Implemented UNet and PSPNet architectures using Tensorflow on idd20k_lite dataset. The idd20k_lite dataset has 7 classes that include Drivable, Non-Drivable, Living things, Vehicles, Road-side objects, Far-objects, and Sky. The segmentation challenge was the pixel-level prediction of all the 7 classes at level 1 of the label hierarchy.
Implemented UNet and PSPNet architectures using Tensorflow on idd20k_lite dataset. The idd20k_lite dataset has 7 classes that include Drivable, Non-Drivable, Living things, Vehicles, Road-side objects, Far-objects, and Sky. The segmentation challenge was the pixel-level prediction of all the 7 classes at level 1 of the label hierarchy.
Implemented UNet and PSPNet architectures using Tensorflow on idd20k_lite dataset. The idd20k_lite dataset has 7 classes that include Drivable, Non-Drivable, Living things, Vehicles, Road-side objects, Far-objects, and Sky. The segmentation challenge was the pixel-level prediction of all the 7 classes at level 1 of the label hierarchy.