Open leonardoaraujosantos opened 7 years ago
Yes. Although, there will be classification scores and bbox offset adjustment for each default box (i.e. 4 in this case).
Yes.
I don't quite understand the question. The net's predictions will be related to each default box.
Each box will have slightly different classification scores and offsets prediction. See the answer 3 above.
Thanks @weiliu89, and sorry for the latest question if it was not that clear.
So considering the activation at conv_9_2 on the diagram the size will be 5x5x256
Spatially the priorboxes will be resized to fit on this 5x5 window correct?
So each cell will have 4 boxes, but the boxes does not cover completly all the cells
On this case which cells should I consider for the red box?
I think it's the opposite, the red box(response of red box) come with cell 5, as priorboxes 'embedded' to each cell.
@weiliu89 am I right or wrong?
I think Fig.1 on original paper is both helpful and a bit (if you think with it for forward pass) confusing.
@weiliu89 check if I understand...
During forward propagation. (Prediction)
So in resume there is no crazy calculation of the scores of each cells that are bellow a particular region (for example red box), in order to do the non maxima supression.
The non-maxima supression will work on each box of each cell (At the end of the prediction, after merging all the boxes).
So each cell will have.... Following the formula (paper page 4) (c + 4)k (Filters) c: Number of classes + Background class 4: (cx,cy,width,height) k: Number of boxes
@marksunpeng what you think?
Sorry @weiliu89 could you confirm if I'm understanding the following topics?
During forward propagation. (Prediction)
The non-maxima supression will work on each box of each cell (At the end of the prediction, after merging all the boxes).
So each cell will have.... Following the formula (paper page 4) (c + 4)k (Filters) c: Number of classes + Background class 4: (cx,cy,width,height) k: Number of boxes
Thanks again.
Introduction
Hi @weiliu89 considering this picture from the paper, and thinking on the prediction phase:
Some of my insights (Could be wrong)
Questions
Doing a zoom on a small activation map.![cellzoom](https://cloud.githubusercontent.com/assets/898383/22287144/963ced30-e2e9-11e6-9242-302ade515c1a.png)
Again thanks for the help