Bilinear-CNN-TensorFlow icon indicating copy to clipboard operation
Bilinear-CNN-TensorFlow copied to clipboard

Published 20 hours ago • verified publisher icon abhaydoke09

can any one tell me what the location means in the paper?

Open Shawn-Chung opened this issue 6 years ago • 3 comments

in the paper, it says "we refer to lacations generally, which can include position and scale",i do not know what it means?

Shawn-Chung avatar Jun 13 '18 02:06 Shawn-Chung

From this line: Bilinear-CNN-TensorFlow/core/bcnn_finetuning.py#L226 as for VGG, I think each "location" corresponds to each pixel in the last feature map. More generally, one location can correspond to one pixel or a patch of pixels (larger scale). Correct me if i'm wrong.

reckdk avatar Aug 14 '18 12:08 reckdk

yes, got it, thx!

Shawn-Chung avatar Aug 15 '18 01:08 Shawn-Chung

hello， I still have a problem. After running the second part of the whole model, I will finish training. It seems that the final model is not saved in the code. Why is this done in the absence of the training model? Can you give me some details?

JUSTDODoDo avatar Oct 28 '18 10:10 JUSTDODoDo