Dmitry Ulyanov

deep-image-prior. Image restoration with neural networks but without learning.

Multicore-TSNE. Parallel t-SNE implementation with Python and Torch wrappers.

texture_nets. Code for "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images" paper.

neural-style-audio-tf. TensorFlow implementation for audio neural style.

fast-neural-doodle. Faster neural doodle

AGE. Code for the paper "Adversarial Generator-Encoder Networks"

online-neural-doodle. Feedforward neural doodle

neural-style-audio-torch. Torch implementation for audio neural style.

typed_print. Easily beautify your logs with a drop-in replacement for the print function.

large-image-viewer. Browser-based image viewer with a support of arbitrary large images

tex-publishing-util. Easy cleaning of your TeX project for conference or arxiv submission

IDAO. Files for IDAO competitors

pytorch-in-theano. Run Pytorch graphs inside Theano graph (and pytorch wrapper for AIS for generative models).

dmitryulyanov.github.io. HTML

Pairwise-Ranking-Aggregation. Pairwise Ranking Aggregation in a Crowdsourced Setting

Practical_DL. DL course taught by Victor Lempitsky

recognition. Jupyter Notebook

fast-neural-style. Feedforward style transfer

mlq. Asynchronous queue for machine learning jobs

parfor. Python

optimize-net. OptNet - Reducing memory usage in torch neural nets

cv-papers-with-code. Computer Vision Papers with Code in GitHub

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

cnn-benchmarks. Benchmarks for popular CNN models

glumpy. Python+Numpy+OpenGL: fast, scalable and beautiful scientific visualization

three.js. JavaScript 3D Library.

vision. Datasets, Transforms and Models specific to Computer Vision

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

readme2tex. Renders TeXy Math for Github Readmes

nn. Lua

ALI. Adversarially Learned Inference

meshlab. The open source mesh processing system

python-fire. Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

eval_gen. Evaluation code with models for the paper "On the Quantitative Analysis of Decoder-Based Generative Models"