ternaus released this
Oct 14, 2019
2e25667 Target: image
This transform mimics the noise that images will have if the ISO parameter of the camera is high. Wiki
e365b52 Targets: image
Solarize inverts all pixels above some threshold. It is an essential part of the work AutoAugment: Learning Augmentation Policies from Data.
9f71038 Target: image
Equalizes image histogram. It is an essential part of the work AutoAugment: Learning Augmentation Policies from Data.
ad95fa0 Target: image
Reduce the number of bits for each pixel. It is an essential part of the work AutoAugment: Learning Augmentation Policies from Data.
Target: image b612786 Decrease Jpeg or WebP compression to the image.
df831d6 Target: image
Decreases image quality by downscaling and upscaling back.
4dbe41e Targets: image, mask, bboxes, keypoints
Crop the given Image to the random size and aspect ratio. This transform is an essential part of many image classification pipelines. Very popular for ImageNet classification.
It has the same API as RandomResizedCrop in torchvision.
4cf6c36 Targets: image, mask
Partition an image into tiles. Shuffle them and merge back.
Targets: image, mask, bboxes, keypoints
Crop area with a mask if the mask is non-empty, else make a random crop.
a502680 Targets: image, mask
Convert image and mask to torch.Tensor
The Yolo format of a bounding box has a format [x, y, width, height], where values normalized to the size of the image. Ex: [0.3, 0.1, 0.05, 0.07]
[x, y, width, height],
[0.3, 0.1, 0.05, 0.07]
Augmentations pipeline has a lot of randomnesses, which is hard to debug. We added Determentsic / Replay mode in which you can track what parameters were applied to the input and use precisely the same transform to another input if necessary.
Jupyter notebook with an example.
One of the use cases is it to use mask_value, which is equal to the ignore_index of your loss. This will decrease the level of noise and may improve convergence.
3.2 times faster for uint8 images.
2 times faster for uint8 images.
2.7 times faster for uint8 images.
4 times faster for uint8 images.
30a3f30 Not all spatial tranforms jave keypoints support yet. In this release we added Crop, CropNonEmptyMaskIfExists, LongestMaxSize, RandomCropNearBBox, Resize, SmallestMaxSize, and Transpose.
We are delighted that albumentations are helpful to the academic community. We extended documentation with a page that lists all papers and preprints that cite albumentations in their work. This page is automatically generated by parsing Google Scholar. At this moment, this number is 24.
We are delighted that albumentations help people to get top results in machine learning competitions at Kaggle and other platforms. We added a "Hall of Fame" where people can share their achievements. This page is manually created. We encourage people to add more information about their results with pull requests, following the contributing guide.
@albu @Dipet @creafz @BloodAxe @ternaus @vfdev-5 @arsenyinfo @qubvel @toshiks @Jae-Hyuck @BelBES @alekseynp @timeous @jveitchmichaelis @bfialkoff
ternaus released this
Jun 26, 2019
Jupyter notebook with an example
Special thanks to @creafz
Special thanks to @vfdev-5 @ternaus @BloodAxe @kirillbobyrev
Special thanks to @qubvel @ternaus @albu @BloodAxe
BloodAxe released this
Mar 4, 2019
Notebook with an example
Special thanks to the Evegene Khvedchenya (@BloodAxe) for the work.
The possible use case are image2image or stereo-image pipelines.
Special thanks to Alexander Buslaev (@albu) for the work.
And many others.
@BloodAxe @albu @creafz @ternaus @erikgaas @marcocaccin @libfun @DBusAI @alexobednikov @StrikerRUS @IlyaOvodov @ZFTurbo @Vcv85 @georgymironov @LinaShiryaeva @vfdev-5 @daisukelab @cdicle