running single shot multibox detector

Question

I run tensorflow/ssd_vehicle_detection from here(https://github.com/balancap/SDC-Vehicle-Detection) with widerface dataset for face detection. after creating tfrecords and write train command i got this :

INFO: tensorflow: starting Sessions

INFO: tensorflow: starting Queues

INFO: tensorflow: global_step/sec : 0

INFO: tensorflow: global_step/sec : 0

INFO: tensorflow: global_step/sec : 0.0172539

INFO: tensorflow: global_step/sec : 0

INFO: tensorflow: global_step/sec : 0

INFO: tensorflow: global_step/sec : 0.0167292

...

Is there any problem? where is loss? Is the network training wrong?

Answer 1

I found it . you just need to wait till training starts:

INFO: tensorflow: global step 10: loss- 0.6134 (90.89 sec/step)