计算yolov5中detect.py生成图像的mAP

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

文章目录
前言一、用YoloV5的detect.py生成预测图，预测类别，预测框坐标，预测置信度1、跑detect.py程序
二、将测试图的Annotation的XML文件转化为txt文件，使用yolo坐标格式表示三、将YoloV5和GroundTruth的yolo坐标转换为voc坐标1.将groundtruth改成voc坐标:2.将yolo结果改成voc坐标:
四、对某些应yolov5未检测到物体而不生成的txt文件，去除groundTruth中对应文件,然后测试mAP

前言
本文适用背景：
准备直接用yolov5提供的预训练模型coco128测试自己图像，而不是自己训练模型，然后进行目标检测。准备对自己测试后的图像进行计算mAP等指标。
本文参考了许多文章，从中拷贝部分程序。如有侵权问题，请及时联系我，我会进行删改。

提示：以下是本篇文章正文内容，下面案例可供参考
一、用YoloV5的detect.py生成预测图，预测类别，预测框坐标，预测置信度
下载yolov5程序包，安装好环境，下载好权重文件放在weights文件夹这种就不说了，不会的自己百度。
1、跑detect.py程序
yolov5中主要有三个程序，train.py，val.py，detect.py。一般正常的训练自己数据集，然后测试。就用到train.py和val.py。但谁让我们不正常呢？我们只是用他的预训练模型来测试自己的图片。所以，首先要保证，你要测试的东西是他的预训练模型能测得到的。coco128.yaml的测试范围如下： 如果你的类别在里面，那恭喜进入下一步。 这么多超参数，你其实要改的不多，第一个weights是权重文件的路径。source是你的原图地址。classes是你在上面那么多类别中选择的类别，比如你的图片有人和车，但你的Annotation中只有人这一个类别，你直接跑的化，会输出车和人的预测结果，但你只要人的结果，你就可以选择–classes 0，表示只检测人。比如我的测试集要测试的类别为： 那对应到coco.yaml中就是 0 2 3 5 7 9，这个数字不一定要从小到大，它只是个标签。 然后–save-txt就是把预测类别，框坐标存在txt文件中。yolo的坐标格式为：
<class_id> <x_center> <y_center> <width> <height>

–save-conf 就是加上置信度，变成：
<class_id> <x_center> <y_center> <width> <height> <confifence>

所以，我的代码最后再终端运行的是：
python detect.py –source /home/test/Mytest –weights weights/yolov5l.pt –classes 0 2 3 5 7 9 –save-txt –save-conf

然后会在runs/detect/exp中生成你要的图片和文件。
上面是训练的基础，但我们需要修改代码。因为大家也看到了coco.yaml记录了图片的类别和标签，即person：0，car：2，bus：5。但我们的测试集的类别是people：0，bus：1， car：2.怎么办呢? 直接上代码:
# Write results
for *xyxy, conf, cls in reversed(det):
# print(cls)
if cls ==torch.tensor(0., device='cuda:0'):cls = torch.tensor(0., device='cuda:0')
if cls ==torch.tensor(5., device='cuda:0'):cls =torch.tensor(1., device='cuda:0')
if cls ==torch.tensor(2., device='cuda:0'):cls =torch.tensor(2., device='cuda:0')
if cls ==torch.tensor(3., device='cuda:0'):cls =torch.tensor(3., device='cuda:0')
if cls ==torch.tensor(9., device='cuda:0'):cls =torch.tensor(4., device='cuda:0')
if cls ==torch.tensor(7., device='cuda:0'):cls =torch.tensor(5., device='cuda:0')
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')

if save_img or save_crop or view_img: # Add bbox to image
if cls ==torch.tensor(0., device='cuda:0'):cls = torch.tensor(0., device='cuda:0')
if cls ==torch.tensor(1., device='cuda:0'):cls =torch.tensor(5., device='cuda:0')
if cls ==torch.tensor(2., device='cuda:0'):cls =torch.tensor(2., device='cuda:0')
if cls ==torch.tensor(3., device='cuda:0'):cls =torch.tensor(3., device='cuda:0')
if cls ==torch.tensor(4., device='cuda:0'):cls =torch.tensor(9., device='cuda:0')
if cls ==torch.tensor(5., device='cuda:0'):cls =torch.tensor(7., device='cuda:0')
c = int(cls) # integer class
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
annotator.box_label(xyxy, label, color=colors(c, True))
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)

去detect.py中找到上述代码段,加上我改的那些个if语句.也就是模型检测到一辆bus,他给出标签为5,那我们就在存储到txt前将5改为1.总共两段if代码段,前一段是改txt的,后一段是改回来,避免给图片写名字时写错. 这样,我们就获得了yolov5的预测结果. 如果你仔细看生成的txt文件,你会发现部分图片没有生成txt,这是因为模型没在你那张图片上检测到物体,他就不生成txt文件,txt文件名会和图片名一致
二、将测试图的Annotation的XML文件转化为txt文件，使用yolo坐标格式表示
如何将我们测试图的GroundTruth标签从xml转换成txt(这边xml名字要和前面图片名一致) 直接上代码: voc_label.py
# -*- coding: utf-8 -*-
# xml解析包
import xml.etree.ElementTree as ET
import os
from os import getcwd
import shutil

sets = ['test_m3df']
classes = ['People', 'Bus', 'Car', 'Motorcycle', 'Lamp', 'Truck']

style = '.png'

# 进行归一化操作
def convert(size, box): # size:(原图w,原图h) , box:(xmin,xmax,ymin,ymax)
dw = 1. / size[0] # 1/w
dh = 1. / size[1] # 1/h
x = (box[0] + box[1]) / 2.0 # 物体在图中的中心点x坐标
y = (box[2] + box[3]) / 2.0 # 物体在图中的中心点y坐标
w = box[1] – box[0] # 物体实际像素宽度
h = box[3] – box[2] # 物体实际像素高度
x = x * dw # 物体中心点x的坐标比(相当于 x/原图w)
w = w * dw # 物体宽度的宽度比(相当于 w/原图w)
y = y * dh # 物体中心点y的坐标比(相当于 y/原图h)
h = h * dh # 物体宽度的宽度比(相当于 h/原图h)
return (x, y, w, h) # 返回 相对于原图的物体中心点的x坐标比,y坐标比,宽度比,高度比,取值范围[0-1]

# year ='2012', 对应图片的id（文件名）
def convert_annotation(image_id):
'''
将对应文件名的xml文件转化为label文件，xml文件包含了对应的bunding框以及图片长款大小等信息，
通过对其解析，然后进行归一化最终读到label文件中去，也就是说
一张图片文件对应一个xml文件，然后通过解析和归一化，能够将对应的信息保存到唯一一个label文件中去
labal文件中的格式：calss x y w h　　同时，一张图片对应的类别有多个，所以对应的ｂｕｎｄｉｎｇ的信息也有多个
'''
# 对应的通过year 找到相应的文件夹，并且打开相应image_id的xml文件，其对应bund文件
in_file = open('./data/Annotations/%s.xml' % (image_id), encoding='utf-8')
# 准备在对应的image_id 中写入对应的label，分别为
# <object-class> <x> <y> <width> <height>
out_file = open('./data/labels/%s.txt' % (image_id), 'w', encoding='utf-8')
# 解析xml文件
tree = ET.parse(in_file)
# 获得对应的键值对
root = tree.getroot()
# 获得图片的尺寸大小
size = root.find('size')
# 如果xml内的标记为空，增加判断条件
if size != None:
# 获得宽
w = int(size.find('width').text)
# 获得高
h = int(size.find('height').text)
# 遍历目标obj
for obj in root.iter('object'):
# 获得difficult ？？
difficult = obj.find('difficult').text
# 获得类别 =string 类型
cls = obj.find('name').text
# 如果类别不是对应在我们预定好的class文件中，或difficult==1则跳过
if cls not in classes or int(difficult) == 1:
continue
# 通过类别名称找到id
cls_id = classes.index(cls)
# 找到bndbox 对象
xmlbox = obj.find('bndbox')
# 获取对应的bndbox的数组 = ['xmin','xmax','ymin','ymax']
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
print(image_id, cls, b)
# 带入进行归一化操作
# w = 宽, h = 高， b= bndbox的数组 = ['xmin','xmax','ymin','ymax']
bb = convert((w, h), b)
# bb 对应的是归一化后的(x,y,w,h)
# 生成 calss x y w h 在label文件中
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

# 返回当前工作目录
wd = getcwd()
print(wd)

# 先找labels文件夹如果不存在则创建
labels = './data/labels'
if os.path.exists(labels):
shutil.rmtree(labels) # delete output folder
os.makedirs(labels) # make new output folder

for image_set in sets:
'''
对所有的文件数据集进行遍历
做了两个工作：
　　　　１．将所有图片文件都遍历一遍，并且将其所有的全路径都写在对应的txt文件中去，方便定位
　　　　２．同时对所有的图片文件进行解析和转化，将其对应的bundingbox 以及类别的信息全部解析写到label 文件中去
　　　　　最后再通过直接读取文件，就能找到对应的label 信息
'''
# 读取在ImageSets/Main 中的train、test..等文件的内容
# 包含对应的文件名称
# image_ids = open('./data/ImageSets/%s.txt' % (image_set)).read().strip().split()
image_ids = os.listdir('图片地址')
image_id_s = []
for i in image_ids:
file_name=i.split('.')[0]
image_id_s.append(file_name)
# 打开对应的2012_train.txt 文件对其进行写入准备

txt_name = './data/%s.txt' % (image_set)
if os.path.exists(txt_name):
os.remove(txt_name)
else:
open(txt_name, 'w')

list_file = open(txt_name, 'w')
# 将对应的文件_id以及全路径写进去并换行
for image_id in image_id_s:
list_file.write('data/images/%s%s\n' % (image_id, style))
# 调用 year = 年份 image_id = 对应的文件名_id
convert_annotation(image_id)
# 关闭文件
list_file.close()

参考该文:https://blog.csdn.net/weixin_42182534/article/details/123608276 这样我们就获得了标签的yolo格式坐标的txt
三、将YoloV5和GroundTruth的yolo坐标转换为voc坐标
1.将groundtruth改成voc坐标:
直接上代码: get_GT.py
import numpy as np
import cv2
import torch
import os

label_path = './test_label'
image_path = './test'

# 坐标转换，原始存储的是YOLOv5格式
# Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
def xywhn2xyxy(x, w=800, h=800, padw=0, padh=0):
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = w * (x[:, 0] – x[:, 2] / 2) + padw # top left x
y[:, 1] = h * (x[:, 1] – x[:, 3] / 2) + padh # top left y
y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x
y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y
return y

folder = os.path.exists('GT')
if not folder:
os.makedirs('GT')

folderlist = os.listdir(label_path)
for i in folderlist:
label_path_new = os.path.join(label_path, i)
with open(label_path_new, 'r') as f:
lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # predict_label

read_label = label_path_new.replace(".txt", ".png")
read_label_path = read_label.replace('test_label', 'test')
print(read_label_path)
img = cv2.imread(str(read_label_path))
h, w = img.shape[:2]
lb[:, 1:] = xywhn2xyxy(lb[:, 1:], w, h, 0, 0) # 反归一化
for _, x in enumerate(lb):
class_label = int(x[0]) # class
cv2.rectangle(img, (round(x[1]), round(x[2])), (round(x[3]), round(x[4])), (0, 255, 0))
with open('GT/' + i, 'a') as fw:
fw.write(str(x[0]) + ' ' + str(x[1]) + ' ' + str(x[2]) + ' ' + str(x[3]) + ' ' + str(
x[4]) + '\n')

2.将yolo结果改成voc坐标:
get_DR.py
import numpy as np
import cv2
import torch
import os

label_path = './predict_label'
image_path = './test'

# 坐标转换，原始存储的是YOLOv5格式
# Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
def xywhn2xyxy(x, w=800, h=800, padw=0, padh=0):
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = w * (x[:, 0] – x[:, 2] / 2) + padw # top left x
y[:, 1] = h * (x[:, 1] – x[:, 3] / 2) + padh # top left y
y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x
y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y
return y

folder = os.path.exists('DR')
if not folder:
os.makedirs('DR')

folderlist = os.listdir(label_path)
for i in folderlist:
label_path_new = os.path.join(label_path, i)
with open(label_path_new, 'r') as f:
lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # predict_label
# print(lb)
read_label = label_path_new.replace(".txt", ".png")
read_label_path = read_label.replace('predict_label', 'test')
img = cv2.imread(str(read_label_path))
h, w = img.shape[:2]
lb[:, 1:] = xywhn2xyxy(lb[:, 1:], w, h, 0, 0) # 反归一化

# 绘图
for _, x in enumerate(lb):
class_label = int(x[0]) # class
cv2.rectangle(img, (round(x[1]), round(x[2])), (round(x[3]), round(x[4])), (0, 255, 0))
cv2.putText(img, str(class_label), (int(x[1]), int(x[2] – 2)), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1,
color=(0, 0, 255), thickness=2)
with open('DR/' + i, 'a') as fw: # 这里需要把confidence放到第二位
# print(fw)
fw.write(str(x[0]) + ' ' + str(x[5]) + ' ' + str(x[1]) + ' ' + str(x[2]) + ' ' + str(x[3]) + ' ' + str(
x[4]) + '\n')
# cv2.imshow('show', img)
# cv2.waitKey(0) # 按键结束
# cv2.destroyAllWindows()

此处参考:https://blog.csdn.net/qq_38412266/article/details/119559719 不过他的两个get代码在最后第两行,'0'写错了,改成str(x[0]),然后 cv2.rectangle要输入为整数.直接用我的就行
四、对某些应yolov5未检测到物体而不生成的txt文件，去除groundTruth中对应文件,然后测试mAP
这边直接用: get_map.py
import glob
import json
import os
import shutil
import operator
import sys
import argparse
import math

import numpy as np

MINOVERLAP = 0.4

parser = argparse.ArgumentParser()
parser.add_argument('-na', '–no-animation', help="no animation is shown.", action="store_true")
parser.add_argument('-np', '–no-plot', help="no plot is shown.", action="store_true")
parser.add_argument('-q', '–quiet', help="minimalistic console output.", action="store_true")
parser.add_argument('-i', '–ignore', nargs='+', type=str, help="ignore a list of classes.")
parser.add_argument('–set-class-iou', nargs='+', type=str, help="set IoU for a specific class.")
args = parser.parse_args()

'''
0,0 ——> x (width)
|
| (Left,Top)
| *_________
| | |
| |
y |_________|
(height) *
(Right,Bottom)
'''

if args.ignore is None:
args.ignore = []

specific_iou_flagged = False
if args.set_class_iou is not None:
specific_iou_flagged = True

os.chdir(os.path.dirname(os.path.abspath(__file__)))

GT_PATH = './GT'
DR_PATH = './DR'
IMG_PATH = './test'
if os.path.exists(IMG_PATH):
for dirpath, dirnames, files in os.walk(IMG_PATH):
if not files:
args.no_animation = True
else:
args.no_animation = True

show_animation = False
if not args.no_animation:
try:
import cv2

show_animation = True
except ImportError:
print("\"opencv-python\" not found, please install to visualize the results.")
args.no_animation = True

draw_plot = False
if not args.no_plot:
try:
import matplotlib.pyplot as plt

draw_plot = True
except ImportError:
print("\"matplotlib\" not found, please install it to get the resulting plots.")
args.no_plot = True

def log_average_miss_rate(precision, fp_cumsum, num_images):
"""
log-average miss rate:
Calculated by averaging miss rates at 9 evenly spaced FPPI points
between 10e-2 and 10e0, in log-space.
output:
lamr | log-average miss rate
mr | miss rate
fppi | false positives per image
references:
[1] Dollar, Piotr, et al. "Pedestrian Detection: An Evaluation of the
State of the Art." Pattern Analysis and Machine Intelligence, IEEE
Transactions on 34.4 (2012): 743 – 761.
"""

if precision.size == 0:
lamr = 0
mr = 1
fppi = 0
return lamr, mr, fppi

fppi = fp_cumsum / float(num_images)
mr = (1 – precision)

fppi_tmp = np.insert(fppi, 0, -1.0)
mr_tmp = np.insert(mr, 0, 1.0)

ref = np.logspace(-2.0, 0.0, num=9)
for i, ref_i in enumerate(ref):
j = np.where(fppi_tmp <= ref_i)[-1][-1]
ref[i] = mr_tmp[j]

lamr = math.exp(np.mean(np.log(np.maximum(1e-10, ref))))

return lamr, mr, fppi

"""
throw error and exit
"""

def error(msg):
print(msg)
sys.exit(0)

"""
check if the number is a float between 0.0 and 1.0
"""

def is_float_between_0_and_1(value):
try:
val = float(value)
if val > 0.0 and val < 1.0:
return True
else:
return False
except ValueError:
return False

"""
Calculate the AP given the recall and precision array
1st) We compute a version of the measured precision/recall curve with
precision monotonically decreasing
2nd) We compute the AP as the area under this curve by numerical integration.
"""

def voc_ap(rec, prec):
"""
— Official matlab code VOC2012—
mrec=[0 ; rec ; 1];
mpre=[0 ; prec ; 0];
for i=numel(mpre)-1:-1:1
mpre(i)=max(mpre(i),mpre(i+1));
end
i=find(mrec(2:end)~=mrec(1:end-1))+1;
ap=sum((mrec(i)-mrec(i-1)).*mpre(i));
"""
rec.insert(0, 0.0) # insert 0.0 at begining of list
rec.append(1.0) # insert 1.0 at end of list
mrec = rec[:]
prec.insert(0, 0.0) # insert 0.0 at begining of list
prec.append(0.0) # insert 0.0 at end of list
mpre = prec[:]
"""
This part makes the precision monotonically decreasing
(goes from the end to the beginning)
matlab: for i=numel(mpre)-1:-1:1
mpre(i)=max(mpre(i),mpre(i+1));
"""
for i in range(len(mpre) – 2, -1, -1):
mpre[i] = max(mpre[i], mpre[i + 1])
"""
This part creates a list of indexes where the recall changes
matlab: i=find(mrec(2:end)~=mrec(1:end-1))+1;
"""
i_list = []
for i in range(1, len(mrec)):
if mrec[i] != mrec[i – 1]:
i_list.append(i) # if it was matlab would be i + 1
"""
The Average Precision (AP) is the area under the curve
(numerical integration)
matlab: ap=sum((mrec(i)-mrec(i-1)).*mpre(i));
"""
ap = 0.0
for i in i_list:
ap += ((mrec[i] – mrec[i – 1]) * mpre[i])
return ap, mrec, mpre

"""
Convert the lines of a file to a list
"""

def file_lines_to_list(path):
# open txt file lines to a list
with open(path) as f:
content = f.readlines()
# remove whitespace characters like `\n` at the end of each line
content = [x.strip() for x in content]
return content

"""
Draws text in image
"""

def draw_text_in_image(img, text, pos, color, line_width):
font = cv2.FONT_HERSHEY_PLAIN
fontScale = 1
lineType = 1
bottomLeftCornerOfText = pos
cv2.putText(img, text,
bottomLeftCornerOfText,
font,
fontScale,
color,
lineType)
text_width, _ = cv2.getTextSize(text, font, fontScale, lineType)[0]
return img, (line_width + text_width)

"""
Plot – adjust axes
"""

def adjust_axes(r, t, fig, axes):
# get text width for re-scaling
bb = t.get_window_extent(renderer=r)
text_width_inches = bb.width / fig.dpi
# get axis width in inches
current_fig_width = fig.get_figwidth()
new_fig_width = current_fig_width + text_width_inches
propotion = new_fig_width / current_fig_width
# get axis limit
x_lim = axes.get_xlim()
axes.set_xlim([x_lim[0], x_lim[1] * propotion])

"""
Draw plot using Matplotlib
"""

def draw_plot_func(dictionary, n_classes, window_title, plot_title, x_label, output_path, to_show, plot_color,
true_p_bar):
# sort the dictionary by decreasing value, into a list of tuples
sorted_dic_by_value = sorted(dictionary.items(), key=operator.itemgetter(1))
# unpacking the list of tuples into two lists
sorted_keys, sorted_values = zip(*sorted_dic_by_value)
#
if true_p_bar != "":
"""
Special case to draw in:
– green -> TP: True Positives (object detected and matches ground-truth)
– red -> FP: False Positives (object detected but does not match ground-truth)
– orange -> FN: False Negatives (object not detected but present in the ground-truth)
"""
fp_sorted = []
tp_sorted = []
for key in sorted_keys:
fp_sorted.append(dictionary[key] – true_p_bar[key])
tp_sorted.append(true_p_bar[key])
plt.barh(range(n_classes), fp_sorted, align='center', color='crimson', label='False Positive')
plt.barh(range(n_classes), tp_sorted, align='center', color='forestgreen', label='True Positive',
left=fp_sorted)
# add legend
plt.legend(loc='lower right')
"""
Write number on side of bar
"""
fig = plt.gcf() # gcf – get current figure
axes = plt.gca()
r = fig.canvas.get_renderer()
for i, val in enumerate(sorted_values):
fp_val = fp_sorted[i]
tp_val = tp_sorted[i]
fp_str_val = " " + str(fp_val)
tp_str_val = fp_str_val + " " + str(tp_val)
# trick to paint multicolor with offset:
# first paint everything and then repaint the first number
t = plt.text(val, i, tp_str_val, color='forestgreen', va='center', fontweight='bold')
plt.text(val, i, fp_str_val, color='crimson', va='center', fontweight='bold')
if i == (len(sorted_values) – 1): # largest bar
adjust_axes(r, t, fig, axes)
else:
plt.barh(range(n_classes), sorted_values, color=plot_color)
"""
Write number on side of bar
"""
fig = plt.gcf() # gcf – get current figure
axes = plt.gca()
r = fig.canvas.get_renderer()
for i, val in enumerate(sorted_values):
str_val = " " + str(val) # add a space before
if val < 1.0:
str_val = " {0:.2f}".format(val)
t = plt.text(val, i, str_val, color=plot_color, va='center', fontweight='bold')
# re-set axes to show number inside the figure
if i == (len(sorted_values) – 1): # largest bar
adjust_axes(r, t, fig, axes)
# set window title
fig.canvas.set_window_title(window_title)
# write classes in y axis
tick_font_size = 12
plt.yticks(range(n_classes), sorted_keys, fontsize=tick_font_size)
"""
Re-scale height accordingly
"""
init_height = fig.get_figheight()
# comput the matrix height in points and inches
dpi = fig.dpi
height_pt = n_classes * (tick_font_size * 1.4) # 1.4 (some spacing)
height_in = height_pt / dpi
# compute the required figure height
top_margin = 0.15 # in percentage of the figure height
bottom_margin = 0.05 # in percentage of the figure height
figure_height = height_in / (1 – top_margin – bottom_margin)
# set new height
if figure_height > init_height:
fig.set_figheight(figure_height)

# set plot title
plt.title(plot_title, fontsize=14)
# set axis titles
# plt.xlabel('classes')
plt.xlabel(x_label, fontsize='large')
# adjust size of window
fig.tight_layout()
# save the plot
fig.savefig(output_path)
# show image
if to_show:
plt.show()
# close the plot
plt.close()

"""
Create a ".temp_files/" and "results/" directory
"""
TEMP_FILES_PATH = ".temp_files"
if not os.path.exists(TEMP_FILES_PATH): # if it doesn't exist already
os.makedirs(TEMP_FILES_PATH)
results_files_path = "results"
if os.path.exists(results_files_path): # if it exist already
# reset the results directory
shutil.rmtree(results_files_path)

os.makedirs(results_files_path)
if draw_plot:
os.makedirs(os.path.join(results_files_path, "AP"))
os.makedirs(os.path.join(results_files_path, "F1"))
os.makedirs(os.path.join(results_files_path, "Recall"))
os.makedirs(os.path.join(results_files_path, "Precision"))
if show_animation:
os.makedirs(os.path.join(results_files_path, "images", "detections_one_by_one"))

"""
ground-truth
Load each of the ground-truth files into a temporary ".json" file.
Create a list of all the class names present in the ground-truth (gt_classes).
"""
# get a list with the ground-truth files
ground_truth_files_list = glob.glob(GT_PATH + '/*.txt')
if len(ground_truth_files_list) == 0:
error("Error: No ground-truth files found!")
ground_truth_files_list.sort()
# dictionary with counter per class
gt_counter_per_class = {}
counter_images_per_class = {}

for txt_file in ground_truth_files_list:
# print(txt_file)
file_id = txt_file.split(".txt", 1)[0]
file_id = os.path.basename(os.path.normpath(file_id))
# check if there is a correspondent detection-results file
temp_path = os.path.join(DR_PATH, (file_id + ".txt"))
if not os.path.exists(temp_path):
error_msg = "Error. File not found: {}\n".format(temp_path)
error_msg += "(You can avoid this error message by running extra/intersect-gt-and-dr.py)"
error(error_msg)
lines_list = file_lines_to_list(txt_file)
# create ground-truth dictionary
bounding_boxes = []
is_difficult = False
already_seen_classes = []
for line in lines_list:
try:
if "difficult" in line:
class_name, left, top, right, bottom, _difficult = line.split()
is_difficult = True
else:
class_name, left, top, right, bottom = line.split()

except:
if "difficult" in line:
line_split = line.split()
_difficult = line_split[-1]
bottom = line_split[-2]
right = line_split[-3]
top = line_split[-4]
left = line_split[-5]
class_name = ""
for name in line_split[:-5]:
class_name += name + " "
class_name = class_name[:-1]
is_difficult = True
else:
line_split = line.split()
bottom = line_split[-1]
right = line_split[-2]
top = line_split[-3]
left = line_split[-4]
class_name = ""
for name in line_split[:-4]:
class_name += name + " "
class_name = class_name[:-1]
if class_name in args.ignore:
continue
bbox = left + " " + top + " " + right + " " + bottom
if is_difficult:
bounding_boxes.append({"class_name": class_name, "bbox": bbox, "used": False, "difficult": True})
is_difficult = False
else:
bounding_boxes.append({"class_name": class_name, "bbox": bbox, "used": False})
if class_name in gt_counter_per_class:
gt_counter_per_class[class_name] += 1
else:
gt_counter_per_class[class_name] = 1

if class_name not in already_seen_classes:
if class_name in counter_images_per_class:
counter_images_per_class[class_name] += 1
else:
counter_images_per_class[class_name] = 1
already_seen_classes.append(class_name)

with open(TEMP_FILES_PATH + "/" + file_id + "_ground_truth.json", 'w') as outfile:
json.dump(bounding_boxes, outfile)

gt_classes = list(gt_counter_per_class.keys())
gt_classes = sorted(gt_classes)
n_classes = len(gt_classes)

"""
Check format of the flag –set-class-iou (if used)
e.g. check if class exists
"""
if specific_iou_flagged:
n_args = len(args.set_class_iou)
error_msg = \
'\n –set-class-iou [class_1] [IoU_1] [class_2] [IoU_2] […]'
if n_args % 2 != 0:
error('Error, missing arguments. Flag usage:' + error_msg)
# [class_1] [IoU_1] [class_2] [IoU_2]
# specific_iou_classes = ['class_1', 'class_2']
specific_iou_classes = args.set_class_iou[::2] # even
# iou_list = ['IoU_1', 'IoU_2']
iou_list = args.set_class_iou[1::2] # odd
if len(specific_iou_classes) != len(iou_list):
error('Error, missing arguments. Flag usage:' + error_msg)
for tmp_class in specific_iou_classes:
if tmp_class not in gt_classes:
error('Error, unknown class \"' + tmp_class + '\". Flag usage:' + error_msg)
for num in iou_list:
if not is_float_between_0_and_1(num):
error('Error, IoU must be between 0.0 and 1.0. Flag usage:' + error_msg)

"""
detection-results
Load each of the detection-results files into a temporary ".json" file.
"""
dr_files_list = glob.glob(DR_PATH + '/*.txt')
dr_files_list.sort()

for class_index, class_name in enumerate(gt_classes):
bounding_boxes = []
for txt_file in dr_files_list:
file_id = txt_file.split(".txt", 1)[0]
file_id = os.path.basename(os.path.normpath(file_id))
temp_path = os.path.join(GT_PATH, (file_id + ".txt"))
if class_index == 0:
if not os.path.exists(temp_path):
error_msg = "Error. File not found: {}\n".format(temp_path)
error_msg += "(You can avoid this error message by running extra/intersect-gt-and-dr.py)"
error(error_msg)
lines = file_lines_to_list(txt_file)
for line in lines:
try:
tmp_class_name, confidence, left, top, right, bottom = line.split()
except:
line_split = line.split()
bottom = line_split[-1]
right = line_split[-2]
top = line_split[-3]
left = line_split[-4]
confidence = line_split[-5]
tmp_class_name = ""
for name in line_split[:-5]:
tmp_class_name += name + " "
tmp_class_name = tmp_class_name[:-1]

if tmp_class_name == class_name:
bbox = left + " " + top + " " + right + " " + bottom
bounding_boxes.append({"confidence": confidence, "file_id": file_id, "bbox": bbox})

bounding_boxes.sort(key=lambda x: float(x['confidence']), reverse=True)
with open(TEMP_FILES_PATH + "/" + class_name + "_dr.json", 'w') as outfile:
json.dump(bounding_boxes, outfile)

"""
Calculate the AP for each class
"""
sum_AP = 0.0
ap_dictionary = {}
lamr_dictionary = {}
with open(results_files_path + "/results.txt", 'w') as results_file:
results_file.write("# AP and precision/recall per class\n")
count_true_positives = {}

for class_index, class_name in enumerate(gt_classes):
count_true_positives[class_name] = 0
"""
Load detection-results of that class
"""
dr_file = TEMP_FILES_PATH + "/" + class_name + "_dr.json"
dr_data = json.load(open(dr_file))
"""
Assign detection-results to ground-truth objects
"""
nd = len(dr_data)
tp = [0] * nd
fp = [0] * nd
score = [0] * nd
score05_idx = 0
for idx, detection in enumerate(dr_data):
file_id = detection["file_id"]
score[idx] = float(detection["confidence"])
if score[idx] > 0.5:
score05_idx = idx

if show_animation:
ground_truth_img = glob.glob1(IMG_PATH, file_id + ".*")
if len(ground_truth_img) == 0:
error("Error. Image not found with id: " + file_id)
elif len(ground_truth_img) > 1:
error("Error. Multiple image with id: " + file_id)
else:
img = cv2.imread(IMG_PATH + "/" + ground_truth_img[0])
img_cumulative_path = results_files_path + "/images/" + ground_truth_img[0]
if os.path.isfile(img_cumulative_path):
img_cumulative = cv2.imread(img_cumulative_path)
else:
img_cumulative = img.copy()
bottom_border = 60
BLACK = [0, 0, 0]
img = cv2.copyMakeBorder(img, 0, bottom_border, 0, 0, cv2.BORDER_CONSTANT, value=BLACK)

gt_file = TEMP_FILES_PATH + "/" + file_id + "_ground_truth.json"
ground_truth_data = json.load(open(gt_file))
ovmax = -1
gt_match = -1
bb = [float(x) for x in detection["bbox"].split()]
for obj in ground_truth_data:
if obj["class_name"] == class_name:
bbgt = [float(x) for x in obj["bbox"].split()]
bi = [max(bb[0], bbgt[0]), max(bb[1], bbgt[1]), min(bb[2], bbgt[2]), min(bb[3], bbgt[3])]
iw = bi[2] – bi[0] + 1
ih = bi[3] – bi[1] + 1
if iw > 0 and ih > 0:
# compute overlap (IoU) = area of intersection / area of union
ua = (bb[2] – bb[0] + 1) * (bb[3] – bb[1] + 1) + (bbgt[2] – bbgt[0]
+ 1) * (bbgt[3] – bbgt[1] + 1) – iw * ih
ov = iw * ih / ua
if ov > ovmax:
ovmax = ov
gt_match = obj

if show_animation:
status = "NO MATCH FOUND!"
min_overlap = MINOVERLAP
if specific_iou_flagged:
if class_name in specific_iou_classes:
index = specific_iou_classes.index(class_name)
min_overlap = float(iou_list[index])
if ovmax >= min_overlap:
if "difficult" not in gt_match:
if not bool(gt_match["used"]):
tp[idx] = 1
gt_match["used"] = True
count_true_positives[class_name] += 1
with open(gt_file, 'w') as f:
f.write(json.dumps(ground_truth_data))
if show_animation:
status = "MATCH!"
else:
fp[idx] = 1
if show_animation:
status = "REPEATED MATCH!"
else:
fp[idx] = 1
if ovmax > 0:
status = "INSUFFICIENT OVERLAP"

"""
Draw image to show animation
"""
if show_animation:
height, widht = img.shape[:2]
# colors (OpenCV works with BGR)
white = (255, 255, 255)
light_blue = (255, 200, 100)
green = (0, 255, 0)
light_red = (30, 30, 255)
# 1st line
margin = 10
v_pos = int(height – margin – (bottom_border / 2.0))
text = "Image: " + ground_truth_img[0] + " "
img, line_width = draw_text_in_image(img, text, (margin, v_pos), white, 0)
text = "Class [" + str(class_index) + "/" + str(n_classes) + "]: " + class_name + " "
img, line_width = draw_text_in_image(img, text, (margin + line_width, v_pos), light_blue, line_width)
if ovmax != -1:
color = light_red
if status == "INSUFFICIENT OVERLAP":
text = "IoU: {0:.2f}% ".format(ovmax * 100) + "< {0:.2f}% ".format(min_overlap * 100)
else:
text = "IoU: {0:.2f}% ".format(ovmax * 100) + ">= {0:.2f}% ".format(min_overlap * 100)
color = green
img, _ = draw_text_in_image(img, text, (margin + line_width, v_pos), color, line_width)
# 2nd line
v_pos += int(bottom_border / 2.0)
rank_pos = str(idx + 1) # rank position (idx starts at 0)
text = "Detection #rank: " + rank_pos + " confidence: {0:.2f}% ".format(
float(detection["confidence"]) * 100)
img, line_width = draw_text_in_image(img, text, (margin, v_pos), white, 0)
color = light_red
if status == "MATCH!":
color = green
text = "Result: " + status + " "
img, line_width = draw_text_in_image(img, text, (margin + line_width, v_pos), color, line_width)

font = cv2.FONT_HERSHEY_SIMPLEX
if ovmax > 0: # if there is intersections between the bounding-boxes
bbgt = [int(round(float(x))) for x in gt_match["bbox"].split()]
cv2.rectangle(img, (bbgt[0], bbgt[1]), (bbgt[2], bbgt[3]), light_blue, 2)
cv2.rectangle(img_cumulative, (bbgt[0], bbgt[1]), (bbgt[2], bbgt[3]), light_blue, 2)
cv2.putText(img_cumulative, class_name, (bbgt[0], bbgt[1] – 5), font, 0.6, light_blue, 1,
cv2.LINE_AA)
bb = [int(i) for i in bb]
cv2.rectangle(img, (bb[0], bb[1]), (bb[2], bb[3]), color, 2)
cv2.rectangle(img_cumulative, (bb[0], bb[1]), (bb[2], bb[3]), color, 2)
cv2.putText(img_cumulative, class_name, (bb[0], bb[1] – 5), font, 0.6, color, 1, cv2.LINE_AA)
# show image
cv2.imshow("Animation", img)
cv2.waitKey(20) # show for 20 ms
# save image to results
output_img_path = results_files_path + "/images/detections_one_by_one/" + class_name + "_detection" + str(
idx) + ".jpg"
cv2.imwrite(output_img_path, img)
# save the image with all the objects drawn to it
cv2.imwrite(img_cumulative_path, img_cumulative)

cumsum = 0
for idx, val in enumerate(fp):
fp[idx] += cumsum
cumsum += val

cumsum = 0
for idx, val in enumerate(tp):
tp[idx] += cumsum
cumsum += val

rec = tp[:]
for idx, val in enumerate(tp):
rec[idx] = float(tp[idx]) / np.maximum(gt_counter_per_class[class_name], 1)

prec = tp[:]
for idx, val in enumerate(tp):
prec[idx] = float(tp[idx]) / np.maximum((fp[idx] + tp[idx]), 1)

ap, mrec, mprec = voc_ap(rec[:], prec[:])
F1 = np.array(rec) * np.array(prec) * 2 / np.where((np.array(prec) + np.array(rec)) == 0, 1,
(np.array(prec) + np.array(rec)))

sum_AP += ap
text = "{0:.2f}%".format(ap * 100) + " = " + class_name + " AP " # class_name + " AP = {0:.2f}%".format(ap*100)

if len(prec) > 0:
F1_text = "{0:.2f}".format(F1[score05_idx]) + " = " + class_name + " F1 "
Recall_text = "{0:.2f}%".format(rec[score05_idx] * 100) + " = " + class_name + " Recall "
Precision_text = "{0:.2f}%".format(prec[score05_idx] * 100) + " = " + class_name + " Precision "
else:
F1_text = "0.00" + " = " + class_name + " F1 "
Recall_text = "0.00%" + " = " + class_name + " Recall "
Precision_text = "0.00%" + " = " + class_name + " Precision "

rounded_prec = ['%.2f' % elem for elem in prec]
rounded_rec = ['%.2f' % elem for elem in rec]
results_file.write(text + "\n Precision: " + str(rounded_prec) + "\n Recall :" + str(rounded_rec) + "\n\n")
if not args.quiet:
if len(prec) > 0:
print(text + "\t||\tscore_threhold=0.5 : " + "F1=" + "{0:.2f}".format(F1[score05_idx]) \
+ " ; Recall=" + "{0:.2f}%".format(rec[score05_idx] * 100) + " ; Precision=" + "{0:.2f}%".format(
prec[score05_idx] * 100))
else:
print(text + "\t||\tscore_threhold=0.5 : F1=0.00% ; Recall=0.00% ; Precision=0.00%")
ap_dictionary[class_name] = ap

n_images = counter_images_per_class[class_name]
lamr, mr, fppi = log_average_miss_rate(np.array(rec), np.array(fp), n_images)
lamr_dictionary[class_name] = lamr

"""
Draw plot
"""
if draw_plot:
plt.plot(rec, prec, '-o')
area_under_curve_x = mrec[:-1] + [mrec[-2]] + [mrec[-1]]
area_under_curve_y = mprec[:-1] + [0.0] + [mprec[-1]]
plt.fill_between(area_under_curve_x, 0, area_under_curve_y, alpha=0.2, edgecolor='r')

fig = plt.gcf()
fig.canvas.set_window_title('AP ' + class_name)

plt.title('class: ' + text)
plt.xlabel('Recall')
plt.ylabel('Precision')
axes = plt.gca()
axes.set_xlim([0.0, 1.0])
axes.set_ylim([0.0, 1.05])
fig.savefig(results_files_path + "/AP/" + class_name + ".png")
plt.cla()

plt.plot(score, F1, "-", color='orangered')
plt.title('class: ' + F1_text + "\nscore_threhold=0.5")
plt.xlabel('Score_Threhold')
plt.ylabel('F1')
axes = plt.gca()
axes.set_xlim([0.0, 1.0])
axes.set_ylim([0.0, 1.05])
fig.savefig(results_files_path + "/F1/" + class_name + ".png")
plt.cla()

plt.plot(score, rec, "-H", color='gold')
plt.title('class: ' + Recall_text + "\nscore_threhold=0.5")
plt.xlabel('Score_Threhold')
plt.ylabel('Recall')
axes = plt.gca()
axes.set_xlim([0.0, 1.0])
axes.set_ylim([0.0, 1.05])
fig.savefig(results_files_path + "/Recall/" + class_name + ".png")
plt.cla()

plt.plot(score, prec, "-s", color='palevioletred')
plt.title('class: ' + Precision_text + "\nscore_threhold=0.5")
plt.xlabel('Score_Threhold')
plt.ylabel('Precision')
axes = plt.gca()
axes.set_xlim([0.0, 1.0])
axes.set_ylim([0.0, 1.05])
fig.savefig(results_files_path + "/Precision/" + class_name + ".png")
plt.cla()

if show_animation:
cv2.destroyAllWindows()

results_file.write("\n# mAP of all classes\n")
mAP = sum_AP / n_classes
text = "mAP = {0:.2f}%".format(mAP * 100)
results_file.write(text + "\n")
print(text)

# remove the temp_files directory
shutil.rmtree(TEMP_FILES_PATH)

"""
Count total of detection-results
"""
# iterate through all the files
det_counter_per_class = {}
for txt_file in dr_files_list:
# get lines to list
lines_list = file_lines_to_list(txt_file)
for line in lines_list:
class_name = line.split()[0]
# check if class is in the ignore list, if yes skip
if class_name in args.ignore:
continue
# count that object
if class_name in det_counter_per_class:
det_counter_per_class[class_name] += 1
else:
# if class didn't exist yet
det_counter_per_class[class_name] = 1
# print(det_counter_per_class)
dr_classes = list(det_counter_per_class.keys())

"""
Plot the total number of occurences of each class in the ground-truth
"""
if draw_plot:
window_title = "ground-truth-info"
plot_title = "ground-truth\n"
plot_title += "(" + str(len(ground_truth_files_list)) + " files and " + str(n_classes) + " classes)"
x_label = "Number of objects per class"
output_path = results_files_path + "/ground-truth-info.png"
to_show = False
plot_color = 'forestgreen'
draw_plot_func(
gt_counter_per_class,
n_classes,
window_title,
plot_title,
x_label,
output_path,
to_show,
plot_color,
'',
)

"""
Write number of ground-truth objects per class to results.txt
"""
with open(results_files_path + "/results.txt", 'a') as results_file:
results_file.write("\n# Number of ground-truth objects per class\n")
for class_name in sorted(gt_counter_per_class):
results_file.write(class_name + ": " + str(gt_counter_per_class[class_name]) + "\n")

"""
Finish counting true positives
"""
for class_name in dr_classes:
# if class exists in detection-result but not in ground-truth then there are no true positives in that class
if class_name not in gt_classes:
count_true_positives[class_name] = 0
# print(count_true_positives)

"""
Plot the total number of occurences of each class in the "detection-results" folder
"""
if draw_plot:
window_title = "detection-results-info"
# Plot title
plot_title = "detection-results\n"
plot_title += "(" + str(len(dr_files_list)) + " files and "
count_non_zero_values_in_dictionary = sum(int(x) > 0 for x in list(det_counter_per_class.values()))
plot_title += str(count_non_zero_values_in_dictionary) + " detected classes)"
# end Plot title
x_label = "Number of objects per class"
output_path = results_files_path + "/detection-results-info.png"
to_show = False
plot_color = 'forestgreen'
true_p_bar = count_true_positives
draw_plot_func(
det_counter_per_class,
len(det_counter_per_class),
window_title,
plot_title,
x_label,
output_path,
to_show,
plot_color,
true_p_bar
)

"""
Write number of detected objects per class to results.txt
"""
with open(results_files_path + "/results.txt", 'a') as results_file:
results_file.write("\n# Number of detected objects per class\n")
for class_name in sorted(dr_classes):
n_det = det_counter_per_class[class_name]
text = class_name + ": " + str(n_det)
text += " (tp:" + str(count_true_positives[class_name]) + ""
text += ", fp:" + str(n_det – count_true_positives[class_name]) + ")\n"
results_file.write(text)

"""
Draw log-average miss rate plot (Show lamr of all classes in decreasing order)
"""
if draw_plot:
window_title = "lamr"
plot_title = "log-average miss rate"
x_label = "log-average miss rate"
output_path = results_files_path + "/lamr.png"
to_show = False
plot_color = 'royalblue'
draw_plot_func(
lamr_dictionary,
n_classes,
window_title,
plot_title,
x_label,
output_path,
to_show,
plot_color,
""
)

"""
Draw mAP plot (Show AP's of all classes in decreasing order)
"""
if draw_plot:
window_title = "mAP"
plot_title = "mAP = {0:.2f}%".format(mAP * 100)
x_label = "Average Precision"
output_path = results_files_path + "/mAP.png"
to_show = True
plot_color = 'royalblue'
draw_plot_func(
ap_dictionary,
n_classes,
window_title,
plot_title,
x_label,
output_path,
to_show,
plot_color,
""
)

可能代码会报错,缺少了intersect_gt_and_dr.py,这是因为我们上面说的,有些图检测不出目标,就不生成txt文件,现在匹配不了. 用下面代码:(它就是intersect_gt_and_dr.py),运行完之后在跑上面的get_map.py
import sys
import os
import glob

## This script ensures same number of files in ground-truth and detection-results folder.
## When you encounter file not found error, it's usually because you have
## mismatched numbers of ground-truth and detection-results files.
## You can use this script to move ground-truth and detection-results files that are
## not in the intersection into a backup folder (backup_no_matches_found).
## This will retain only files that have the same name in both folders.

# make sure that the cwd() in the beginning is the location of the python script (so that every path makes sense)

GT_PATH = 'F:\shiyanshi\yolov5-master\GT'
DR_PATH = 'F:\shiyanshi\yolov5-master\DR'

backup_folder = 'backup_no_matches_found' # must end without slash

os.chdir(GT_PATH)
gt_files = glob.glob('*.txt')
if len(gt_files) == 0:
print("Error: no .txt files found in", GT_PATH)
sys.exit()
os.chdir(DR_PATH)
dr_files = glob.glob('*.txt')
if len(dr_files) == 0:
print("Error: no .txt files found in", DR_PATH)
sys.exit()

gt_files = set(gt_files)
dr_files = set(dr_files)
print('total ground-truth files:', len(gt_files))
print('total detection-results files:', len(dr_files))
print()

gt_backup = gt_files – dr_files
dr_backup = dr_files – gt_files

def backup(src_folder, backup_files, backup_folder):
# non-intersection files (txt format) will be moved to a backup folder
if not backup_files:
print('No backup required for', src_folder)
return
os.chdir(src_folder)
## create the backup dir if it doesn't exist already
if not os.path.exists(backup_folder):
os.makedirs(backup_folder)
for file in backup_files:
os.rename(file, backup_folder + '/' + file)

backup(GT_PATH, gt_backup, backup_folder)
backup(DR_PATH, dr_backup, backup_folder)
if gt_backup:
print('total ground-truth backup files:', len(gt_backup))
if dr_backup:
print('total detection-results backup files:', len(dr_backup))

intersection = gt_files & dr_files
print('total intersected files:', len(intersection))
print("Intersection completed!")

以上代码参考:https://blog.csdn.net/qq_38412266/article/details/119559719来源：qq_40840829