MobileNetv2-SSDLite

Caffe implementation of SSD detection on MobileNetv2, converted from tensorflow.
【As of June 3, 2018】 Be careful as it will not work with Intel Movidius Neural Compute Stick (NCS) NCSDK v1.12.00.

I fixed a little clone of Chuanqi305/MobileNetv2-SSDLite.
https://github.com/chuanqi305/MobileNetv2-SSDLite.git
I have not confirmed the behavior of the generated model at all.
Pull Request is welcomed.

Environment

Ubuntu 16.04
Python 2.7.12
Python 3.5.2

Prerequisites

Tensorflow and Caffe version SSD is properly installed on your computer.
There is a ReLU6 layer implementation in chuanqi305's fork of SSD.

Procedure

Implementation of MovileNetv2-SSDLite (Pascal VOC, ReLU6 layer enabled) by Caffe

Usage

Firstly you should download the original model from tensorflow.
Use gen_model.py to generate the train.prototxt and deploy.prototxt (or use the default prototxt).

python gen_model.py -s deploy -c 91 >deploy.prototxt

Use dump_tensorflow_weights.py to dump the weights of conv layer and batchnorm layer.
Use load_caffe_weights.py to load the dumped weights to deploy.caffemodel.
Use the code in src to accelerate your training if you have a cudnn7, or add "engine: CAFFE" to your depthwise convolution layer to solve the memory issue.
The original tensorflow model is trained on MSCOCO dataset, maybe you need deploy.caffemodel for VOC dataset, use coco2voc.py to get deploy_voc.caffemodel.

Train your own dataset

Generate the trainval_lmdb and test_lmdb from your dataset.
Write a labelmap.prototxt
Use gen_model.py to generate some prototxt files, replace the "CLASS_NUM" with class number of your own dataset.

python gen_model.py -s train -c CLASS_NUM >train.prototxt
python gen_model.py -s test -c CLASS_NUM >test.prototxt
python gen_model.py -s deploy -c CLASS_NUM >deploy.prototxt

Copy coco/solver_train.prototxt and coco/train.sh to your project and start training.

Note

There are some differences between caffe and tensorflow implementation:

The padding method 'SAME' in tensorflow sometimes use the [0, 0, 1, 1] paddings, means that top=0, left=0, bottom=1, right=1 padding. In caffe, there is no parameters can be used to do that kind of padding.
MobileNet on Tensorflow use ReLU6 layer y = min(max(x, 0), 6), but caffe has no ReLU6 layer. Replace ReLU6 with ReLU cause a bit accuracy drop in ssd-mobilenetv2, but very large drop in ssdlite-mobilenetv2. There is a ReLU6 layer implementation in my fork of ssd.

pinto0309 / mobilenetv2-ssdlite Goto Github PK