Deep learning-based segmentation with U-Net architecture on Oxford-IIIT Pet dataset, leveraging VGG16 model.
computer-vision
deep-learning
cnn
neural-networks
segmentation
image-analysis
vgg16
semantic-segmentation
u-net
oxford-iiit-pets-dataset
pixel-level-annotations
semantic-labels
label-each-pixel
-
Updated
May 20, 2023 - Jupyter Notebook