前言:上次讲了YOLOv3中的模型构建,从头到尾理了一遍从cfg读取到模型整个构建的过程。其中模型构建中最重要的YOLOLayer还没有梳理,本文将从代码的角度理解YOLOLayer的构建与实现。
1. Grid创建
YOLOv3是一个单阶段的目标检测器,将目标划分为不同的grid,每个grid分配3个anchor作为先验框来进行匹配。首先读一下代码中关于grid创建的部分。
首先了解一下pytorch中的API:torch.mershgrid
举一个简单的例子就比较清楚了:
Python 3.7.3 (default, Apr 24 2019, 15:29:51) [MSC v.1915 64 bit (AMD64)] :: Anaconda, Inc. on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> a = torch.arange(3)
>>> b = torch.arange(5)
>>> x,y = torch.meshgrid(a,b)
>>> a
tensor([0, 1, 2])
>>> b
tensor([0, 1, 2, 3, 4])
>>> x
tensor([[0, 0, 0, 0, 0],
[1, 1, 1, 1, 1],
[2, 2, 2, 2, 2]])
>>> y
tensor([[0, 1, 2, 3, 4],
[0, 1, 2, 3, 4],
[0, 1, 2, 3, 4]])
>>>
单纯看输入输出,可能不是很明白,列举一个例子:
>>> for i in range(3):
... for j in range(4):
... print("(", x[i,j], "," ,y[i,j],")")
...
( tensor(0) , tensor(0) )
( tensor(0) , tensor(1) )
( tensor(0) , tensor(2) )
( tensor(0) , tensor(3) )
( tensor(1) , tensor(0) )
( tensor(1) , tensor(1) )
( tensor(1) , tensor(2) )
( tensor(1) , tensor(3) )
( tensor(2) , tensor(0) )
( tensor(2) , tensor(1) )
( tensor(2) , tensor(2) )
( tensor(2) , tensor(3) )
>>> torch.stack((x,y),2)
tensor([[[0, 0],
[0, 1],
[0, 2],
[0, 3],
[0, 4]],
[[1, 0],
[1, 1],
[1, 2],
[1, 3],
[1, 4