xiaoxiongli

@argman Dear argman, i check the cfg file lib/fast_rcnn/config.py: __C.TRAIN.RPN_MIN_SIZE = 16 __C.TEST.RPN_MIN_SIZE = 16 **it seems the parameter is OK**, So What's the problem about this issue?

@Simonhong111 i am not use py-R-FCN, i implement the 4-stage training in MATLAB according the shaoqingren's faster-rcnn MATLAB code, I think you can ask the py-R-FCN code's author for help....

@sanghoon Dear sanghoon, sure, i already send you a e-mail with the test result and also some comment, thank you very much^_^...

@Caojunxu NO!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

@ck196 above 24x24, or maybe above 32x32.................................... i send you a email and hope discuss with you when you are free

@AITTSMD example_finetune384, i use K40. in the aspect of speed, make sure that you do NOT compile caffe with cudnn, because cudnn's 1x1 convolution is slow.

WOW! NIPS2016!!! nice~ i have never been to such a big conference... , wish you have a wonderful workshop and travelling

Dear @aaaaeerr, how about your result?

the dc predict is work well. the ac1x7/7x1 and ac7x7 is not good becaue of: 1)for 1x7/7x1 ac: if we encode the diff of 1x7/7x1ac and orignal ac, some of...

Dear freesouls: i try to train a model using your default settings, the training loss seems big(comparing your training log): train regression error: 575.186, mean error: **0.0799759** Validation at stage:...