training error

[yuwenxiong]

training error

[Jiaming-Liu]

ImportError: numpy.core.multiarray failed to import
after running
pip install -U numpy==1.11.0

[muyue1238]

I ran into this same problem, too. Have to say I got tortured by this problem for near two weeks, and the solution is atually quiet simple. I refered to the following question:rbgirshick/py-faster-rcnn#626 . It turns out that numpy-1.13 doesn't support flaot and you have to change some parameters into int. And the wrong parameters will be pointed out in error code, in this case, line 66 and line 185 in proposal_target_layer.py are wrong. After you changed it, you maybe ran into another error in diffrent places, just change them all, and it will finally work. BTW, back-up the files you are going to change incase something went wrong. Hope this will help.

[nashory]

I have the same problem.
Anyone solved?

[Timonzimm]

Followed the solution presented here: rbgirshick/py-faster-rcnn#481
pip install -U numpy==1.11.0

It personally worked perfectly afterwards.

[starxhong]

rbgirshick/py-faster-rcnn#481
gives two ways to solve the problem perfectly w./wo. reinstall numpy

[wander1985]

I've got similar error.
By changing
fg_rois_per_this_image = min(fg_rois_per_image, fg_inds.size) to
fg_rois_per_this_image = np.int64(min(fg_rois_per_image, fg_inds.size))
in line 182 in proposal_target_layer.py works for me.

Hope this would help.