xxxyyyzzzz

Instead of generating LMDB for whole training set, I've set the number of samples to 10k. I got LMDB og size 11.2 GB. But when I run training with that...

@dragonfly90 can u please tell how did u arrive at result.json file from the caffemodel that is obtained after training?

@louielu1027 I couldn't locate examples/tests/pose_accuracy_coco_test.sh file which generates json file. Also will caffemodel be the input for that shell script?