Data Augmentation using Augmentor || Simple steps to perform Data Augmentation
Data augmentation is the technique of increasing the size of data used for training a model. For reliable predictions, the deep learning models often require a lot of training data, which is not always available. Therefore, the existing data is augmented in order to make a better generalized model.
Although data augmentation can be applied in various domains, it's commonly used in computer vision. Some of the most common data augmentation techniques used for images are:
Some of the most common data augmentation techniques used for images are:
Position augmentation. Scaling. Cropping. Flipping. Padding. Rotation. Translation. Affine transformation.
Color augmentation. Brightness. Contrast. Saturation. Hue.
Augmentor is a Python package designed to aid the augmentation and artificial generation of image data for machine learning tasks. It is primarily a data augmentation tool, but will also incorporate basic image pre-processing functionality.
Step 1: Create a New Pipeline
Step 2: Add Operations to the Pipeline
Step 3: Execute and Sample From the Pipeline
import Augmentor
path_to_data = "/home/user/images/dataset1/"
Create a pipeline
p = Augmentor.Pipeline(path_to_data)
Add some operations to an existing pipeline.
First, we add a horizontal flip operation to the pipeline:
p.flip_left_right(probability=0.4)
Now we add a vertical flip operation to the pipeline:
p.flip_top_bottom(probability=0.8)
Add a rotate90 operation to the pipeline:
p.rotate90(probability=0.1)
Now we can sample from the pipeline:
p.sample(num_of_samples)
On this page of the site you can watch the video online Data Augmentation using Augmentor || Simple steps to perform Data Augmentation with a duration of hours minute second in good quality, which was uploaded by the user InvesTime 04 May 2022, share the link with friends and acquaintances, this video has already been watched 3,357 times on youtube and it was liked by 67 viewers. Enjoy your viewing!
