keras-YOLOv3检测中遇到的问题！（检测视频时效果不好的坑）
1.YOLOv3对图片的检测：
下面是一个可以批量检测图片的代码，只需修改一下图片路径。最终会将检测结果保存在你设置image_save_path路径下。
# -*- coding: utf-8 -*-
"""
Class definition of YOLO_v3 style detection model on image and video
"""
import colorsys
import os
from timeit import default_timer as timer
import time
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
from keras.utils import multi_gpu_model
path = './test/' #待检测图片的位置
#创建创建一个存储检测结果的dir
result_path = './result'
if not os.path.exists(result_path):
os.makedirs(result_path)
#result如果之前存放的有文件，全部清除
for i in os.listdir(result_path):
path_file = os.path.join(result_path,i)
if os.path.isfile(path_file):
os.remove(path_file)
#创建一个记录检测结果的文件
txt_path =result_path + '/result.txt'
file = open(txt_path,'w')
class YOLO(object):
_defaults = {
"model_path": 'model_data/trained_weights_stage_1.h5',
"anchors_path": 'model_data/tiny_yolo_anchors.txt',
"classes_path": 'model_data/voc_classes.txt',
"score" : 0.3,
"iou" : 0.45,
"model_image_size" : (416, 416),
"gpu_num" : 1,
}
@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() # 开始计时
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) #打印图片的尺寸
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')) # 提示用于找到几个bbox
font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
size=np.floor(2e-2 * image.size[1] + 0.2).astype('int32'))
thickness = (image.size[0] + image.size[1]) // 500
# 保存框检测出的框的个数
file.write('find '+str(len(out_boxes))+' target(s) \n')
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'))
# 写入检测位置
file.write(predicted_class+' score: '+str(score)+' \nlocation: top: '+str(top)+'、 bottom: '+str(bottom)+'、 left: '+str(left)+'、 right: '+str(right)+'\n')
print(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])
# My kingdom for a good redistributable image drawing library.
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('time consume:%.3f s '%(end - start))
return image
def close_session(self):
self.sess.close()
#图片检测
if __name__ == '__main__':
t1 = time.time()
yolo = YOLO()
path_list = os.listdir(path)
for filename in path_list:
image_path = path+'/'+filename
portion = os.path.split(image_path)
file.write(portion[1]+' detect_result：\n')
image = Image.open(image_path)
r_image = yolo.detect_image(image)
file.write('\n')
#r_image.show() 显示检测结果
image_save_path = './result/result_'+portion[1]
print('detect result save to....:'+image_save_path)
r_image.save(image_save_path)
time_sum = time.time() - t1
file.write('time sum: '+str(time_sum)+'s')
print('time sum:',time_sum)
file.close()
yolo.close_session()
这是一个检测单张图片的代码。
def detect_img_for_test():
yolo = YOLO()
image = Image.open('004.jpg') #图片的路劲，在根目录下 可直接键入图片名称
r_image = yolo.detect_image(image)
yolo.close_session()
r_image.show()
if __name__ == '__main__':
detect_img_for_test()
2.YOLOv3对视频的检测：
对视频的检测只需在原码自带的yolo_video.py文件中将路径换成自己的视频路径即可：
#在源码中你会找到如下代码，修改路径即可。
parser.add_argument(
"--input", nargs='?', type=str,required=False,default='192.168.0.5.avi',
help = "Video input path"
)
重点来了!!
我们自己训练或借用别人训练好的模型在检测图片的时候，效果会很好。但是在检测视频的时效果很差。作者在仔细阅读代码后，发现在使用yolo_video.py检测视频的时候，步骤是：截帧-检测（类似图片检测）-拼接帧。问题来了，将每个步骤的结果输出，你会发现虽然最后的输出结果没有变化，但是在截帧之后的图片和原图是不一样的（编码格式造成的）。所以导致我们的检测效果不好。
调用vid.read()获取的帧，是BGR的格式，我们只需将其转换成RGB进行检测，在输出的时候在转回BGR拼接即可。
def detect_video(yolo, video_path, output_path="./result"):
import cv2
vid = cv2.VideoCapture(video_path)
if not vid.isOpened():
raise IOError("Couldn't open webcam or video")
video_FourCC = int(vid.get(cv2.CAP_PROP_FOURCC))
video_fps = vid.get(cv2.CAP_PROP_FPS)
video_size = (int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)))
isOutput = True if output_path != "" else False
if isOutput:
print("!!! TYPE:", type(output_path), type(video_FourCC), type(video_fps), type(video_size))
out = cv2.VideoWriter(output_path, video_FourCC, video_fps, video_size)
accum_time = 0
curr_fps = 0
fps = "FPS: ??"
prev_time = timer()
while True:
return_value, frame = vid.read()
#cv2.imwrite("image.jpg", frame)
#image.show()
#------------------
image = Image.fromarray(cv2.cvtColor(frame,cv2.COLOR_BGR2RGB)) #！！！！！！！！！
image = yolo.detect_image(image)
#----------------------------------
#result = np.asarray(image)
#----------------------------------
result = cv2.cvtColor(np.asarray(image), cv2.COLOR_RGB2BGR) #！！！！！！！！！！
#----------------------------------
curr_time = timer()
exec_time = curr_time - prev_time
prev_time = curr_time
accum_time = accum_time + exec_time
curr_fps = curr_fps + 1
if accum_time > 1:
accum_time = accum_time - 1
fps = "FPS: " + str(curr_fps)
curr_fps = 0
cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=0.50, color=(255, 0, 0), thickness=2)
cv2.namedWindow("result", cv2.WINDOW_NORMAL)
cv2.imshow("result", result)
if isOutput:
out.write(result)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
yolo.close_session()