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 >0in a pytorchDataLoader. 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.
The changes start to add up when you compose multiple transformations together.
TODO
- Initial commit with all currently implemented torchvision transforms
- Cityscapes benchmarks
- Make the
resampleflag onRandomRotation,RandomAffineactually 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
Metadata
Release files for opencv-transforms 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| opencv_transforms-0.0.1.tar.gz | 917.0 kB | Without provenance | Details for opencv_transforms-0.0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| opencv_transforms-0.0.1-py3-none-any.whl | Python 3 | none | any | Details for opencv_transforms-0.0.1-py3-none-any.whl |
Total release size: 935.3 kB
Release files / opencv_transforms-0.0.1.tar.gz
| Download URL | opencv_transforms-0.0.1.tar.gz |
|---|---|
| Size | 917.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f1e3391e6d17b90edc300985601a367a47ca2215074fbe17b98b08a09d372367
|
|
BLAKE2b-256 checksum How to use checksums |
08627bfc342298d086433526238ed71a39d9cafc36574b4673a9032992460d33
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is 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
|
Release files / opencv_transforms-0.0.1-py3-none-any.whl
| Download URL | opencv_transforms-0.0.1-py3-none-any.whl |
|---|---|
| Size | 18.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f639aca4e6107f06269ac89f48ef07aa9a5fe38084080a37bfeb81703d0abcf2
|
|
BLAKE2b-256 checksum How to use checksums |
120444a8df65691e12e2e7747eaaa658df9e9eca1190ffb7ea47b6c94d7dcba7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is 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
|
Security for opencv-transforms 0.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.