jianghaojun/CondenseNetV2
[CVPR 2021] CondenseNet V2: Sparse Feature Reactivation for Deep Networks
This project offers an improved deep learning model for computer vision tasks like image classification and object detection. It takes raw image datasets (e.g., ImageNet, COCO) and outputs highly accurate, yet computationally efficient, trained models. Researchers and practitioners working on vision AI applications will find this useful for developing high-performance image analysis systems.
No commits in the last 6 months.
Use this if you need to train deep neural networks for image classification or object detection with higher accuracy and better computational efficiency than previous CondenseNet models.
Not ideal if your primary goal is real-time inference on very resource-constrained edge devices without access to standard deep learning frameworks.
Stars
86
Forks
19
Language
Python
License
MIT
Category
Last pushed
Aug 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jianghaojun/CondenseNetV2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)