w2020

mindspore

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.

ssdlite-pytorch-mobilenext

A PyTorch implementation of SSDLite on COCO

models

Models and examples built with TensorFlow

deep-learning-for-image-processing

deep learning for image processing including classification and object-detection etc.

vision

Datasets, Transforms and Models specific to Computer Vision

MobileNet-Yolo

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:

tpu

Reference models and tools for Cloud TPUs.

ShuffleNet-Series

DCANet

Deep Connected Attention Networks

pytorch-cifar100

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet)

PyTorch-Networks

Pytorch implementation of cnn network

mobilenetv2.pytorch

72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

mobilenetv3

mobilenetv3 with pytorch，provide pre-train model

pytorch-mobilenet-v3

MobileNetV3 in pytorch and ImageNet pretrained models

MobileNetv2-SSDLite

Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

ShuffleNet

ShuffleNet in PyTorch. Based on https://arxiv.org/abs/1707.01083