search

gkioxari / RstarCNN

R*CNN
Other
132 stars 53 forks source link

question about 'other' class in pascal voc ? #36

Open gooners1886 opened 7 years ago

gooners1886 commented 7 years ago

@gkioxari , I got a question about the processing of 'other' class in pascal voc

  1. in this line, 'other' class is the last element in the class list.
  2. while in this line, i find that it ignore the 0-index class.
    Should it ignore the 'other' class? but acording to 1, index of 'other' class is not 0 ? Any comments ?
gkioxari commented 7 years ago

These are different classes that you are talking about. 1. is action classes for the action recognition branch. 2. is for the person detection branch. For 2. the classes are (background, person)

gooners1886 commented 7 years ago

@gkioxari I still got confused for the two lines above.
which in this line, it ignore the 0-index. i think if use the pascal_voc_2012 for training, the class list shoud be ('jumping', 'phoning', 'playinginstrument', 'reading', 'ridingbike', 'ridinghorse', 'running', 'takingphoto', 'usingcomputer', 'walking', 'other'). So num_classes in this line is 11. if it ignores the 0-index, which means ignore 'jumping' class when applying mean subtraction and stds division. I think the column 0 in variable targets means the class_id: 0 for jumping, 1 for phoning ... 10 means other. Does 0 also means backgroud ? I find both background and jumping will use 0 for class-index in the column 0 of variable targets. Is that right?
I find this line creates an zero array, the colomn 0 of the variable targets means either groundtruth label is 0, or IOU is below threshold. so after this methon returns, we can not tell what does 0 means. should I change it from targets = np.zeros((rois.shape[0], 5), dtype=np.float32) to targets = np.zeros((rois.shape[0], 5), dtype=np.float32) targets[:,0] = -1 Do I miss something important?

Would you give some explanations in details ？ Thank you very much~