import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import numpy as np
from util import *
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_ = torch.from_numpy(img_).float() #Convert to float
img_ = Variable(img_) # Convert to Variable
return img_
"""
# 加载文件并过滤掉文本中多余内容
file = open(cfgfile, 'r')
lines = file.read().split('\n') # store the lines in a list等价于readlines
lines = [x for x in lines if len(x) > 0] # 去掉空行
lines = [x for x in lines if x[0] != '#'] # 去掉以#开头的注释行
lines = [x.rstrip().lstrip() for x in lines] # 去掉左右两边的空格(rstricp是去掉右边的空格，lstrip是去掉左边的空格)
# cfg文件中的每个块用[]括起来最后组成一个列表，一个block存储一个块的内容，即每个层用一个字典block存储。
block = {}
blocks = []
for line in lines:
if line[0] == "[": # 这是cfg文件中一个层(块)的开始
if len(block) != 0: # 如果块内已经存了信息, 说明是上一个块的信息还没有保存
blocks.append(block) # 那么这个块（字典）加入到blocks列表中去
block = {} # 覆盖掉已存储的block,新建一个空白块存储描述下一个块的信息(block是字典)
block["type"] = line[1:-1].rstrip() # 把cfg的[]中的块名作为键type的值
else:
key,value = line.split("=") #按等号分割
block[key.rstrip()] = value.lstrip()#左边是key(去掉右空格)，右边是value(去掉左空格)，形成一个block字典的键值对
blocks.append(block) # 退出循环，将最后一个未加入的block加进去
# print('\n\n'.join([repr(x) for x in blocks]))
return blocks
for index, x in enumerate(blocks[1:]): #这里，我们迭代block[1:] 而不是blocks，因为blocks的第一个元素是一个net块，它不属于前向传播。
module = nn.Sequential()# 这里每个块用nn.sequential()创建为了一个module,一个module有多个层
#check the type of block
#create a new module for the block
#append to module_list
#Add the Batch Norm Layer
if batch_normalize:
bn = nn.BatchNorm2d(filters)
module.add_module("batch_norm_{0}".format(index), bn)
#Check the activation.
#It is either Linear or a Leaky ReLU for YOLO
# 给定参数负轴系数0.1
if activation == "leaky":
activn = nn.LeakyReLU(0.1, inplace = True)
module.add_module("leaky_{0}".format(index), activn)
#Yolo is the detection layer
elif x["type"] == "yolo":
mask = x["mask"].split(",")
mask = [int(x) for x in mask]
anchors = x["anchors"].split(",")
anchors = [int(a) for a in anchors]
anchors = [(anchors, anchors[i+1]) for i in range(0, len(anchors),2)]
anchors = [anchors for i in mask]
def forward(self, x, CUDA):
modules = self.blocks[1:] # 除了net块之外的所有，forward这里用的是blocks列表中的各个block块字典
outputs = {} #We cache the outputs for the route layer
write = 0#write表示我们是否遇到第一个检测。write=0，则收集器尚未初始化，write=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。
for i, module in enumerate(modules):
module_type = (module["type"])
if module_type == "convolutional" or module_type == "upsample":
x = self.module_list(x)
elif module_type == "route":
layers = module["layers"]
layers = [int(a) for a in layers]
if (layers[0]) > 0:
layers[0] = layers[0] - i
# 如果只有一层时。从前面的if (layers[0]) > 0:语句中可知，如果layer[0]>0，则输出的就是当前layer[0]这一层的特征,如果layer[0]<0，输出就是从route层(第i层)向后退layer[0]层那一层得到的特征
if len(layers) == 1:
x = outputs[i + (layers[0])]
#第二个元素同理
else:
if (layers[1]) > 0:
layers[1] = layers[1] - i
if not write: #if no collector has been intialised. 因为一个空的tensor无法与一个有数据的tensor进行concatenate操作，
detections = x #所以detections的初始化在有预测值出来时才进行，
write = 1 #用write = 1标记，当后面的分数出来后，直接concatenate操作即可。
#The first 5 values are header information
# 1. Major version number
# 2. Minor Version Number
# 3. Subversion number
# 4,5. Images seen by the network (during training)
header = np.fromfile(fp, dtype = np.int32, count = 5)# 这里读取first 5 values权重
self.header = torch.from_numpy(header)
self.seen = self.header[3]
#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 将从weights文件中得到的权重bn_biases复制到model中(bn.bias.data)
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:#如果 batch_normalize 的检查结果不是 True，只需要加载卷积层的偏置项
#Number of biases
num_biases = conv.bias.numel()
