Skip to content


Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

Latest commit

- add to the supported models in `share/example/`:
  - `resnet18`
  - `vgg11`
  - `vgg11_bn`

Git stats


Failed to load latest commit information.



Documentation Status tests PyPI Version License

Zennit (Zennit explains neural networks in torch) is a high-level framework in Python using Pytorch for explaining/exploring neural networks. Its design philosophy is intended to provide high customizability and integration as a standardized solution for applying rule-based attribution methods in research, with a strong focus on Layerwise Relevance Propagation (LRP). Zennit strictly requires models to use Pytorch's torch.nn.Module structure (including activation functions).

Zennit is currently under active development, but should be mostly stable.

If you find Zennit useful for your research, please consider citing our related paper:

      author  = {Anders, Christopher J. and
                 Neumann, David and
                 Samek, Wojciech and
                 Müller, Klaus-Robert and
                 Lapuschkin, Sebastian},
      title   = {Software for Dataset-wide XAI: From Local Explanations to Global Insights with {Zennit}, {CoRelAy}, and {ViRelAy}},
      journal = {CoRR},
      volume  = {abs/2106.13200},
      year    = {2021},


The latest documentation is hosted at


To install directly from PyPI using pip, use:

$ pip install zennit

Alternatively, install from a manually cloned repository to try out the examples:

$ git clone
$ pip install ./zennit


At its heart, Zennit registers hooks at Pytorch's Module level, to modify the backward pass to produce rule-based attributions like LRP (instead of the usual gradient). All rules are implemented as hooks (zennit/ and most use the LRP basis BasicHook (zennit/

Composites (zennit/ are a way of choosing the right hook for the right layer. In addition to the abstract NameMapComposite, which assigns hooks to layers by name, and LayerMapComposite, which assigns hooks to layers based on their Type, there exist explicit Composites, some of which are EpsilonGammaBox (ZBox in input, Epsilon in dense, Gamma in convolutions) or EpsilonPlus (Epsilon in dense, ZPlus in convolutions). All composites may be used by directly importing from zennit.composites, or by using their snake-case name as key for zennit.composites.COMPOSITES.

Canonizers (zennit/ temporarily transform models into a canonical form, if required, like SequentialMergeBatchNorm, which automatically detects and merges BatchNorm layers followed by linear layers in sequential networks, or AttributeCanonizer, which temporarily overwrites attributes of applicable modules, e.g. to handle the residual connection in ResNet-Bottleneck modules.

Attributors (zennit/ directly execute the necessary steps to apply certain attribution methods, like the simple Gradient, SmoothGrad or Occlusion. An optional Composite may be passed, which will be applied during the Attributor's execution to compute the modified gradient, or hybrid methods.

Using all of these components, an LRP-type attribution for VGG16 with batch-norm layers with respect to label 0 may be computed using:

import torch
from torchvision.models import vgg16_bn

from zennit.composites import EpsilonGammaBox
from zennit.canonizers import SequentialMergeBatchNorm
from zennit.attribution import Gradient

data = torch.randn(1, 3, 224, 224)
model = vgg16_bn()

canonizers = [SequentialMergeBatchNorm()]
composite = EpsilonGammaBox(low=-3., high=3., canonizers=canonizers)

with Gradient(model=model, composite=composite) as attributor:
    out, relevance = attributor(data, torch.eye(1000)[[0]])

A similar setup using the example script produces the following attribution heatmaps: beacon heatmaps

For more details and examples, have a look at our documentation.

More Example Heatmaps

More heatmaps of various attribution methods for VGG16 and ResNet50, all generated using share/example/, can be found below.

Heatmaps for VGG16

vgg16 heatmaps

Heatmaps for ResNet50

resnet50 heatmaps


See for detailed instructions on how to contribute.


Zennit is licensed under the GNU LESSER GENERAL PUBLIC LICENSE VERSION 3 OR LATER -- see the LICENSE, COPYING and COPYING.LESSER files for details.