Flashtorch: Visualize PyTorch Model Features

Understand the project

Practical overview

Use Flashtorch when you have a PyTorch image model and want visual feature-analysis examples or utilities for saliency and activation maximization.

Generate an image-specific saliency map to see which regions are associated with a selected class response.
Visualize what a CNN filter responds to by maximizing its activation.
Use image-handling utilities and ImageNet class-index lookup in a model-analysis workflow.

Before you choose

The toolkit is distributed as a Python package installable with pip.
The documented visualizations focus on image models and CNN feature analysis.
The repository provides example notebooks, including Colab versions for saliency and activation maximization.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install FlashTorch for use with PyTorch neural-network visualization.

Run the command below to install FlashTorch.
Documented command
```
pip install flashtorch
```
For an existing installation that you want to upgrade, run the command below instead.
Documented command
```
pip install flashtorch -U
```

FlashTorch is installed or upgraded in the Python environment where pip was run.

This covers installation only; it does not document running a visualization.
FlashTorch is described as a PyTorch visualization toolkit; the README does not specify further installation prerequisites.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 7 November 2026
Original website title: MisaOgura/flashtorch · Official homepage title · retained in its source language