yolo不多做介绍，请参相关博客和论文
本文主要是使用pytorch来对yolo中每一步进行实现 参考：https://blog.paperspace.com/tag/series-yolo/
需要了解：
- 卷积神经网络原理及pytorch实现
- yolo等目标检测算法的检测原理，相关概念如 anchor（锚点）、ROI（感兴趣区域）、IOU（交并比）、NMS（非极大值抑制）、LR softmax分类、边框回归等
本文主要分为四个部分：
- yolo网络层级的定义
- 向前传播
- 置信度阈值和非极大值抑制
- 输入和输出流程
yolo网络层级的定义
Darknet 是 yolo 对目标特征提取的框架，从yolov1的darknet 到 v2，v3的darknet-19，darknet-53
可以看到yolov3的时候已经没有全连接层了，最后只有一个池化层，还加入了resnet的机制。
Demo
layer filters size input output
0 conv 32 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 32 0.299 BFLOPs
1 conv 64 3 x 3 / 2 416 x 416 x 32 -> 208 x 208 x 64 1.595 BFLOPs
2 conv 32 1 x 1 / 1 208 x 208 x 64 -> 208 x 208 x 32 0.177 BFLOPs
3 conv 64 3 x 3 / 1 208 x 208 x 32 -> 208 x 208 x 64 1.595 BFLOPs
4 res 1 208 x 208 x 64 -> 208 x 208 x 64
5 conv 128 3 x 3 / 2 208 x 208 x 64 -> 104 x 104 x 128 1.595 BFLOPs
6 conv 64 1 x 1 / 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BFLOPs
7 conv 128 3 x 3 / 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BFLOPs
8 res 5 104 x 104 x 128 -> 104 x 104 x 128
9 conv 64 1 x 1 / 1 104 x 104 x 128 -> 104 x 104 x 64 0.177 BFLOPs
10 conv 128 3 x 3 / 1 104 x 104 x 64 -> 104 x 104 x 128 1.595 BFLOPs
11 res 8 104 x 104 x 128 -> 104 x 104 x 128
12 conv 256 3 x 3 / 2 104 x 104 x 128 -> 52 x 52 x 256 1.595 BFLOPs
13 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
14 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
15 res 12 52 x 52 x 256 -> 52 x 52 x 256
16 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
17 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
18 res 15 52 x 52 x 256 -> 52 x 52 x 256
19 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
20 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
21 res 18 52 x 52 x 256 -> 52 x 52 x 256
22 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
23 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
24 res 21 52 x 52 x 256 -> 52 x 52 x 256
25 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
26 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
27 res 24 52 x 52 x 256 -> 52 x 52 x 256
28 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
29 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
30 res 27 52 x 52 x 256 -> 52 x 52 x 256
31 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
32 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
33 res 30 52 x 52 x 256 -> 52 x 52 x 256
34 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
35 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
36 res 33 52 x 52 x 256 -> 52 x 52 x 256
37 conv 512 3 x 3 / 2 52 x 52 x 256 -> 26 x 26 x 512 1.595 BFLOPs
38 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
39 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
40 res 37 26 x 26 x 512 -> 26 x 26 x 512
41 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
42 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
43 res 40 26 x 26 x 512 -> 26 x 26 x 512
44 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
45 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
46 res 43 26 x 26 x 512 -> 26 x 26 x 512
47 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
48 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
49 res 46 26 x 26 x 512 -> 26 x 26 x 512
50 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
51 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
52 res 49 26 x 26 x 512 -> 26 x 26 x 512
53 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
54 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
55 res 52 26 x 26 x 512 -> 26 x 26 x 512
56 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
57 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
58 res 55 26 x 26 x 512 -> 26 x 26 x 512
59 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
60 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
61 res 58 26 x 26 x 512 -> 26 x 26 x 512
62 conv 1024 3 x 3 / 2 26 x 26 x 512 -> 13 x 13 x1024 1.595 BFLOPs
63 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
64 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
65 res 62 13 x 13 x1024 -> 13 x 13 x1024
66 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
67 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
68 res 65 13 x 13 x1024 -> 13 x 13 x1024
69 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
70 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
71 res 68 13 x 13 x1024 -> 13 x 13 x1024
72 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
73 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
74 res 71 13 x 13 x1024 -> 13 x 13 x1024
75 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
76 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
77 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
78 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
79 conv 512 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 512 0.177 BFLOPs
80 conv 1024 3 x 3 / 1 13 x 13 x 512 -> 13 x 13 x1024 1.595 BFLOPs
81 conv 255 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 255 0.088 BFLOPs
82 detection
83 route 79
84 conv 256 1 x 1 / 1 13 x 13 x 512 -> 13 x 13 x 256 0.044 BFLOPs
85 upsample 2x 13 x 13 x 256 -> 26 x 26 x 256
86 route 85 61
87 conv 256 1 x 1 / 1 26 x 26 x 768 -> 26 x 26 x 256 0.266 BFLOPs
88 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
89 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
90 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
91 conv 256 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 256 0.177 BFLOPs
92 conv 512 3 x 3 / 1 26 x 26 x 256 -> 26 x 26 x 512 1.595 BFLOPs
93 conv 255 1 x 1 / 1 26 x 26 x 512 -> 26 x 26 x 255 0.177 BFLOPs
94 detection
95 route 91
96 conv 128 1 x 1 / 1 26 x 26 x 256 -> 26 x 26 x 128 0.044 BFLOPs
97 upsample 2x 26 x 26 x 128 -> 52 x 52 x 128
98 route 97 36
99 conv 128 1 x 1 / 1 52 x 52 x 384 -> 52 x 52 x 128 0.266 BFLOPs
100 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
101 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
102 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
103 conv 128 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 128 0.177 BFLOPs
104 conv 256 3 x 3 / 1 52 x 52 x 128 -> 52 x 52 x 256 1.595 BFLOPs
105 conv 255 1 x 1 / 1 52 x 52 x 256 -> 52 x 52 x 255 0.353 BFLOPs
106 detection
1.具体性能比较暂不多提，实现方法如下：
darknet 网络的 config 从官网中可以下载： https://pjreddie.com/darknet/yolo/
每个config包含如下一些模块：
扫描二维码关注公众号，回复：
4778815 查看本文章
1.1.卷积网络模型，步长有1、2。步长为2做上采样
1.2.yolo3中shortcut 类似于resnet，跨通道连接，
1.3.route层。当层级有两个值时，它将返回由这两个值索引的拼接特征图。实验中为-1 和 61，因此该层级将输出从前一层级（-1）到第 61 层的特征图，并将它们按深度拼接。最后检测时像FPN中对不同层次的特征一个结合，更好检测小目标
1. 4.上采样层
1.5.net网络训练的参数层
1.6.yolo层，设置一些参数，anchor的尺寸是由k-means聚类得到的
所以我们要解析config文件来构建我们的网络。首先创建darknet.py 文件（读取的是yolo3的darknet-53）
from __future__ import division
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import numpy as np
def parse_cfg(cfgfile):
#解析cfg，将每个块存储为词典（键 值），然后添加到列表blocks中
file = open(cfgfile, 'r')
lines = file.read().split('\n') #按行存储
lines = [x for x in lines if len(x) > 0] #不读空行
lines = [x for x in lines if x[0] != '#'] #不读注释
lines = [x.rstrip().lstrip() for x in lines]#去除边缘空白
#遍历列表 得到块
block = {}
blocks = []
for line in lines:
if line[0] == '[': #起始mark 标记
if len(block) != 0: #判断是否为空
blocks.append(block)
block = {} #重新初始化block
block["type"] = line[1:-1].rstrip()
else:
key, value = line.split('=')
block[key.rstrip()] = value.lstrip()
blocks.append(block)
print(blocks)
return blocksblocks 是以字典的形式保存信息，输出为：
{'type': 'convolutional', 'batch_normalize': '1', 'filters': '32', 'size': '3', 'stride': '1', 'pad': '1', 'activation': 'leaky'}, {'type': 'convolutional', 'batch_normalize': '1', 'filters': '64', 'size': '3', 'stride': '2', 'pad': '1', 'activation': 'leaky'},
{'type': 'shortcut', 'from': '-3', 'activation': 'linear'},
{'type': 'route', 'layers': '-4'},
{'type': 'upsample', 'stride': '2'},
{'type': 'net', 'batch': '1', 'subdivisions': '1', 'width': '416', 'height': '416', 'channels': '3', 'momentum': '0.9', 'decay': '0.0005', 'angle': '0', 'saturation': '1.5', 'exposure': '1.5', 'hue': '.1', 'learning_rate': '0.001', 'burn_in': '1000', 'max_batches': '500200', 'policy': 'steps', 'steps': '400000,450000', 'scales': '.1,.1'},
{'type': 'yolo', 'mask': '0,1,2', 'anchors': '10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326', 'classes': '80', 'num': '9', 'jitter': '.3', 'ignore_thresh': '.5', 'truth_thresh': '1', 'random': '1'}，
然后利用字典中的信息构建网络层：
def create_modules(blocks):
net_info = blocks[0]#存储网络信息
module_list = nn.ModuleList()
prev_fileters = 3 #初始化图像通道 但是卷积深度由上一层决定
output_filters =[]#追踪之前的层用来路由
#读取bloks中的元素
for index, x in enumerate(blocks[1:]):
module = nn.Sequential()
#读取convolutional块中的信息
if (x['type'] == 'convolutional'):
activation = x['activation']
try:
batch_normalize = int(x["batch_normalize"])
bias = False
except:
batch_normalize = 0
bias = True
filters = int(x["filters"]) #卷积核数量（维度）
padding = int(x["pad"]) #边框填补
kernel_size = int(x["size"]) #卷积核大小
stride = int(x["stride"]) #步长
if padding:
pad = (kernel_size - 1)//2
else:
pad = 0
###
conv = nn.Conv2d(prev_fileters,filters,kernel_size,
stride,pad,bias=bias)
module.add_module("conv_{0}".format(index),conv)
if batch_normalize:
bn = nn.BatchNorm2d(filters)
module.add_module("batch_norm_{0}".format(index),bn)
if activation == "leaky":
activn = nn.LeakyReLU(0.1,inplace=True)
module.add_module("leaky_{0}".format(index),activn)
###
#读取上采样块
elif (x["type"] == "upsample"):
stride = int(x["stride"])
upsample = nn.Upsample(scale_factor=2, mode="nearest")
module.add_module("upsample_{}".format(index),upsample)
#读取路由块
elif (x["type"] == "route"):
x["layers"] = x["layers"].split(',')
start = int(x["layers"][0])
try:
end = int(x["layers"][1])
except:
end = 0
if start > 0:
start = start - index
if end > 0:
end = end - index
route = EmptyLayer()
module.add_module("route_{0}".format(index),route)
if end < 0:
filters = output_filters[index + start] + output_filters[index + end]
else:
filters = output_filters[index + start]
#读取shortcut
elif x["type"] == "shortcut":
shortcut = EmptyLayer()
module.add_module("shortcut_{}".format(index),shortcut)
#读取yolo
elif x["type"] == "yolo":
mask = x["mask"].split(",")
mask = [int(x) for x in mask]
#读取anchor的尺寸
anchors = x["anchors"].split(",")
anchors = [int(a) for a in anchors]
anchors = [(anchors[i], anchors[i+1]) for i in range(0, len(anchors),2)]
anchors = [anchors[i] for i in mask]
detection = DetectionLayer(anchors)
module.add_module("Detection_{}".format(index),detection)
module_list.append(module)
prev_fileters = filters
output_filters.append(filters)
return (net_info, module_list)
blocks = parse_cfg("cfg/yolov3.cfg")
print(create_modules(blocks))输出：
其中，需在此之前定义两个继承nn.Module的类
class EmptyLayer(nn.Module):
def __init__(self):
super(EmptyLayer,self).__init__()
class DetectionLayer(nn.Module):
def __init__(self, anchors):
super(DetectionLayer, self).__init__()
self.anchors = anchors前向传播
下一节介绍 然后根据读取的网络信息 定义一个前向传播
首先定义一个nn.Module的类 Darknet，获取blocks 和 module_list
class Darknet(nn.Module):
def __init__(self, cfgfile):
super(Darknet, self).__init__()
self.blocks = parse_cfg(cfgfile)
self.net_info, self.module_list = create_modules(self.blocks)然后定义向前传播
def forward(self, x, CUDA=False):
modules = self.blocks[1:]
outputs = {}
'''
write flag 表示我们是否遇到第一个检测。如果 write 是 0，则收集器尚未初始化。
如果 write 是 1，则收集器已经初始化，我们只需要将检测图与收集器级联起来即可。
'''
write = 0
#按顺序读modules 不同的层执行不同的操作
for i, module in enumerate(modules):
module_type = (module["type"])
if module_type == "convolutional" or module_type == "upsample":
x = self.module_list[i](x)
elif module_type == "route":
layers = module["layers"]
layers = [int(a) for a in layers]
if (layers[0]) > 0:
layers[0] = layers[0] - i
if len(layers) == 1:
x = outputs[i + (layers[0])]
else:
if (layers[1]) > 0:
layers[1] = layers[1] - i
map1 = outputs[i + layers[0]]
map2 = outputs[i + layers[1]]
x = t.cat((map1, map2), 1) #两个张量（tensor）拼接在一起
elif module_type == "shortcut":
from_ = int(module["from"])
x = outputs[i-1] + outputs[i+from_]
#现在可以将三个不同尺度的检测图级联成一个大的张量
elif module_type == "yolo":
anchors = self.module_list[i][0].anchors
inp_dim = int (self.net_info["height"])
num_classer = int (module["classes"])
x = x.data
x = predict_transform(x, inp_dim, anchors,
num_classer,CUDA)
if not write:
detections = x
write = 1
else:
detections = t.cat((detections, x), 1)
outputs[i] = x
return detectionsYOLO 的输出是一个卷积特征图，包含沿特征图深度的边界框属性。边界框属性由彼此堆叠的单元格预测得出。因此，如果你需要在 (5,6) 处访问单元格的第二个边框，那么你需要通过 map[5,6, (5+C): 2*(5+C)] 将其编入索引。这种格式对于输出处理过程（例如通过目标置信度进行阈值处理、添加对中心的网格偏移、应用锚点等）很不方便。
另一个问题是由于检测是在三个尺度上进行的，预测图的维度将是不同的。虽然三个特征图的维度不同，但对它们执行的输出处理过程是相似的。如果能在单个张量而不是三个单独张量上执行这些运算，就太好了。
为了解决这些问题，我们引入了函数 predict_transform 在utils.py文件中
def predict_transform(prediction, inp_dim, anchors, num_classes, CUDA = True):
batch_size = prediction.size(0)
stride = inp_dim // prediction.size(2)
grid_size = inp_dim // stride
bbox_attrs = 5 + num_classes
num_anchors = len(anchors)
prediction = prediction.view(batch_size, bbox_attrs*num_anchors, grid_size*grid_size)
prediction = prediction.transpose(1,2).contiguous()
prediction = prediction.view(batch_size, grid_size*grid_size*num_anchors, bbox_attrs)
anchors = [(a[0]/stride, a[1]/stride) for a in anchors]
#Sigmoid the centre_X, centre_Y. and object confidencce
prediction[:,:,0] = torch.sigmoid(prediction[:,:,0])
prediction[:,:,1] = torch.sigmoid(prediction[:,:,1])
prediction[:,:,4] = torch.sigmoid(prediction[:,:,4])
#Add the center offsets
grid = np.arange(grid_size)
a,b = np.meshgrid(grid, grid)
x_offset = torch.FloatTensor(a).view(-1,1)
y_offset = torch.FloatTensor(b).view(-1,1)
if CUDA:
x_offset = x_offset.cuda()
y_offset = y_offset.cuda()
x_y_offset = torch.cat((x_offset, y_offset), 1).repeat(1,num_anchors).view(-1,2).unsqueeze(0)
prediction[:,:,:2] += x_y_offset
#log space transform height and the width
anchors = torch.FloatTensor(anchors)
if CUDA:
anchors = anchors.cuda()
anchors = anchors.repeat(grid_size*grid_size, 1).unsqueeze(0)
prediction[:,:,2:4] = torch.exp(prediction[:,:,2:4])*anchors
prediction[:,:,5: 5 + num_classes] = torch.sigmoid((prediction[:,:, 5 : 5 + num_classes]))
prediction[:,:,:4] *= stride
return predictionpredict_transform 函数把检测特征图转换成二维张量，张量的每一行对应边界框的属性，如下所示：
现在，在 darknet.py 文件的顶部定义以下函数
def get_test_input():
img = cv2.imread("dog-cycle-car.png")
img = cv2.resize(img, (416,416)) #Resize to the input dimension
img_ = img[:,:,::-1].transpose((2,0,1)) # BGR -> RGB | H X W C -> C X H X W
img_ = img_[np.newaxis,:,:,:]/255.0 #Add a channel at 0 (for batch) | Normalise
img_ = t.from_numpy(img_).float() #Convert to float
img_ = Variable(img_) # Convert to Variable
return img_测试代码
model = Darknet("cfg/yolov3.cfg")
inp = get_test_input()
pred = model(inp)
print (pred)输出
下载预训练权重
https://pjreddie.com/media/files/yolov3.weights
读取权重
def load_weights(self, weightfile):
fp = open(weightfile, "rb")
header = np.fromfile(fp, dtype = np.int32, count = 5)
self.header = t.from_numpy(header)
self.seen = self.header[3]
weights = np.fromfile(fp, dtype=np.float32)
ptr = 0
for i in range(len(self.module_list)):
module_type = self.blocks[i+1]["type"]
if module_type == "convolutional":
module = self.module_list[i]
try:
batch_normalize = int(self.blocks[i+1]["batch_normalize"])
except:
batch_normalize = 0
conv = module[0]
if (batch_normalize):
bn = module[1]
num_bn_biases = bn.bias.numel()
bn_biases = t.from_numpy(weights[ptr:ptr + num_bn_biases])
ptr += num_bn_biases
bn_weights = t.from_numpy(weights[ptr: ptr + num_bn_biases])
ptr += num_bn_biases
bn_running_mean = t.from_numpy(weights[ptr: ptr + num_bn_biases])
ptr += num_bn_biases
bn_running_var = t.from_numpy(weights[ptr: ptr + num_bn_biases])
ptr += num_bn_biases
#Cast the loaded weights into dims of model weights.
bn_biases = bn_biases.view_as(bn.bias.data)
bn_weights = bn_weights.view_as(bn.weight.data)
bn_running_mean = bn_running_mean.view_as(bn.running_mean)
bn_running_var = bn_running_var.view_as(bn.running_var)
#Copy the data to model
bn.bias.data.copy_(bn_biases)
bn.weight.data.copy_(bn_weights)
bn.running_mean.copy_(bn_running_mean)
bn.running_var.copy_(bn_running_var)
else:
#Number of biases
num_biases = conv.bias.numel()
#Load the weights
conv_biases = t.from_numpy(weights[ptr: ptr + num_biases])
ptr = ptr + num_biases
#reshape the loaded weights according to the dims of the model weights
conv_biases = conv_biases.view_as(conv.bias.data)
#Finally copy the data
conv.bias.data.copy_(conv_biases)
#Let us load the weights for the Convolutional layers
num_weights = conv.weight.numel()
#Do the same as above for weights
conv_weights = t.from_numpy(weights[ptr:ptr+num_weights])
ptr = ptr + num_weights
conv_weights = conv_weights.view_as(conv.weight.data)
conv.weight.data.copy_(conv_weights)测试：
model = Darknet("cfg/yolov3.cfg")
model.load_weights("yolov3.weights")
inp = get_test_input()
pred = model(inp)
print (pred)通过模型构建和权重加载，就可以开始进行目标检测了
下一章介绍如何利用 objectness 置信度阈值和非极大值抑制生成最终的检测结果。