albumentations VS imgaug

You can use albumentations if you are comfortable with using open source libraries https://github.com/albumentations-team/albumentations

One of the members of the core team of our open-source library https://albumentations.ai/

It was not the only reason he was hired; it was a solid addition to his already good performance at the interviews.

Or at least that is what the hiring manager later said.

I am one of the creators and maintainers of https://albumentations.ai/.

- 12800+ stars

Is something planned to support data augmentations? Something like https://albumentations.ai/

Here you go: https://albumentations.ai/

I think they should use some data augmentation techniques like I am using for Infinity AI if you wanna see more here. Note that most of these do not work for image generation.

Our second approach was a more automated one. Here the idea was to try out an image augmentation library, Albumentations, and use it for adversarial attacks. This time, instead of one-shot images, we applied the transformations at random time ranges. We chose for these transformations also to be more subtle than then one-shot images, such as vertical flips, grayscaling, downscaling, …

Check out albumentations. If your use case is segmentation, check out the offline augmentation of this project

I think this is the most popular open source project: https://github.com/albumentations-team/albumentations

You can also curate your own dataset by using open source images (https://universe.roboflow.com/search?q=faces%20images%3E1000) and open source augmentations (https://github.com/albumentations-team/albumentations). Or you can do use the augmentation UI (https://docs.roboflow.com/image-transformations/image-augmentation) to apply noise, blurring, shear, crop, etc.

There are many good options when it comes to tools and libraries for implementing data augmentation into our deep learning pipeline. You could for instance do your own augmentations using NumPy or Pillow. Some of the most popular dedicated libraries for image augmentation include Albumentations, imgaug, and Augmentor. Both TensorFlow and PyTorch even come with their own packages dedicated to image augmentation.

https://github.com/aleju/imgaug This one is way better for image.

I have to improve my dataset with more backgrounds featuring obstacles. At the moment I'm working on creating a dataset with both items and trinkets, and I'm planning on using https://github.com/aleju/imgaug which will replace most of the stuff I'm doing with PIL.

Do you acknowledge that there is ImageDataGenerator and ImgAug?

Albumentations no longer uses the imgaug library by default. All previous imgaug augmentations in the library are reimplemented in Albumentations with the same API (but you can still install Albumentations with imgaug if you need the old augmentations).

I would also recommend you to give a try to TensorFlow Object Detection Model - https://github.com/tensorflow/models/tree/master/research/object_detection with augmentation - https://github.com/aleju/imgaug pipeline. The same worked for me in a similar use case where I had to localise logo on documents.