| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 4968708 | Computer Vision and Image Understanding | 2017 | 9 Pages |
Abstract
We show that the use of 128 Ã 128 pixel images is sufficient to make qualitative conclusions about optimal network structure that hold for the full size Caffe and VGG nets. The results are obtained an order of magnitude faster than with the standard 224Â pixel images.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Dmytro Mishkin, Nikolay Sergievskiy, Jiri Matas,