeSAM model for use with Autodistill.☆27Updated last year
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.☆57Updated last year
- Evaluate the performance of computer vision models and prompts for zero-shot models (Grounding DINO, CLIP, BLIP, DINOv2, ImageBind, model…☆36Updated last year
- Official Pytorch Implementation of Self-emerging Token Labeling☆35Updated last year
- RepGhostNetV2: When RepGhost meets MobileNetV4☆14Updated last year
- Add MobileSAM support for Inpaint anything using Segment Anything and inpainting models.☆52Updated 2 years ago
- Auto Segmentation label generation with SAM (Segment Anything) + Grounding DINO☆20Updated 6 months ago
- ☆49Updated 2 years ago
- Official implementation of the paper: “CountingDINO: A Training-free Pipeline for Exemplar-based Class-Agnostic Counting”☆39Updated 2 months ago
- Estimate dataset difficulty and detect label mistakes using reconstruction error ratios!☆26Updated 7 months ago
- Includes the VideoCount dataset and CountVid code for the paper Open-World Object Counting in Videos.☆66Updated last month
- The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoi…☆24Updated 2 years ago
- EfficientSAM + YOLO World base model for use with Autodistill.☆10Updated last year
- DEYOv1.5☆25Updated last year
- Demo for Qwen2.5-VL-3B-Instruct on Axera device.☆12Updated 3 weeks ago
- A tool convert TensorRT engine/plan to a fake onnx☆41Updated 2 years ago
- ONNX-compatible DocShadow: High-Resolution Document Shadow Removal. Supports TensorRT 🚀☆23Updated last year
- Official PyTorch implementation of "No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding"☆32Updated last year
- Object tracking pipelines complete with RF-DETR, YOLOv9, YOLO-NAS, YOLOv8, and YOLOv7 detection and BYTETracker tracking☆79Updated 2 months ago