sunshiding Goto Github PK

deep_cca

A Deep CCA program written by a plain numpy and scipy library

deepgcca-pytorch

An implementation of Deep Generalized Canonical Correlation Analysis (DGCCA or Deep GCCA) with pytorch.

deepinterestnetwork

deeplab-pytorch

PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC

deeplda

An implementation of Deep Linear Discriminant Analysis (DeepLDA) in Keras

deeplda-1

End-to-end Deep Linear Discriminant Analysis in Pytorch.

deeplearning

dengyang17.github.io

dlupi-heteroscedastic-dropout

Deep Learning under Privileged Information Using Heteroscedastic Dropout (CVPR 2018, Official Repo)

dmc

Code for Deep Multimodal Clustering (CVPR2019)

dmvl

This is the code of the paper "Decoupled Representation for Multi-View Learning". The code will be sorted out later.

dscnn

dual-teacher

Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-Efficient Cardiac Segmentation

edex-ui

A cross-platform, customizable science fiction terminal emulator with advanced monitoring & touchscreen support.

eml

Knowledge distillation (KD) is an effective method for acquiring smaller networks exhibiting excellent performance in running on most common devices. Previous methods mainly use logits to realize KD; however, the rich knowledge contained in feature maps has not yet been fully utilized. To address this problem, we propose a novel online KD method—embedded mutual learning (EML). By embedding an adaptive fusion branch and ensemble classifier between two parallel sub-networks, EML uses logits as well as overall feature map distribution of the co-trained sub-networks to fully mine and utilize the implicit knowledge between networks. Specifically, EML is widely applicable to various sub-network combinations, comprising heterogeneous or homogeneous networks. We conduct experiments on three public datasets: CIFAR-10, CIFAR-100, and ImageNet, which prove that our method outperforms state-of-the-art KD methods.

et-bert

The repository of ET-BERT, a network traffic classification model on encrypted traffic. The work has been accepted as The Web Conference (WWW) 2022 accepted paper.

face_recognize

ArcFace pytorch

facenet

FaceNet for face recognition using pytorch

facenet-pytorch-vggface2

A PyTorch implementation of Google's FaceNet [1] paper for training a facial recognition model with Triplet Loss and an implementation of the Shenzhen Institutes of Advanced Technology's 'Center Loss' [2] combined with Cross Entropy Loss using the VGGFace2 dataset. A pre-trained model using Triplet Loss is available for download.

fair-sslime

FAIR Self-Supervised Learning Integrated Multi-modal Environment (SSLIME)

fast-transformers

Pytorch library for fast transformer implementations

faster-rcnn.pytorch

A faster pytorch implementation of faster r-cnn

faster_rcnn_pytorch

Faster RCNN with PyTorch

fcn_pytorch

FCN pytorch

food-recipe-cnn

food image to recipe with deep convolutional neural networks.

gcnet-pytorch

This is a pytorch type of block，including Non-local block，Simple Non-local block，GC block and all GC block; refer to paper《GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond》

geometry_processing

3D object recognition using multiview CNNs

giung2

googlenet-bn

GoogleNet-BN,namely InceptionNetV2 based on pytorch.

grad-cam.pytorch

pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络;欢迎试用、关注并反馈问题...