Skip to main content

A drop-in replacement for Torchvision Transforms using OpenCV

Project description

opencv_transforms

This repository is intended as a faster drop-in replacement for Pytorch's Torchvision augmentations. This repo uses OpenCV for fast image augmentation for PyTorch computer vision pipelines. I wrote this code because the Pillow-based Torchvision transforms was starving my GPU due to slow image augmentation.

Requirements

  • A working installation of OpenCV. Tested with OpenCV version 3.4.1
  • Tested on Windows 10. There is evidence that OpenCV doesn't work well with multithreading on Linux / MacOS, for example num_workers >0 in a pytorch DataLoader. I haven't tried this on those systems.

Installation

  • git clone https://github.com/jbohnslav/opencv_transforms.git
  • Add to your python path

Usage

  • from opencv_transforms import opencv_transforms as transforms
  • From here, almost everything should work exactly as the original transforms.

Example: Image resizing

import numpy as np
image = np.random.randint(low=0, high=255, size=(1024, 2048, 3))
resize = transforms.Resize(size=(256,256))
image = resize(image)

Should be 1.5 to 10 times faster than PIL. See benchmarks

Performance

  • Most transformations are between 1.5X and ~4X faster in OpenCV. Large image resizes are up to 10 times faster in OpenCV.
  • To reproduce the following benchmarks, download the Cityscapes dataset.
  • An example benchmarking file can be found in the notebook bencharming_v2.ipynb I wrapped the Cityscapes default directories with a HDF5 file for even faster reading.

resize random crop change brightness change brightness and contrast change contrast only random horizontal flips

The changes start to add up when you compose multiple transformations together. composed transformations

TODO

  • Initial commit with all currently implemented torchvision transforms
  • Cityscapes benchmarks
  • Make the resample flag on RandomRotation, RandomAffine actually do something
  • Speed up augmentation in saturation and hue. Currently, fastest way is to convert to a PIL image, perform same augmentation as Torchvision, then convert back to np.ndarray

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

opencv_transforms-0.0.1.tar.gz (917.0 kB view details)

Uploaded Source

Built Distribution

opencv_transforms-0.0.1-py3-none-any.whl (18.4 kB view details)

Uploaded Python 3

File details

Details for the file opencv_transforms-0.0.1.tar.gz.

File metadata

  • Download URL: opencv_transforms-0.0.1.tar.gz
  • Upload date:
  • Size: 917.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.6.0.post20191030 requests-toolbelt/0.9.1 tqdm/4.38.0 CPython/3.7.5

File hashes

Hashes for opencv_transforms-0.0.1.tar.gz
Algorithm Hash digest
SHA256 f1e3391e6d17b90edc300985601a367a47ca2215074fbe17b98b08a09d372367
MD5 74a80614851f67127c00971a8e8e9555
BLAKE2b-256 08627bfc342298d086433526238ed71a39d9cafc36574b4673a9032992460d33

See more details on using hashes here.

File details

Details for the file opencv_transforms-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: opencv_transforms-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 18.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.6.0.post20191030 requests-toolbelt/0.9.1 tqdm/4.38.0 CPython/3.7.5

File hashes

Hashes for opencv_transforms-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 f639aca4e6107f06269ac89f48ef07aa9a5fe38084080a37bfeb81703d0abcf2
MD5 d006c18eb13abe8908a6f054805ef416
BLAKE2b-256 120444a8df65691e12e2e7747eaaa658df9e9eca1190ffb7ea47b6c94d7dcba7

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page