美文网首页机器学习与深度学习
Autonomous driving application -

Autonomous driving application -

作者: U2509 | 来源:发表于2019-03-03 21:33 被阅读0次

    2019-03-03
    Summary for YOLO:
    Input image (608, 608, 3)
    The input image goes through a CNN, resulting in a (19,19,5,85) dimensional output.
    After flattening the last two dimensions, the output is a volume of shape (19, 19, 425):
    Each cell in a 19x19 grid over the input image gives 425 numbers.
    425 = 5 x 85 because each cell contains predictions for 5 boxes, corresponding to 5 anchor boxes, as seen in lecture.
    85 = 5 + 80 where 5 is because (pc,bx,by,bh,bw)(pc,bx,by,bh,bw) has 5 numbers, and and 80 is the number of classes we'd like to detect
    You then select only few boxes based on:
    Score-thresholding: throw away boxes that have detected a class with a score less than the threshold
    Non-max suppression: Compute the Intersection over Union and avoid selecting overlapping boxes
    This gives you YOLO's final output

    holding to eliminate overlapping boxes
    

    Because training a YOLO model from randomly initialized weights is non-trivial and requires a large dataset as well as lot of computation, we used previously trained model parameters in this exercise. If you wish, you can also try fine-tuning the YOLO model with your own dataset, though this would be a fairly non-trivial exercise.

    相关文章

      网友评论

        本文标题:Autonomous driving application -

        本文链接:https://www.haomeiwen.com/subject/ojzmuqtx.html