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.
Training
Please training using the gluon image_classification interface.
Accuracy in ImageNet
In the first epoch, we've got 14.314% validation accuracy in ImageNet 2012 dataset. We will release a pretrained model when we get the accuracy of the paper.