pytorch-mobilenet-v2

A PyTorch implementation of MobileNetV2

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

[NEW] Add the code to automatically download the pre-trained weights.

Training Recipe

Recently I have figured out a good training setting:

1. number of epochs: 150
2. learning rate schedule: cosine learning rate, initial lr=0.05
3. weight decay: 4e-5
4. remove dropout

You should get >72% top-1 accuracy with this training recipe!

Accuracy & Statistics

Here is a comparison of statistics against the official TensorFlow implementation.

Usage

To use the pretrained model, run

from MobileNetV2 import mobilenet_v2

net = mobilenet_v2(pretrained=True)

Data Pre-processing

I used the following code for data pre-processing on ImageNet:

…