Exploration of deconvolutions, transposed convolutions, and fractionally strided convolutions.
-
Updated
Jul 15, 2022 - Jupyter Notebook
Exploration of deconvolutions, transposed convolutions, and fractionally strided convolutions.
Trained a generative Adverserial Network (GAN) which when given the satellite image of a place as input, outputs the Map image of that same location. It was trained using standard adverserial training.
The fast transformation algorithm for transposed convolutional layers
Convolutional autoencoder reducing traffic sign images to 1/6 of their original size.
Application of U-Net to semantic image segmentation of road images by pixel-wise classification
Add a description, image, and links to the transposed-convolution topic page so that developers can more easily learn about it.
To associate your repository with the transposed-convolution topic, visit your repo's landing page and select "manage topics."