The UNet architecture used here is borrowed from https://github.com/jvanvugt/pytorch-unet. The only modification made in the UNet architecture mentioned in the above ...

This is a pytorch implementation of the Muti-task Learning using CNN + AutoEncoder. Cifar10 is available for the datas et by default. You can also use your own dataset. epoch,train loss,train accuracy ...

Abstract: Multiresolution deep learning approaches, such as the UNet architecture, have achieved high performance in classifying and segmenting images. Most traditional convolutional neural network ...