Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Visualization toolkit for neural networks in PyTorch! Demo -->
| Date | Stars |
|---|---|
| 2026-07-31 | 743 |
| 2026-08-01 | 743 |
| 2026-08-02 | 743 |
| 2026-08-06 | 743 |
| 2026-08-11 | 743 |
| 2026-08-12 | 743 |
| 2026-08-18 | 743 |
| 2026-08-24 | 744 |
| 2026-09-16 | 744 |
| 2026-09-20 | 744 |
Today
— stars today
This week
— stars this week
This month
+1 stars this month
Momentum
0.0
growth rate 0.00%/day
# FlashTorch [](https://pypi.org/project/flashtorch/) [](https://travis-ci.com/MisaOgura/flashtorch) [](https://pypi.org/project/flashtorch/) [](https://github.com/MisaOgura/flashtorch/blob/master/LICENSE) [](https://zenodo.org/badge/latestdoi/177140934) [](https://saythanks.io/to/MisaOgura) A Python visualization toolkit, built with PyTorch, for neural networks in PyTorch. Neural networks are often described as "black box". The lack of understanding on how neural networks make predictions enables unpredictable/biased models, causing real harm to society and a loss of trust in AI-assisted systems. **Feature visualization** is an area of research, which aims to understand how neural networks _perceive_ images. However, implementing such techniques is often complicated. **FlashTorch was created to solve this problem!** You can apply feature visualization techniques (such as **[saliency maps](#saliency-maps-flashtorchsaliency)** and **[activation maximization](#activation-maximization-flashtorchactivmax)**) on your model, with as little as _a few lines of code_. It is compatible with pre-trained models that come with [torchvision](https://pytorch.org/docs/stable/torchvision/models.html), and seamlessly integrates with other custom models built in PyTorch. ### Interested? Take a look at the quick 3min intro/demo to FlashTorch below! [](https://youtu.be/18Iw4qYqfPo) ### Want to try? Head over to example notebooks on Colab! - Saliency maps: [](https://colab.research.google.com/github/MisaOgura/flashtorch/blob/master/examples/visualize_saliency_with_backprop_colab.ipynb) - Activation maximization: [](https://colab.research.google.com/github/MisaOgura/flashtorch/blob/master/examples/activation_maximization_colab.ipynb) ## Overview - [Installation](#installation) - [Quickstart](#quickstart) - [Use FlashTorch](#use-flashtorch) - [Develop FlashTorch](#develop-flashtorch) - [How to contribute](#how-to-contribute) - [Resources](#resources) - [Citation](#citation) - [Author](#author) ## Installation If you are installing FlashTorch for the first time: ```bash $ pip install flashtorch ``` Or if you are upgrading it: ```bash $ pip install flashtorch -U ``` ### API guide These are currently available modules. - `flashtorch.utils`: some useful utility functions for data handling & transformation - `flashtorch.utils.imagenet`: `ImageNetIndex` class for easy-ish retrieval of class index - `flashtorch.saliency.backprop`: `Backprop` class for calculating gradients - `flashtorch.activmax.gradient_ascent`: `GradientAscent` class for activation maximization You can inspect each module with Python built-in function `help`. The output of that is available on [Quick API Guide](https://github.com/MisaOgura/flashtorch/wiki/Quick-API-Guide) for your convenience. ## Quickstart ### Use FlashTorch Below, you can find simple demos to get you started, as well as links to some handy notebooks showing additional examples of using FlashTorch. #### Image handling (`flashtorch.utils`) - [Image handling](https://github.com/MisaOgura/flashtorch/blob/master/examples/examples/image_handling.ipynb) notebook #### Saliency maps (`flashtorch.saliency`) - [Saliency map with backpropagation](https://github.com/MisaOgura/flashtorch/blob/master/examples/visualize_saliency_with_backprop.ipynb) notebook - [Go
Excerpt of 9,976 characters
Read on GitHub
126
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ffde3cf368b9d237, topic:deep-learning, topic:pytorch
matched fp:ffde3cf368b9d237, topic:interpretability