You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
paper中提到的:For 4 bounding box coordinates, we round down top left coordinates and round up width and height to expand the detection bounding box.这个在貌似在code中未体现?
看了code,有几个疑问:
paper中的FEM模块(Fig3)和code实现(class FEM(nn.Module))时,貌似不一样.
paper中,输入分3份,然后每份分别经过3个dilation conv层.而code中,貌似并不是这样的操作.
multi_scale_test_pyramid算是对multi_scale_test一个补充吗??感觉就是单纯的用了更多的测试尺度.
多尺度测试时,为什么图片缩小时,要排除一些小结果(小于30的)??而图片放大时,要排除一些大结果(大于100的)??
paper中提到的:For 4 bounding box coordinates, we round down top left coordinates and round up width and height to expand the detection bounding box.这个在貌似在code中未体现?
还有一个关于PyramidBox的问题:
麻烦了!!
The text was updated successfully, but these errors were encountered: