liuyang-ict/SAP-DETR

[CVPR 2023] Official implementation of "SAP-DETR: Bridging the Gap between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency "

32
/ 100
Emerging

This project helps computer vision researchers and practitioners efficiently detect objects within images. You feed it raw image data, and it outputs precise bounding box coordinates for identified objects, accelerating the training process for object detection models. This is ideal for those working on real-time image analysis, autonomous systems, or large-scale content moderation.

No commits in the last 6 months.

Use this if you need to train object detection models significantly faster while maintaining high accuracy, especially when working with Transformer-based architectures.

Not ideal if you are looking for a pre-trained, ready-to-use application and do not have expertise in training machine learning models.

object-detection computer-vision image-analysis deep-learning model-training-acceleration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

30

Forks

3

Language

Python

License

Apache-2.0

Last pushed

May 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/liuyang-ict/SAP-DETR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.