Visual Learning and Recognition: Difference between revisions
| Line 429: | Line 429: | ||
The a sequence of FC layers produces an output. | The a sequence of FC layers produces an output. | ||
;Sliding Window | ;Sliding Window | ||
If network takes 3x221x221 and you have an image 3x257x257. | If network takes 3x221x221 and you have an image 3x257x257. | ||
Run image through network with sliding window. Then greedily merge the boxes. | Run image through network with sliding window. Then greedily merge the boxes. | ||