Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.
The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:
Caffe implementation of SSD detection on MobileNetv2, converted from tensorflow.
Tensorflow and Caffe version SSD is properly installed on your computer.
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
There are some differences between caffe and tensorflow implementation: 1. 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. 2. 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.