This is a Caffe implementation of Google's MobileNets. For details, please read the original paper:

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

We provide a pretrained MobileNet model on ImageNet, which achieves slightly better accuracy rates than the original one reported in the paper.

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

• BGR mean values [103.94,116.78,123.68] are subtracted
• scale: 0.017 is used as std values for image preprocessing
• please uncomment engine: CAFFE used in the conv layers with group, if you encounter memory problems.