Skip to main content
Torqueo logo

Torqueo is a simple and hackable library for experimentation with image warping in PyTorch. It is designed to facilitate easy manipulation and transformation of images using various warping techniques.

🚀 Getting Started with Torqueo

Torqueo requires Python 3.7 or newer and several dependencies, including Numpy. Installation is straightforward with Pypi:

pip install torqueo

With Torqueo installed, you can dive into image warping. The API is designed to be intuitive, requiring only a few hyperparameters to get started.

Example usage:

import torch
import timm
from torqueo import Fisheye

transformed_images = Fisheye()(images)

Starter Notebook: Open in Google Colab

Documentation

Torqueo documentation can be found here: Documentation

Examples of transformations

Below are some examples of image transformations using Torqueo.

Original Image
Original Image
Barrel
Barrel
Fisheye
Fisheye
Perspective
Perspective
Pinch
Pinch
Spherize
Spherize
Stretch
Stretch
Swirl
Swirl
Twirl
Twirl
Wave
Wave

Authors of the code

Metadata

Release files for Torqueo 0.0.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for Torqueo 0.0.3
File Size Uploaded
torqueo-0.0.3.tar.gz 11.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for Torqueo 0.0.3
File Interpreter ABI Platform
Torqueo-0.0.3-py3-none-any.whl Python 3 none any Details

Total release size: 30.4 kB

Release files / torqueo-0.0.3.tar.gz

Download URL torqueo-0.0.3.tar.gz
Size 11.6 kB
Tags Source
SHA-256 checksum
How to use checksums
2a4c9c0490ad9d472b27a7b5d2a0156d535659f760d6649c122ddb07844714ca
BLAKE2b-256 checksum
How to use checksums
167990623aca2a0075cd1cf2471d095bd92bbf847b2868d91f5cef892790d0a7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.0 CPython/3.12.3

Release files / Torqueo-0.0.3-py3-none-any.whl

Download URL Torqueo-0.0.3-py3-none-any.whl
Size 18.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
63bb5d5c9b5eaba863a756d148a72db41f289bfb5a478a75674be44c880a60b2
BLAKE2b-256 checksum
How to use checksums
b87719d57b101edf0346187e57f7b621a212e2f7605c92380be809b1755d7cdf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.0 CPython/3.12.3

Release history Release notifications | RSS feed

This release

0.0.3 This release

2 release files

0.0.2

2 release files

0.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page