HankYe/PAGCP
[T-PAMI'23] PAGCP for the compression of YOLOv5
When working with computer vision models like YOLOv5 for object detection, these models can often be too large and slow for deployment on devices with limited computing power, such as mobile phones or embedded systems. This project helps by taking your existing YOLOv5 model and outputting a significantly smaller and faster version, while maintaining most of its accuracy for tasks like identifying objects in images. It's designed for engineers and researchers deploying AI vision solutions where model size and speed are critical.
121 stars. No commits in the last 6 months.
Use this if you need to deploy YOLOv5 models on edge devices or in cloud environments where computational resources (FLOPs, parameters) are severely constrained, and you need to reduce model size and inference time without major performance loss.
Not ideal if your primary goal is to train a new, highly accurate object detection model from scratch without any concerns about model size, speed, or deployment on resource-limited hardware.
Stars
121
Forks
10
Language
Python
License
GPL-3.0
Category
Last pushed
Apr 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/HankYe/PAGCP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
weiyithu/NerfingMVS
[ICCV 2021 Oral] NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
Jumpat/SegmentAnythingin3D
Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)
POSTECH-CVLab/SCNeRF
[ICCV21] Self-Calibrating Neural Radiance Fields
half-potato/nmf
Our method takes as input a collection of images (100 in our experiments) with known cameras,...
synthesiaresearch/humanrf
Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"