This code is taking more time to train than the tf-faster-rcnn. When I am running at 1800 scale this code is taking 2.9 sec /iter as compared to 1.7sec/iter in tf-faster-rcnn.
Also going out of memory at 1800 input scale ( my gpu had 16gb of gpu memory) with this code, whereas tf-faster-rcnn isn't.
This code is taking more time to train than the tf-faster-rcnn. When I am running at 1800 scale this code is taking 2.9 sec /iter as compared to 1.7sec/iter in tf-faster-rcnn. Also going out of memory at 1800 input scale ( my gpu had 16gb of gpu memory) with this code, whereas tf-faster-rcnn isn't.