Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Deep learning applied to georeferenced datasets

End-to-end image segmentation kit based on PaddlePaddle.

Deep Learning library using GPU(CUDA/cuBLAS)

Weighted MinHash implementation on CUDA (multi-gpu).

Minimal Deep Learning library is written in Python/Cython/C++ and Numpy/CUDA/cuDNN.

A community run, 5-day PyTorch Deep Learning Bootcamp

Numeric Erlang - vector and matrix operations with CUDA. Heavily inspired by Pteracuda - https://github.com/kevsmith/pteracuda

📚 A collection of papers about Referring Image Segmentation.

A fast and highly scalable GPU dynamic memory allocator

Weighted Softmax Loss Layer for Caffe

ThunderSVM: A Fast SVM Library on GPUs and CPUs

MatConvNet: CNNs for MATLAB

ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation

Ubuntu 18.04 How to install Nvidia driver + CUDA + CUDNN + build tensorflow for gpu step by step command line

DoubleU-Net for Semantic Image Segmentation in TensorFlow Keras

WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].

Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation

This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.