szagoruyko/attention-transfer
Improving Convolutional Networks via Attention Transfer (ICLR 2017)
This project helps machine learning engineers improve the accuracy of their image classification models. By taking a smaller, less powerful image recognition model and 'teaching' it from a larger, more accurate model, you can get better performance from the smaller model. The end result is a more accurate small model that can classify images more reliably.
1,466 stars. No commits in the last 6 months.
Use this if you need to boost the performance of a compact image classification model, especially when working with datasets like CIFAR-10 or ImageNet.
Not ideal if you are looking for a general-purpose machine learning library outside of convolutional neural network image tasks or if you don't already work with PyTorch.
Stars
1,466
Forks
274
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 11, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/szagoruyko/attention-transfer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
philipperemy/keras-attention
Keras Attention Layer (Luong and Bahdanau scores).
tatp22/linformer-pytorch
My take on a practical implementation of Linformer for Pytorch.
ematvey/hierarchical-attention-networks
Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is...
datalogue/keras-attention
Visualizing RNNs using the attention mechanism
thushv89/attention_keras
Keras Layer implementation of Attention for Sequential models