torch-anatomy 0.1.1

Layer-by-layer visualizer for PyTorch models

torch-anatomy

Layer-by-layer visualizer for PyTorch models — Understand what each layer actually does.

Install

pip install torch-anatomy

Usage

from torch_anatomy import visualize_layers
from torchvision import models

model = models.resnet18(pretrained=True)
visualize_layers(
    model=model,
    input_image='dog.jpg',
    layers_to_show=['Conv2d', 'ReLU'],
    channels_per_layer=6,
    colormap='inferno',
    show_colorbar=True
)

Or from CLI:

torch-anatomy --model resnet18 --image dog.jpg

Features

• Plug-and-play for any PyTorch CNN
• Visualizes feature maps for key layers
• Customizable channels, colormap, and more

License

MIT