Closed Maofei closed 7 years ago
@Maofei
Due to the multi-scale feature concatenation, both of the height and the weight of an input tensor for our network should be multiple of 32, which leads to different values of scale factors in general.
@Maofei
Please see 1) 'def _get_image_blob(im)' in lib/fast-rcnn/test.py that computes the scale factors for the original height and the original width, respectively, and 2) 'def im_detect(net, im, _t, boxes=None)' in the same file that assigns those values to blobs['im_info'], so that our 'im_info' blob has two scale factors.
@kyehyeon So at the training phase, there is only one scale ?
The training was done in a multi-scale way. However, as @kyehyeon has mentioned, due to the network structures, we had to keep the shape of training images to be multiples of 32. So scale factor along x-axis can be different from the one along y-axis.
No matter I met with this problem: top_shape[j] == bottom[i]->shape(j) (40 vs. 39) All inputs must have the same shape, except at concat_axis.
the "im_info" toped from python implemented data layer only has one scale for both height and width, but the proposal layer implemented in C++ use two scale for height and width separately.
I'm wondering whether it's a mistake or do i missed something? @sanghoon