开源软件名称（OpenSource Name）：

开源软件地址(OpenSource Url)：

开源编程语言(OpenSource Language)：

开源软件介绍(OpenSource Introduction)：

A MXNet/Gluon implementation of MobileNetV2

This is a Gluon implementation of MobileNetV2 architecture as described in the paper Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation.

Pretrained Models on ImageNet

We provide pretrained MobileNetV2(width_mult: 1.0, crop_size: 224) models on ImageNet, which achieve slightly better accuracy rates than the original ones reported in the paper.

The top-1/5 accuracy rates by using single center crop (crop size: 224x224, image size: 256xN):

Training Script

For training, please refer to liangfu/mxnet-mobilenet-v2. Our pretrained model is converted from that. The MXNet officially offer a pretrained model (and training script) here too.

Normalization

The input images are substrated by mean RGB = [ 123.68, 116.78, 103.94 ].