SunshineAtNoon

Any solution to this?

@zirohut Do you need MATLAB to run this code?

Same problems here

hi, @paulinder . I am trying to use dlib's selective search too. I changed some code in demo.py to use dlib’s selective search to generate proposal bounding boxes, so no...

@paulinder I suppose you use find_candidate_object_locations to generate bounding boxes. Did you try to set the min_size parameter of this function to a greater value so that less bounding box...

@haimansx No, I have not solved the problem, I think the only way to solve the problem is by implementing the two functions above in c++

@tanjoreg No, I haven't solved this issue. Fast Rcnn can only be trained on GPU as far as I know. But it can be tested on CPU.

As I mentioned above, I think the way to solve this issue is to implement the two functions above in c++.

@zeyuanxy Hi~, How did you generate images for the background class? How many images are needed for this class?

@pradeepj247 these links might help: https://github.com/zeyuanxy/fast-rcnn/tree/master/help/train http://sunshineatnoon.github.io/Train-fast-rcnn-model-on-imagenet-without-matlab/