https://medium.com/@jonathan_hui/real-time-object-detection-with-yolo-yolov2-28b1b93e2088
I wondered if all anchors should be applied for a loss value. The answer is yes in my guess.
'Papers > Machine learning' 카테고리의 다른 글
| Various calculations for Convolutions (0) | 2019.04.30 |
|---|---|
| Anchor size for yolo (0) | 2019.04.27 |
| Faster RCNN vs. SSD (0) | 2019.04.27 |
| Cross-entropy cost function (0) | 2019.04.27 |
| batch, epoch, iteration (0) | 2019.04.15 |