Open zimenglan-sysu-512 opened 8 years ago
I recently have a research in image segmentation,it also says "multi-scale testing",so what is "multi-scale testing" mean?
Have you solved? I met the same problem.
@zimenglan-sysu-512 Did you trained the networks on a multi-scale way or you just trained the network on single scale?
@hzh8311 , Do you know how to achieve multi-sacle training now?
recently i want to try multi-scale testing. since the
rpn
network does not support multi-scale orbatchsize > 1
, so i setbatchsize = 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 thedemo.py
: if try different scale (only one scale at the same time), the results look normal, for example:scale: 684
scale: 564
scales: 564 and 684 together
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 networknet
, that is to say each scale has its ownnet
, 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.