Real-world segmentation datasets
When searching for image segmentation datasets, Pluto found about 500 useable real-world segmentation datasets. The topics range from self-driving automobiles and medicine to micro-fossils. Pluto picked two segmentation datasets from popular market segments.
The other consideration is that the image type must be easy to work with in the Albumentations library. Pluto uses the PIL and NumPy libraries to read and convert the photos into a three-dimensional array. The original image’s shape is (width, height, and depth), where depth is usually equal to three. The mask image’s shape is (width, height), where the value is 0, 1, 2, and so on up to the number of labels.
The PIL library can read image formats such as
.png, and about 50...