search

zlingkang / mobilenet_ssd_pedestrian_detection

Mobilenet SSD based pedestrian detection
49 stars 20 forks source link

I can't train caltech pedestrian dataset correcly #2

Open DanielXu123 opened 6 years ago

DanielXu123 commented 6 years ago

Hi, zlingkang.

I have a strange problem when dealing with the Caltech dataset. Bascially, I think we are using the same dataset. I also collect all the pedestrian data from the originall Caltech dataset, and I also changed the name from pedestrian to person.

But, when I start to train the dataset, I get the loss keeps being 0.

Like this issue I create before. https://github.com/chuanqi305/MobileNet-SSD/issues/116

Have you met that kind of situation? And Could you share your solver_train.prototxt, I think maybe I got some wrong Hyper parameters setting in this file.

Many Thanks , Looking forward for your reply.

DanielXu123 commented 6 years ago

And, where should I place these files? Especially for the python script. I modified the caffe_root direction, but can't run correctly.