xiaoxiongli

hi, cache-tlb, you can run it in GPU mode.

I think you'd better to buy a GPU. such as M40. it is really fast if you use a GPU.

please enable the caffe log in the matlab to see what happend, it will have a log file to give you some hint about the error.

@ouxinyu I recommend you that use the R-FCN's python version, it is trained in a end2end method(not 4-stage training), the end2end training method is 1.5x faster than 4-stage training. and...

@ouxinyu I recommend you that use the R-FCN's python version, it is trained in a end2end method(not 4-stage training), the end2end training method is 1.5x faster than 4-stage training. and...

@northeastsquare for my own training data(229 category logo, about 3w images) , compare to faster-rcnn, the mAP change from 90 to 97. i do not know the result of VOC2007,...

I also have this question, but it seems the answer is no.