zhaoweicai / mscnn

Caffe implementation of our multi-scale object detection framework
404 stars 211 forks source link

Deploy file of caltech #23

Open mst9009 opened 7 years ago

mst9009 commented 7 years ago

Hi @zhaoweicai I just found the mscnn_deploy.prototxt file for caltech in example folder is different from that in pretrained model you provided,there is no roi_cl and roi_cl_relu layer in pretrained files,is it necessary to remove these layers when I traning on caltech format data?

zhaoweicai commented 7 years ago

hi @MST9009 Yes, they are different. I added that layer to make the models for caltech and KITTI consistent. In my experiments, the new model and the pretrained model don't have much difference for Caltech. You can use either of them.