Cless
Cless
@leejiajun @banxiaduhuo Hi, did you solve the problem? I got the same issue when training ZF model on custom dataset
Right, some images have big ratio of width and height cause this.Thanks!
I remember that this py-faster-rccn doesn't used selective search
To train with your own network, I think you need to define the network in Caffe prototxt first, then train it on labeled datasets to get Caffe model. After that,...
In my case, I modified https://github.com/rbgirshick/py-faster-rcnn/blob/master/lib/datasets/imdb.py#L218 and changed this line `if gt_roidb is not None and gt_roidb[i]['boxes'].size > 0:` to `if gt_roidb[i] is not None and gt_roidb[i]['boxes'].size > 0:`
@slchiang How about using ``` def filter_roidb(roidb): """Remove roidb entries that have no usable RoIs.""" ``` at https://github.com/rbgirshick/py-faster-rcnn/blob/master/lib/fast_rcnn/train.py#L127 ?
> thanks for the answer. would be cool to have the process time automatically in the log included (for instance in the end: 0.8sec) 2021-09-16 14:53:12,774 - INFO - 127.0.0.1:52962...
Thanks a lot. I'm researching options for a production environment, so there are more questions. Is it safe to search/add/remove in EuclidesDB concurrently? How many requests could EuclidesDB handle at...
solved after following steps here
@trimechee do you know the corresponding parameters in VLC? (They should be here: https://wiki.videolan.org/VLC_command-line_help/) We can pass VLC params in Settings.