95.47% on CIFAR10 with PyTorch

PyTorch implementation of Mixer-nano (#parameters is 0.67M, originally Mixer-S/16 has 18M) with 90.83 % acc. on CIFAR-10. Training from scratch.

Implementation and tutorials of normalizing flows with the novel distributions module

Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019.

Demo entry "Cornell vox by Varko" for Graffathon 2016

GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

The repository holds several custom network layers. Some of which were used in my recent optical flow project: Learning Energy Based Inpainting for Optical Flow.

Minimal API for receptive field calculation in PyTorch

a generative algorithm

painting by functions

A resource repository for 3D machine learning

Examples of different quil sketches.

Darwin: A Framework for Machine Learning Research and Development

CPM-Flow, CVPR 2016

Stereo Semi Global Matching by cuda

Semiglobal Matching (SGM) implementation using CUDA

A MATLAB toolbox for exporting publication quality figures

Pytorch implementation of FlowNet by Dosovitskiy et al.

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

Segmentation-Aware Convolutional Networks Using Local Attention Masks

p5.js is a client-side JS platform that empowers artists, designers, students, and anyone to learn to code and express themselves creatively on the web. It is based on the core principles of Proces…

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Mutli-label text classification using ConvNet and graph embedding (Tensorflow implementation)

an imagenet example in torch.

Torch-7 FFI bindings for NVIDIA CuDNN

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

A tool for easy extraction of motion vectors stored in video files

Torch interface to HDF5 library