Stars
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
Classic papers and resources on recommendation
Best Practices on Recommendation Systems
CTR prediction model based on spark(LR, GBDT, DNN)
[AAAI-2020] Official implementation for "Online Knowledge Distillation with Diverse Peers".
Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。
A PyTorch implementation of Ranking Distillation
CTR prediction using FM FFM and DeepFM
A PyTorch implementation for PyramidNets (Deep Pyramidal Residual Networks, https://arxiv.org/abs/1610.02915)
A pytorch implementation of paper 'Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation', https://arxiv.org/abs/1905.08094
Representation learning on large graphs using stochastic graph convolutions.
Google Research
Pytorch Implementation of Graph Convolutional Neural Networks
A PyTorch implementation of "Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks" (KDD 2019).
OpenMMLab Detection Toolbox and Benchmark
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
pytorch1.0 updated. Support cpu test and demo. (Use detectron2, it's a masterpiece)
Knowledge Distillation: CVPR2020 Oral, Revisiting Knowledge Distillation via Label Smoothing Regularization
A framework for data augmentation for 2D and 3D image classification and segmentation
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet…
Awesome Knowledge Distillation
A simplified implemention of Faster R-CNN that replicate performance from origin paper
A faster pytorch implementation of faster r-cnn