Comgra: A Tool for Analyzing and Debugging Neural Networks
- URL: http://arxiv.org/abs/2407.21656v1
- Date: Wed, 31 Jul 2024 14:57:23 GMT
- Title: Comgra: A Tool for Analyzing and Debugging Neural Networks
- Authors: Florian Dietz, Sophie Fellenz, Dietrich Klakow, Marius Kloft,
- Abstract summary: We introduce comgra, an open source python library for use with PyTorch.
Comgra extracts data about the internal activations of a model and organizes it in a GUI.
It can show both summary statistics and individual data points, compare early and late stages of training, focus on individual samples of interest, and visualize the flow of the gradient through the network.
- Score: 35.89730807984949
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Neural Networks are notoriously difficult to inspect. We introduce comgra, an open source python library for use with PyTorch. Comgra extracts data about the internal activations of a model and organizes it in a GUI (graphical user interface). It can show both summary statistics and individual data points, compare early and late stages of training, focus on individual samples of interest, and visualize the flow of the gradient through the network. This makes it possible to inspect the model's behavior from many different angles and save time by rapidly testing different hypotheses without having to rerun it. Comgra has applications for debugging, neural architecture design, and mechanistic interpretability. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at https://github.com/FlorianDietz/comgra.
Related papers
- pyvene: A Library for Understanding and Improving PyTorch Models via
Interventions [79.72930339711478]
$textbfpyvene$ is an open-source library that supports customizable interventions on a range of different PyTorch modules.
We show how $textbfpyvene$ provides a unified framework for performing interventions on neural models and sharing the intervened upon models with others.
arXiv Detail & Related papers (2024-03-12T16:46:54Z) - Interpreting Deep Neural Networks with the Package innsight [0.951828574518325]
innsight is generally the first R package implementing feature attribution methods for neural networks.
It operates independently of the deep learning library allowing the interpretation of models from any R package.
Innsight benefits internally from the torch package's fast and efficient array calculations.
arXiv Detail & Related papers (2023-06-19T10:12:32Z) - PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time
Series [0.0]
PyPOTS is an open-source Python library dedicated to data mining and analysis on partially-observed time series.
It provides easy access to diverse algorithms categorized into four tasks: imputation, classification, clustering, and forecasting.
arXiv Detail & Related papers (2023-05-30T07:57:05Z) - torchgfn: A PyTorch GFlowNet library [56.071033896777784]
torchgfn is a PyTorch library that aims to address this need.
It provides users with a simple API for environments and useful abstractions for samplers and losses.
arXiv Detail & Related papers (2023-05-24T00:20:59Z) - PyTorch Geometric Signed Directed: A Software Package on Graph Neural
Networks for Signed and Directed Graphs [20.832917829426098]
PyTorch Geometric Signed Directed (PyGSD) is a software package for signed and directed networks.
PyGSD consists of easy-to-use GNN models, synthetic and real-world data, as well as task-specific evaluation metrics and loss functions.
As an extension library for PyG, our proposed software is maintained with open-source releases, detailed documentation, continuous integration, unit tests and code coverage checks.
arXiv Detail & Related papers (2022-02-22T10:25:59Z) - Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data
via Differentiable Cross-Approximation [53.95297550117153]
We propose an end-to-end trainable framework that processes large-scale visual data tensors by looking emphat a fraction of their entries only.
The proposed approach is particularly useful for large-scale multidimensional grid data, and for tasks that require context over a large receptive field.
arXiv Detail & Related papers (2021-05-29T08:39:57Z) - Efficient Graph Deep Learning in TensorFlow with tf_geometric [53.237754811019464]
We introduce tf_geometric, an efficient and friendly library for graph deep learning.
tf_geometric provides kernel libraries for building Graph Neural Networks (GNNs) as well as implementations of popular GNNs.
The kernel libraries consist of infrastructures for building efficient GNNs, including graph data structures, graph map-reduce framework, graph mini-batch strategy, etc.
arXiv Detail & Related papers (2021-01-27T17:16:36Z) - TensorX: Extensible API for Neural Network Model Design and Deployment [0.0]
TensorFlowX is a Python library for prototyping, design, and deployment of complex neural network models in computation.
A special emphasis is put on ease of use, performance, and API consistency.
arXiv Detail & Related papers (2020-12-29T00:15:38Z) - Little Ball of Fur: A Python Library for Graph Sampling [8.089234432461804]
Little Ball of Fur is a Python library that includes more than twenty graph sampling algorithms.
We show the practical usability of the library by estimating various global statistics of social networks and web graphs.
arXiv Detail & Related papers (2020-06-08T01:35:24Z) - MOGPTK: The Multi-Output Gaussian Process Toolkit [71.08576457371433]
We present MOGPTK, a Python package for multi-channel data modelling using Gaussian processes (GP)
The aim of this toolkit is to make multi-output GP (MOGP) models accessible to researchers, data scientists, and practitioners alike.
arXiv Detail & Related papers (2020-02-09T23:34:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.