Morteza-Asadi-Shalmaiy/Superres-fr: Convolutional autoencoder trained from scratch on CelebA faces — 128-dim latent space, full checkpoint/resume support, built to run end-to-end in Google Colab.

Convolutional autoencoder trained from scratch on CelebA faces — 128-dim latent space, full checkpoint/resume support, built to run end-to-end in Google Colab.

Read Original

Related