sara-nl/attention-sampling-pytorch
This is a PyTorch implementation of the paper: "Processing Megapixel Images with Deep Attention-Sampling Models".
This project helps researchers and machine learning practitioners who work with very large images, like those found in medical imaging or high-resolution surveillance, to train deep learning models more efficiently. It takes megapixel images and outputs trained models capable of tasks like object detection, without needing to process every pixel of the enormous input image. Scientists and engineers developing computer vision solutions for large-scale imagery would find this useful.
No commits in the last 6 months.
Use this if you are a researcher or practitioner in computer vision dealing with extremely high-resolution images where traditional deep learning methods are too computationally expensive.
Not ideal if you need perfectly reproducible results from the original paper's claims, as this PyTorch implementation currently shows higher error rates and potential bugs.
Stars
41
Forks
9
Language
Python
License
MIT
Category
Last pushed
Oct 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sara-nl/attention-sampling-pytorch"
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.
datalogue/keras-attention
Visualizing RNNs using the attention mechanism
ematvey/hierarchical-attention-networks
Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is...
thushv89/attention_keras
Keras Layer implementation of Attention for Sequential models