记yolov3模型map值计算
文件准备
计算代码
计算代码地址: mAP-master
准备数据集
准备若干用于计算map值的数据集
目录结构(供参考)
计算map
写入文件名
首先需要在VOC2007\ImageSets\Main目录下的test.txt文件中写入用于计算的数据集文件名
运行如下代码。(voc2ssd.py)
import os
import random
xmlfilepath=r'VOC2007\Annotations'#xml文件所在地址
saveBasePath=r"VOC2007\ImageSets\Main"#test.txt文件所在地址
train_percent=1.0
trainval_percent=0#0表示以上目录中所有数据集都用于计算map，可自行修改
temp_xml = os.listdir(xmlfilepath)
total_xml = []
for xml in temp_xml:
if xml.endswith(".xml"):
total_xml.append(xml)
num=len(total_xml)
list=range(num)
tv=int(num*trainval_percent)
tr=int(tv*train_percent)
trainval= random.sample(list,tv)
train=random.sample(trainval,tr)
print("train and val size",tv)
print("traub suze",tr)
ftrainval = open(os.path.join(saveBasePath,'trainval.txt'), 'w')
ftest = open(os.path.join(saveBasePath,'test.txt'), 'w')
ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w')
fval = open(os.path.join(saveBasePath,'val.txt'), 'w')
for i in list:
name=total_xml[i][:-4]+'\n'
if i in trainval:
ftrainval.write(name)
if i in train:
ftrain.write(name)
else:
fval.write(name)
else:
ftest.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest .close()
生成真实值文件
接下来我们需要准备一个保存真实值的文件夹(mAP-master\input\ground-truth，删除原有的)
运行如下代码(yolo_true.py)
import sys
import os
import glob
import xml.etree.ElementTree as ET
image_ids = open('VOC2007/ImageSets/Main/test.txt').read().strip().split()#之前生成的test.txt所在地址
if not os.path.exists("./input"):
os.makedirs("./input")
if not os.path.exists("./input/ground-truth"):
os.makedirs("./input/ground-truth")
for image_id in image_ids:
with open("mAP-master/input/ground-truth/"+image_id+".txt", "a") as new_f:#用于存储真实值文件所用的文件目录
root = ET.parse("VOCdevkit/VOC2007/Annotations/"+image_id+'.xml').getroot()#数据集中xml文件所在文件夹
for obj in root.findall('object'):
obj_name = obj.find('name').text
bndbox = obj.find('bndbox')
left = bndbox.find('xmin').text
top = bndbox.find('ymin').text
right = bndbox.find('xmax').text
bottom = bndbox.find('ymax').text
new_f.write("%s %s %s %s %s\n" % (obj_name, left, top, right, bottom))
print("Conversion completed!")
拷贝数据集图片(可选)
将用于计算的数据集图片拷贝到mAP-master\input\images-optional目录下，请手动删除原有图片，在计算时会显示预测情况，嫌麻烦可忽略此步骤。
生成预测值文件
修改原yolo.py文件，将预测结果保存到mAP-master\input\detection-results文件夹下(请手动删除原有的)
# -*- coding: utf-8 -*-
"""
Class definition of YOLO_v3 style detection model on image and video
"""
import colorsys
import os
import sys
from timeit import default_timer as timer
import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw
from yolo3.model import yolo_eval, yolo_body, tiny_yolo_body
from yolo3.utils import letterbox_image
import os
from keras.utils import multi_gpu_model
class YOLO(object):
_defaults = {
"model_path": 'logs/000/ep450.h5', ##训练好的模型的路径
"anchors_path": 'model_data/yolo_anchors.txt',
"classes_path": 'model_data/voc_classes.txt',
"score" : 0.3,
"iou" : 0.45,
"model_image_size" : (416, 416),
"gpu_num" : 0
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
def __init__(self, **kwargs):
self.__dict__.update(self._defaults) # set up default values
self.__dict__.update(kwargs) # and update with user overrides
self.class_names = self._get_class()
self.anchors = self._get_anchors()
self.sess = K.get_session()
self.boxes, self.scores, self.classes = self.generate()
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def _get_anchors(self):
anchors_path = os.path.expanduser(self.anchors_path)
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
return np.array(anchors).reshape(-1, 2)
def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
# Load model, or construct model and load weights.
num_anchors = len(self.anchors)
num_classes = len(self.class_names)
is_tiny_version = num_anchors==6 # default setting
try:
self.yolo_model = load_model(model_path, compile=False)
except:
self.yolo_model = tiny_yolo_body(Input(shape=(None,None,3)), num_anchors//2, num_classes) \
if is_tiny_version else yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes)
self.yolo_model.load_weights(self.model_path) # make sure model, anchors and classes match
else:
assert self.yolo_model.layers[-1].output_shape[-1] == \
num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
'Mismatch between model and given anchor and class sizes'
print('{} model, anchors, and classes loaded.'.format(model_path))
# Generate colors for drawing bounding boxes.
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
np.random.seed(10101) # Fixed seed for consistent colors across runs.
np.random.shuffle(self.colors) # Shuffle colors to decorrelate adjacent classes.
np.random.seed(None) # Reset seed to default.
# Generate output tensor targets for filtered bounding boxes.
self.input_image_shape = K.placeholder(shape=(2, ))
if self.gpu_num>=2:
self.yolo_model = multi_gpu_model(self.yolo_model, gpus=self.gpu_num)
boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
len(self.class_names), self.input_image_shape,
score_threshold=self.score, iou_threshold=self.iou)
return boxes, scores, classes
def detect_image(self, image):
start = timer()
if self.model_image_size != (None, None):
assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
boxed_image = letterbox_image(image, tuple(reversed(self.model_image_size)))
else:
new_image_size = (image.width - (image.width % 32),
image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
print(image_data.shape)
image_data /= 255.
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={
self.yolo_model.input: image_data,
self.input_image_shape: [image.size[1], image.size[0]],
K.learning_phase(): 0
})
print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
thickness = (image.size[0] + image.size[1]) // 300
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
top, left, bottom, right = box
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
print(label, (left, top), (right, bottom))
new_f.write("%s %s %s %s %s\n" % (label, left, top, right, bottom))
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
draw.rectangle(
[left + i, top + i, right - i, bottom - i],
outline=self.colors[c])
draw.rectangle(
[tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[c])
draw.text(text_origin, label, fill=(0, 0, 0), font=font)
del draw
end = timer()
print(end - start)
return image
def close_session(self):
self.sess.close()
if __name__ == '__main__':
yolo=YOLO()
dirname="../VOC2007/JPEGImages/" ##该目录为测试照片的存储路径，每次测试照片的数量可以自己设定
path=os.path.join(dirname)
pic_list=os.listdir(path)
count=0
for filename in pic_list:
tmp_file=pic_list[count]
new_f=open("../mAP-master/input/detection-results/"+tmp_file.replace(".jpg", ".txt"), "a") #预测坐标生成txt文件保存的路径
abs_path=path+pic_list[count]
image = Image.open(abs_path)
r_image = yolo.detect_image(image)
count=count+1
print(count)
yolo.close_session()
计算map值
运行mAP-master下的main.py文件
查看结果
后记
深度学习初学者，抛砖引玉。