Torch implementation of neural style algorithm

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Image-to-image translation with conditional adversarial nets

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

[ICCV 2017] Torch code for Grad-CAM

Torch on steroids

Train a deeper LSTM and normalized CNN Visual Question Answering model. This current code can get 58.16 on OpenEnded and 63.09 on Multiple-Choice on test-standard.

Graph Computation for nn

Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders

Capsule network with variations. Originally proposed by Tieleman & Hinton : http:https://www.cs.toronto.edu/~tijmen/tijmen_thesis.pdf

Variational Autoencoder trained by Feature Perceputal Loss

[CVPR 2018] Cross-View Image Synthesis using Conditional GANs, [CVIU 2019] Cross-view image synthesis using geometry-guided conditional GANs

Code to generate visual metamers via foveated feed-forward style transfer (ICLR 2019)

Train DeepSat dataset with Torch

Live Cell Histology: Extracting latent features from label-free live cell images using Adversarial Autoencoders