Welcome new user! You can search existing questions and answers without registering, but please register to post new questions and receive answers. Note that due to large amounts of spam attempts, your first three posts will be manually moderated, so please be patient.
We have moved to a new forum at http://jevois.usc.edu, please check it out. The forum at jevois.org/qa will not allow new user registrations but is maintained alive for its useful past questions and answers.

Is this a bug in PyDetectionDNN.py

0 votes

Hi,

Line # 253 says.

self.net.setInput(np.array([inpHeight, inpWidth, 1.6], dtype=np.float32), 'im_info')

Shouldn't that be "self.inpHeight" and "self.inpWidth"?

I assume it doesn't matter because you don't use RCNN or R-FCN.

Jack

asked Oct 8, 2018 in User questions by jack.johnson.pub (230 points)

1 Answer

0 votes
yes, good catch! We have not found good lightweight Faster-RCNN so indeed that section of code had not been tested. Traveling now but update asap.

Can you share any Faster-RCNN weights and config files if you find one that works?
answered Oct 11, 2018 by JeVois (46,580 points)
...