Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…

MicroK8s is a small, fast, single-package Kubernetes for datacenters and the edge.

Microsoft Distributed Machine Learning Toolkit

Residual Attention Network for Image Classification

code for Holistically-Nested Edge Detection

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

Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST

Capsule Network on Fashion MNIST dataset

Wide Residual Networks (WideResNets) in PyTorch

Dual Path Networks on cifar-10 and fashion-mnist datasets

auto-tuning momentum SGD optimizer

CTR prediction using FM FFM and DeepFM

Tensorflow implementation of DeepFM for CTR prediction.

Image augmentation for machine learning experiments.

Open solution to the Data Science Bowl 2018

kaggle 2018 data science bowl competition

code for "Deeply supervised salient object detection with short connections" published in CVPR 2017

Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.

Repository for DeepLab family

starter from "How to Train a GAN?" at NIPS2016

DeMoN: Depth and Motion Network

Magenta: Music and Art Generation with Machine Intelligence

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Caffe models (including classification, detection and segmentation) and deploy files for famouse networks

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

High-Level Training, Data Augmentation, and Utilities for Pytorch

Train AI models efficiently on medical images using any framework

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).