rentainhe/visualization
a collection of visualization function
This tool helps researchers and data scientists visually interpret how their computer vision models are 'looking' at images. You provide an image and either bounding box coordinates with attention scores or a grid-based attention mask. It then generates new images that overlay a heatmap on the original image, showing which regions or grids the model focused on, alongside an optional line chart for general data visualization.
449 stars. No commits in the last 6 months.
Use this if you need to visualize the attention mechanisms of your computer vision models on specific images or create simple line charts from numerical data.
Not ideal if you need interactive visualizations, highly customized charts, or complex multi-modal data interpretations.
Stars
449
Forks
41
Language
Python
License
MIT
Category
Last pushed
Jan 15, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rentainhe/visualization"
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