OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Pytorch Summary

Pytorch Summary is a Python library for printing a Keras-style summary of a PyTorch neural network, adding layer output shapes and parameter counts to the model representation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pytorch Summary — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you have a PyTorch model and its input dimensions and want a layer-by-layer report beyond the standard printed model representation.

Who it is for

PyTorch developers inspecting model structure during development or debugging.

Documented uses

  • Review layer output shapes and parameter counts in a compact report.
  • Add model-structure information to a debugging workflow.
Before you choose

Requirements & limits

The repository is public and identifies the project as open source under the MIT license. The README documents installation with pip or use by cloning the repository.

  • The summary call requires the model's input dimensions and performs a forward pass.
  • The README recommends considering the newer, updated torchinfo project.

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

Generate a summary for a PyTorch model

Print a Keras-style structure report for a model using its input dimensions.

Before you start

  • A PyTorch model object.
  • The model's input dimensions.
  • Install the package with pip install torchsummary or clone the project repository.

Steps

  1. Install torchsummary or clone the repository.

  2. Import summary with from torchsummary import summary.

  3. Call summary(your_model, input_size=(channels, H, W)) with the model and its input dimensions.

Expected outcome

A printed model summary with layer output shapes and parameter counts; the examples also report estimated memory sizes.

Guide limitations

  • An input size is required because the utility makes a forward pass through the network.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
sksq96/pytorch-summary · Official homepage title · retained in its source language
How we review sourcesSuggest a correction