search

rbgirshick / py-faster-rcnn

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
Other
8.1k stars 4.11k forks source link

multi-scale testing? #275

Open zimenglan-sysu-512 opened 8 years ago

zimenglan-sysu-512 commented 8 years ago

recently i want to try multi-scale testing. since the rpn network does not support multi-scale or batchsize > 1, so i set batchsize = 1 and loop for multi-scale to stack the results of each scale for one image. but i got some wired problems, when i run the demo.py: if try different scale (only one scale at the same time), the results look normal, for example:

scale: 684 image

scale: 564 image

scales: 564 and 684 together image

it is so wired that the results from mulit-scales have some strange bounding boxes. but if try single scale multiply times for the same image, results look normal; if i try multi-scale case, i found that the the results of last scale in cfg.TEST.SCALES look normal, the rest from other scales but not the last one look wired. if try to replicate the network net, that is to say each scale has its own net, the results stacked from these scales look normal.

i try to figure out what happens, but can't find any useful info, i guess the network net in the multi-scale testing get dirty.

have anyone met this before?

thanks.

dongzhuoyao commented 7 years ago

I recently have a research in image segmentation,it also says "multi-scale testing",so what is "multi-scale testing" mean?

feymanpriv commented 7 years ago

Have you solved? I met the same problem.

hzh8311 commented 7 years ago

@zimenglan-sysu-512 Did you trained the networks on a multi-scale way or you just trained the network on single scale?

wwwpbai commented 4 years ago

@hzh8311 , Do you know how to achieve multi-sacle training now?