def inference():
net = dnn.readNetFromCaffe(args.caffe_prototxt_path, args.caffe_model_path)
input_size = [int(v.strip()) for v in args.input_size.split(",")]
witdh = input_size[0]
height = input_size[1]
priors = define_img_size(input_size)
result_path = args.results_path
imgs_path = args.imgs_path
if not os.path.exists(result_path):
os.makedirs(result_path)
listdir = os.listdir(imgs_path)
for file_path in listdir:
img_path = os.path.join(imgs_path, file_path)
img_ori = cv2.imread(img_path)
rect = cv2.resize(img_ori, (witdh, height))
rect = cv2.cvtColor(rect, cv2.COLOR_BGR2RGB)
net.setInput(dnn.blobFromImage(rect, 1 / image_std, (witdh, height), 127))
time_time = time.time()
boxes, scores = net.forward(["boxes", "scores"])
print("inference time: {} s".format(round(time.time() - time_time, 4)))
boxes = np.expand_dims(np.reshape(boxes, (-1, 4)), axis=0)
scores = np.expand_dims(np.reshape(scores, (-1, 2)), axis=0)
boxes = convert_locations_to_boxes(boxes, priors, center_variance, size_variance)
boxes = center_form_to_corner_form(boxes)
boxes, labels, probs = predict(img_ori.shape[1], img_ori.shape[0], scores, boxes, args.threshold)
for i in range(boxes.shape[0]):
box = boxes[i, :]
cv2.rectangle(img_ori, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
cv2.imwrite(os.path.join(result_path, file_path), img_ori)
print("result_pic is written to {}".format(os.path.join(result_path, file_path)))
cv2.imshow("ultra_face_ace_opencvdnn_py", img_ori)
cv2.waitKey(-1)
cv2.destroyAllWindows()
def load_model(self, modelTxt, modelBin, classDict, width=300, height = 300, scale = 0.00783, meanVal = 127.5):
self.net = dnn.readNetFromCaffe(modelTxt, modelBin)
self.dict = classDict
self.width = width
self.height = height
self.scale = scale
self.mean_val = meanVal
def __init__(self,
prototype: Path = None,
model: Path = None,
embedder: Path = None,
labelencoder: Path = None,
recognizer: Path = None,
confidenceThreshold: float = 0.8):
self.prototype = prototype
self.model = model
self.confidenceThreshold = confidenceThreshold
if self.prototype is None:
raise FaceRecognizerException(
"must specify prototype '.prototxt.txt' file "
"path")
if self.model is None:
raise FaceRecognizerException(
"must specify model '.caffemodel' file path")
self.classifier = readNetFromCaffe(str(prototype), str(model))
if embedder is None:
raise FaceRecognizerException(
"must specify Face Embedding '.t7' file "
"path")
if recognizer is None:
raise FaceRecognizerException("must specify face recognizor")
if labelencoder is None:
raise FaceRecognizerException("must specify Classifier")
self.embedder = readNetFromTorch(str(embedder))
# load the actual face recognition model along with the label encoder
self.recognizer = pickle.loads(open(str(recognizer), "rb").read())
self.le = pickle.loads(open(str(labelencoder), "rb").read())
def recognition_word(img, boxes, rec_modelPath):
deploy = os.path.join(rec_modelPath, 'deploy.prototxt')
weights = os.path.join(rec_modelPath, 'weights.caffemodel')
labelPath = os.path.join(rec_modelPath, 'label.txt')
text_ = []
Confidence_ = []
row = open(labelPath, encoding='gbk').read().strip().split("\n")
class_label = row
net = dnn.readNetFromCaffe(deploy, weights)
for box in boxes:
img_word = img[int(box[1]):int(box[5]), int(box[0]):int(box[4])].copy()
img_word = cv.cvtColor(img_word, cv.COLOR_RGB2GRAY)
#img_word = img_word[:, :, 0]
img_word = cv.resize(img_word, (64, 64))
blob = dnn.blobFromImage(img_word, 1, (64, 64), (0.))
text, Confidence = model_predict(blob, net, class_label, 1)
text_.append(text[0])
Confidence_.append(round(Confidence[0], 2))
# print(text_)
# print(Confidence_)
return text_, Confidence_
def __init__(self):
# Parametros necesarios para graficar.
self.cap = None
self.h = 0 # alto de la imagen capturada
self.w = 0 # ancho de la imagen captirada
self.old_frame = None
# Detecciones
self.confthr = .5 # umbral de confiabilidad
self.dimthr = .25 # umbral de dimensión (.5 ~50% del ancho total de la imágen)
self.box_startXY = []
self.box_endXY = []
self.detections = [] # detecciones
# radar: modelo y directorio de salida
self.prototxt = './models/MobileNetSSD_deploy.prototxt.txt'
self.modelo = './models/MobileNetSSD_deploy.caffemodel'
self.dir_out = './out/'
self.CLASSES = [
"background", "aeroplane", "bicycle", "bird", "boat", "bottle",
"bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant", "sheep", "sofa", "train",
"tvmonitor"
]
self.IGNORE = {
"background", "aeroplane", "bicycle", "bird", "boat", "bottle",
"cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike",
"person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"
}
# iniciamos el modelo
self.net = readNetFromCaffe(self.prototxt, self.modelo)
self.flag = False
def __init__(self) :
self.inWidth = 300
self.inHeight = 300
self.confThreshold = 0.5
self.prototxt = osp.join(BASE_DIR, 'weights/deploy.prototxt')
self.caffemodel = osp.join(BASE_DIR, 'weights/res10_300x300_ssd_iter_140000.caffemodel')
self.net = dnn.readNetFromCaffe(self.prototxt, self.caffemodel)
def __init__(self):
"""ResnetFaceDetecor class rewrite version
"""
prototxt = 'face_detector/deploy.prototxt'
caffemodel = 'face_detector/res10_300x300_ssd_iter_140000.caffemodel'
self.inWidth = 300
self.inHeight = 300
self.net = dnn.readNetFromCaffe(prototxt, caffemodel)
def caffe2wxf(path):
model = opencv.readNetFromCaffe(path + ".prototxt", path + ".caffemodel")
layers = model.getLayerNames()
npy = {}
for i in layers:
try:
npy[i] = model.getParam(i)
except Exception:
pass
wxf.export(npy, path + '.wxf', target_format='wxf')
def __init__(self,
name: str = 'dnn.readNetFromCaffe',
find_best: bool = True,
color: tuple = (0, 255, 0)):
super().__init__(name=name, find_best=find_best, color=color)
model_filename, config_filename = ModelsSource.get_model_cv2_dnn_cafee_filename(
)
self._net = dnn.readNetFromCaffe(config_filename, model_filename)
self.add_not_none_option('config', config_filename)
self.add_not_none_option('model', model_filename)
def detect(frame):
blob = dnn.blobFromImage(frame, 1, (1024, 768), (0, 0, 0),True)
net = dnn.readNetFromCaffe(cm_path + 'density.prototxt', cm_path + 'density.caffemodel')
net.setInput(blob)
density = net.forward()
density = density/1000.0
person_num = np.sum(density[:])
return int(person_num)
def __init__(self, prototype: Path=None, model: Path=None,
confidenceThreshold: float=0.6):
self.prototype = prototype
self.model = model
self.confidenceThreshold = confidenceThreshold
if self.prototype is None:
raise FaceDetectorException("must specify prototype '.prototxt.txt' file "
"path")
if self.model is None:
raise FaceDetectorException("must specify model '.caffemodel' file path")
self.classifier = readNetFromCaffe(str(prototype), str(model))
def __init__(
self,
dnnModelFile="./resources/face_detectors/facedetect_dnn_res10_300x300_ssd_iter_140000_fp16.caffemodel",
dnnConfigFile="./resources/face_detectors/facedetect_dnn_deploy.prototxt",
confidenceThreshold=.6,
postProcessCallback=None):
super().__init__(postProcessCallback=postProcessCallback)
# check files
open(dnnConfigFile, 'r').close()
open(dnnModelFile, 'r').close()
self.net = dnn.readNetFromCaffe(dnnConfigFile, dnnModelFile)
self.confidenceThreshold = confidenceThreshold
def face_detection():
net = dnn.readNetFromCaffe(prototxt, caffemodel)
#cap = cv.VideoCapture(0)
#cap = cv.VideoCapture("E:/视频库/srcImage/OneStopMoveEnter1cor.avi")
frame = cv.imread("face01.jpg")
while True:
#ret, frame = cap.read()
cols = frame.shape[1]
rows = frame.shape[0]
net.setInput(
dnn.blobFromImage(frame, 1.0, (inWidth, inHeight),
(104.0, 177.0, 123.0), False, False))
detections = net.forward()
perf_stats = net.getPerfProfile()
print('Inference time: %.2f ms' %
(perf_stats[0] / cv.getTickFrequency() * 1000))
for i in range(detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > confThreshold:
global count
count += 1
print(confidence)
xLeftBottom = int(detections[0, 0, i, 3] * cols)
yLeftBottom = int(detections[0, 0, i, 4] * rows)
xRightTop = int(detections[0, 0, i, 5] * cols)
yRightTop = int(detections[0, 0, i, 6] * rows)
cv.rectangle(frame, (xLeftBottom, yLeftBottom),
(xRightTop, yRightTop), (0, 255, 0))
label = "face: %.4f" % confidence
labelSize, baseLine = cv.getTextSize(label,
cv.FONT_HERSHEY_SIMPLEX,
0.5, 1)
cv.rectangle(
frame, (xLeftBottom, yLeftBottom - labelSize[1]),
(xLeftBottom + labelSize[0], yLeftBottom + baseLine),
(255, 255, 255), cv.FILLED)
cv.putText(frame, label, (xLeftBottom, yLeftBottom),
cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
cv.imshow("detections", frame)
print('the num of face: %d ' % count)
if cv.waitKey(0) != -1:
break
def __init__(
self,
prototxt_path: str,
model_path: str,
min_confidence: float,
):
"""Initialize configuration and load pretrained net.
Args:
prototxt_path: Path to net .prototxt file
model_path: Path to net .caffemodel file
min_confidence: Minimum confidence for accepting pe
"""
self._min_confidence = min_confidence
self._net = dnn.readNetFromCaffe(prototxt_path, model_path)
def load_model(self):
global sess, age, gender, train_mode, images_pl
global fa
global face_net
global emotion_labels, emotion_classifier, emotion_target_size
global parentDir
# parser = argparse.ArgumentParser()
# parser.add_argument("--model_path", "--M", default="./models", type=str, help="Model Path")
# args = parser.parse_args()
sess, age, gender, train_mode, images_pl = self.load_network(parentDir + "./models")
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor(parentDir + "\\src\\dist\\FaceSDK\\face_recognition_models\\models\\shape_predictor_68_face_landmarks.dat")
fa = FaceAligner(predictor, desiredFaceWidth=160)
face_model_txt = parentDir + '/trained_models/face_models/deploy_resnet.prototxt'
face_model_bin = parentDir + '/trained_models/face_models/res10_300x300_ssd_iter_140000_fp16.caffemodel'
face_net = dnn.readNetFromCaffe(face_model_txt, face_model_bin)
def face_detection(self):
net = dnn.readNetFromCaffe(prototxt, caffemodel)
net.setInput(
dnn.blobFromImage(self.image, 1.0, (inWidth, inHeight),
(104.0, 177.0, 123.0), False))
detections = net.forward()
# print(detections.shape)
# print(detections)
cols = self.image.shape[1]
rows = self.image.shape[0]
for i in range(detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > confThreshold:
self.count += 1
# print(confidence)
xLeftBottom = int(detections[0, 0, i, 3] * cols)
yLeftBottom = int(detections[0, 0, i, 4] * rows)
xRightTop = int(detections[0, 0, i, 5] * cols)
yRightTop = int(detections[0, 0, i, 6] * rows)
cv2.rectangle(self.image, (xLeftBottom, yLeftBottom),
(xRightTop, yRightTop), (0, 255, 0))
label = "face: %.4f" % confidence
# labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1)
cv2.putText(self.image, label, (xLeftBottom, yLeftBottom),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
cvRGBImg = cv2.cvtColor(self.image, cv2.COLOR_BGR2RGB)
qi = QImage(cvRGBImg.data, cvRGBImg.shape[1], cvRGBImg.shape[0],
cvRGBImg.shape[1] * 3, QImage.Format_RGB888)
pix = QPixmap.fromImage(qi)
self.label2.setPixmap(pix)
self.label2.show()
self.label3.clear()
if self.count > 0:
self.label3.setText("图中检测到{}张人脸".format(self.count))
else:
self.label3.setText("图中未检测到人脸")
def __init__(self,Tello:myTello):
self.prev_flight_data = None
self.record = False
self.tracking = False
self.keydown = False
self.date_fmt = '%Y-%m-%d_%H%M%S'
self.speed = 20
self.speed2 = 10
self.drone = Tello
# self.init_drone()
self.caffe_prototxt_path = "../Face_Distance/model/RFB-320.prototxt"
self.caffe_model_path = "../Face_Distance/model/RFB-320.caffemodel"
self.net = dnn.readNetFromCaffe(self.caffe_prototxt_path, self.caffe_model_path)
# container for processing the packets into frames
# self.container = av.open(self.drone.get_video_stream())
# self.vid_stream = self.drone.container.streams.video[0]
self.out_file = None
self.out_stream = None
self.out_name = None
self.start_time = time.time()
# tracking a color
green_lower = (30, 50, 50)
green_upper = (80, 255, 255)
#red_lower = (0, 50, 50)
# red_upper = (20, 255, 255)
# blue_lower = (110, 50, 50)
# upper_blue = (130, 255, 255)
self.track_cmd = ""
self.ball_tracker = ball_tracker(self.drone.height,
self.drone.width,
green_lower, green_upper)
self.face_tracker = face_tracker(self.drone.height,
self.drone.width,)
#coding=utf-8
from cv2 import dnn
import cv2
import e2e
inWidth = 720
inHeight = 1024
WHRatio = inWidth / float(inHeight)
inScaleFactor = 0.007843
meanVal = 127.5
classNames = ('background',
'plate')
net = dnn.readNetFromCaffe("MobileNetSSD_test.prototxt","lpr.caffemodel")
import time
def detect(cpp):
frame = cv2.imread(cpp)
blob = dnn.blobFromImage(frame, inScaleFactor, (inWidth, inHeight), meanVal)
net.setInput(blob)
t0 = time.time()
detections = net.forward()
print time.time() - t0
cols = frame.shape[1]
rows = frame.shape[0]
if cols / float(rows) > WHRatio:
cropSize = (int(rows * WHRatio), rows)
else:
#coding=utf-8
from cv2 import dnn
import cv2
inWidth = 720
inHeight = 1024
#inWidth = 1024
#inHeight = 720 #for mssd512_voc.caffemodel
WHRatio = inWidth / float(inHeight)
inScaleFactor = 0.007843
meanVal = 127.5
classNames = ('background', 'plate')
net = dnn.readNetFromCaffe("lpr.prototxt", "lpr.caffemodel")
import time
def detect(cpp):
frame = cv2.imread(cpp)
blob = dnn.blobFromImage(frame, inScaleFactor, (inWidth, inHeight),
meanVal)
net.setInput(blob)
t0 = time.time()
detections = net.forward()
print time.time() - t0
cols = frame.shape[1]
rows = frame.shape[0]
#coding=utf-8
from cv2 import dnn
import cv2
import e2e
inWidth = 720
inHeight = 1024
WHRatio = inWidth / float(inHeight)
inScaleFactor = 0.007843
meanVal = 127.5
classNames = ('background', 'plate')
net = dnn.readNetFromCaffe("MobileNetSSD_test.prototxt", "lpr.caffemodel")
import time
def detect(cpp):
frame = cv2.imread(cpp)
blob = dnn.blobFromImage(frame, inScaleFactor, (inWidth, inHeight),
meanVal)
net.setInput(blob)
t0 = time.time()
detections = net.forward()
print time.time() - t0
cols = frame.shape[1]
rows = frame.shape[0]
if cols / float(rows) > WHRatio:
cropSize = (int(rows * WHRatio), rows)
from __future__ import print_function
import numpy as np
import cv2
from cv2 import dnn
import timeit
def timeit_forward(net):
print("Runtime:", timeit.timeit(lambda: net.forward(), number=10))
def get_class_list():
with open('synset_words.txt', 'rt') as f:
return [x[x.find(" ") + 1:] for x in f]
blob = dnn.blobFromImage(cv2.imread('space_shuttle.jpg'), 1, (224, 224), (104, 117, 123), False)
print("Input:", blob.shape, blob.dtype)
net = dnn.readNetFromCaffe('bvlc_googlenet.prototxt', 'bvlc_googlenet.caffemodel')
net.setInput(blob)
prob = net.forward()
#timeit_forward(net) #Uncomment to check performance
print("Output:", prob.shape, prob.dtype)
classes = get_class_list()
print("Best match", classes[prob.argmax()])
You can find the original code here:
https://github.com/opencv/opencv/blob/24bed38c2b2c71d35f2e92aa66648f8485a70892/samples/dnn/resnet_ssd_face_python.py
"""
import cv2 as cv
from cv2 import dnn
WIDTH = 300
HEIGHT = 300
PROTOTXT = './deploy.prototxt'
MODEL = './res10_300x300_ssd_iter_140000.caffemodel'
CASCADES_FILE = "./lbpcascade_frontalface_improved.xml"
CASCADES = cv.CascadeClassifier(CASCADES_FILE)
NET = dnn.readNetFromCaffe(PROTOTXT, MODEL)
VIDEO = 'test.avi'
def get_lbp_facebox(image):
"""
Get the bounding box fo faces in image by LBP feature.
"""
rects = CASCADES.detectMultiScale(image, scaleFactor=1.3, minNeighbors=4, minSize=(30, 30),
flags=cv.CASCADE_SCALE_IMAGE)
if len(rects) == 0:
return []
for rect in rects:
rect[2] += rect[0]
rect[3] += rect[1]
return rects
def dnn_show_result(prob, classes, n):
y = sorted(prob[0], reverse=True) # 从大到小排序
#异常踩坑：# 前n名 # range(50)
# range(50)报错，因为range返回range对象，不返回数组对象
# 将range对象转换为list列表对象在进行遍历
z = list(range(n))
for i in range(0, n):
z[i] = np.where(prob[0] == y[i])[0][0]
print(u"第", i + 1, u"匹配：", classes[z[i]], end='')
print(u"类所在行：", z[i] + 1, " ", u"可能性:", y[i])
if __name__ == "__main__":
if len(sys.argv) < 2:
print("USAGE: googlenet.py images/tiger.jpg")
sys.exit()
print("dddd")
fn = sys.argv[1]
blob = dnn.blobFromImage(cv2.imread(fn), 1, (224, 224), (104, 117, 123))
print("Input:", blob.shape, blob.dtype)
net = dnn.readNetFromCaffe(cm_path + 'bvlc_googlenet.prototxt',
cm_path + 'bvlc_googlenet.caffemodel')
net.setInput(blob)
prob = net.forward()
print("Output:", prob.shape, prob.dtype)
classes = get_class_list()
dnn_show_result(prob, classes, 3)
def __init__(self, model_path, weights_path):
self.net = readNetFromCaffe(model_path, weights_path)
from __future__ import print_function
import numpy as np
import cv2
from cv2 import dnn
import timeit
def timeit_forward(net):
print("Runtime:", timeit.timeit(lambda: net.forward(), number=10))
def get_class_list():
with open('synset_words.txt', 'rt') as f:
return [x[x.find(" ") + 1:] for x in f]
blob = dnn.blobFromImage(cv2.imread('space_shuttle.jpg'), 1, (224, 224),
(104, 117, 123), False)
print("Input:", blob.shape, blob.dtype)
net = dnn.readNetFromCaffe('bvlc_googlenet.prototxt',
'bvlc_googlenet.caffemodel')
net.setInput(blob)
prob = net.forward()
#timeit_forward(net) #Uncomment to check performance
print("Output:", prob.shape, prob.dtype)
classes = get_class_list()
print("Best match", classes[prob.argmax()])
"background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus",
"car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike",
"person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"
]
colors = np.random.uniform(0, 255, size=(len(labels), 3))
image = cv2.imread('bali-crop.jpg')
#prepare test image
(h, w) = image.shape[:2]
#prepare model network
blob = dnn.blobFromImage(image, 1, (512, 512))
prototxt = "models\VGGNet\VOC0712Plus\SSD_512x512_ft\deploy.prototxt"
model = "models\VGGNet\VOC0712Plus\SSD_512x512_ft\VGG_VOC0712Plus_SSD_512x512_ft_iter_160000.caffemodel"
net = dnn.readNetFromCaffe(prototxt, model)
#feed in image and get result
net.setInput(blob)
t = time.time()
prob = net.forward()
print("Runtime:", time.time() - t)
#diaplay result
for i in np.arange(0, prob.shape[2]):
confidence = prob[0, 0, i, 2]
if confidence > 0.4: #change threshold value to get the result you want
# get data from prob
index = int(prob[0, 0, i, 1])
box = prob[0, 0, i, 3:7] * np.array([w, h, w, h])
(x, y, endX, endY) = box.astype("int")
parser = argparse.ArgumentParser()
parser.add_argument("--video", help="number of video device", default=0)
parser.add_argument("--prototxt", default="mobilenet_v2_deploy.prototxt")
parser.add_argument("--caffemodel", default="mobilenet_v2.caffemodel")
parser.add_argument("--classNames", default="synset.txt")
args = parser.parse_args()
width = 480
height = 640
camera = picamera.PiCamera()
camera.resolution = (width, height)
camera.rotation = 90
offset = 22
net = dnn.readNetFromCaffe(args.prototxt, args.caffemodel)
f = open(args.classNames, 'r')
rawClassNames = f.readlines()
classNames = []
for nameStr in rawClassNames:
spaceIndex = nameStr.find(' ')
nameStr = nameStr[spaceIndex:-2]
classNames.append(nameStr)
inWidth = 224
inHeight = 224
inScaleFactor = 0.017
meanVal = (103.94, 116.78, 123.68)
resultText = None
pygame.init()
def __init__(self, prototype, model, confidence_threshold: float = 0.6):
self.prototype = prototype
self.model = model
self.confidence_threshold = confidence_threshold
self.classifier = readNetFromCaffe(str(prototype), str(model))
"贵": "GUIB",
"云": "YUN",
"川": "CHUAN"
}
plateTypeName = ["蓝", "黄", "绿", "白", "黑 "]
fontC = ImageFont.truetype("Font/platech.ttf", 38,
0) # 加载中文字体，38表示字体大小，0表示unicode编码
inWidth = 480 # 480 # from ssd.prototxt ，540，960,720,640,768,设置图片宽度
inHeight = 640 # 640 ，720，1280，960，480，1024
WHRatio = inWidth / float(inHeight) # 计算宽高比
inScaleFactor = 0.007843 # 1/127.5
meanVal = 127.5
classNames = ('background', 'plate')
net = dnn.readNetFromCaffe("model/MobileNetSSD_test.prototxt",
"model/lpr.caffemodel") # 读入模型文件
net.setPreferableBackend(dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(dnn.DNN_TARGET_CPU) # 使用cpu
# net.setPreferableTarget(dnn.DNN_TARGET_OPENCL) # 启用GPU OPENCL 加速 ，默认FP32
# net.setPreferableTarget(dnn.DNN_TARGET_OPENCL_FP16) # only for intel xianka test faster speed
# 画车牌定位框及识别出来的车牌字符，返回标记过的图片
def drawPred(frame, label, left, top, right, bottom):
# 画车牌定位边框.左上点，右下点,红色，边框粗细：2
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
# 画车牌字符
img = Image.fromarray(frame)
draw = ImageDraw.Draw(img)
draw.text((left + 1, top - 38), label, (0, 0, 255),
import cv2 as cv
except ImportError:
raise ImportError('Can\'t find OpenCV Python module. If you\'ve built it from sources without installation, '
'configure environemnt variable PYTHONPATH to "opencv_build_dir/lib" directory (with "python3" subdirectory if required)')
from cv2 import dnn
inWidth = 300
inHeight = 300
confThreshold = 0.5
prototxt = 'face_detector/deploy.prototxt'
caffemodel = 'face_detector/res10_300x300_ssd_iter_140000.caffemodel'
if __name__ == '__main__':
net = dnn.readNetFromCaffe(prototxt, caffemodel)
cap = cv.VideoCapture(0)
while True:
ret, frame = cap.read()
cols = frame.shape[1]
rows = frame.shape[0]
net.setInput(dnn.blobFromImage(frame, 1.0, (inWidth, inHeight), (104.0, 177.0, 123.0), False, False))
detections = net.forward()
perf_stats = net.getPerfProfile()
print('Inference time, ms: %.2f' % (perf_stats[0] / cv.getTickFrequency() * 1000))
for i in range(detections.shape[2]):
confidence = detections[0, 0, i, 2]
def _get_classifier(self):
prototxt_p = self.model_p / "deploy.prototxt.txt"
caffemodel_p = self.model_p / "res10_300x300_ssd_iter_140000.caffemodel"
return readNetFromCaffe(str(prototxt_p), str(caffemodel_p))
import cv2 as cv
from cv2 import dnn
img = cv.imread('/home/king/Desktop/1.png')
net = dnn.readNetFromCaffe('./res/deploy.prototxt', './res/res10_300x300_ssd_iter_140000.caffemodel')
net.setInput(dnn.blobFromImage(img, 1.0, (300, 300), (104.0, 177.0, 123.0), False, False))
detections = net.forward()
cols = img.shape[1]
rows = img.shape[0]
for i in range(detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > 0.5:
xLeftBottom = int(detections[0, 0, i, 3] * cols)
yLeftBottom = int(detections[0, 0, i, 4] * rows)
xRightTop = int(detections[0, 0, i, 5] * cols)
yRightTop = int(detections[0, 0, i, 6] * rows)
cv.rectangle(img, (xLeftBottom, yLeftBottom), (xRightTop, yRightTop), (0, 0, 255))
cv.imshow('img', img)
cv.waitKey(0)
cv.destroyAllWindows()
plateTypeName = ["蓝", "黄", "绿", "白", "黑 "]
import os
dir_path = os.getcwd()
fontC = ImageFont.truetype(dir_path + "/hyperlpr_py3/Font/platech.ttf", 30,
0) # 加载中文字体，38表示字体大小，0表示unicode编码
inWidth = 480 # 480 # from ssd.prototxt ，540，960,720,640,768,设置图片宽度
inHeight = 640 # 640 ，720，1280，960，480，1024
WHRatio = inWidth / float(inHeight) # 计算宽高比
inScaleFactor = 0.007843 # 1/127.5
meanVal = 127.5
classNames = ('background', 'plate')
net = dnn.readNetFromCaffe(
dir_path + "/hyperlpr_py3/model/MobileNetSSD_test.prototxt",
dir_path + "/hyperlpr_py3/model/lpr.caffemodel") # 读入模型文件
net.setPreferableBackend(dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(dnn.DNN_TARGET_CPU) # 使用cpu
# net.setPreferableTarget(dnn.DNN_TARGET_OPENCL) # 启用GPU OPENCL 加速 ，默认FP32
# net.setPreferableTarget(dnn.DNN_TARGET_OPENCL_FP16) # only for intel xianka test faster speed
# 画车牌定位框及识别出来的车牌字符，返回标记过的图片
def drawPred(frame, label, left, top, right, bottom):
# 画车牌定位边框.左上点，右下点,红色，边框粗细：2
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
# 画车牌字符
img = Image.fromarray(frame)
draw = ImageDraw.Draw(img)