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()
self.predictor = CardPredictor()
self.points = []
class YOLO():
_defaults = {
"model_path": 'model_data/yolo.h5', #yolo
"anchors_path": 'model_data/yolo_anchors.txt',
"classes_path": 'model_data/coco_classes.txt', #myclasses
"score": 0.3,
"iou": 0.2, # 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()
self.predictor = CardPredictor()
self.points = []
def detect_carnumber(self, img_bgr, box): #r1, r2, r3, r4
img_bgr = img_bgr[box[0]:box[1], box[2]:box[3]]
r = self.predictor.predict(img_bgr)
return r
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, frame):
start = timer()
#origin_img = image
#origin_img = cv2.cvtColor(np.asarray(origin_img), cv2.COLOR_RGB2BGR)
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
})
#out_boxes = [i for i in out_boxes if i in ['bus','car','person']]
#out_scores = [i for i in out_scores if i in ['bus','car','person']]
out_classes = [
i for i in out_classes
if self.class_names[i] in ['bus', 'car', 'person']
]
result_info = 'Found {} boxes for {}'.format(len(out_boxes), 'img')
print(result_info)
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]) // 400
if len(self.points) != len(out_classes):
for i, c in reversed(list(enumerate(out_classes))):
box = out_boxes[i]
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'))
self.points.append({
'class':
self.class_names[c],
'point': [(top + bottom) / 2, (left + right) / 2]
})
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
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'))
if predicted_class == 'car' or predicted_class == 'bus':
box = [top, bottom, left, right]
carpoint = [(top + bottom) / 2, (left + right) / 2]
rate = 51
while rate > 50:
if self.points[i]['class'] == predicted_class:
rate = math.sqrt(
(carpoint[0] - self.points[i]['point'][0])**2 +
(carpoint[1] - self.points[i]['point'][1])**2) / 2
i += 1
if i == len(self.points):
rate = 0
break
carnumber = self.detect_carnumber(frame, box)
if carnumber is None:
carnumber = 'no'
else:
carnumber = ''.join(carnumber)
label = '{} {} {:.2f}'.format(predicted_class, carnumber,
rate) #label = '{} {:.2f}'
else:
label = '{} {:.1f} {:.2f}'.format(predicted_class, score,
rate) #label = '{} {:.2f}'
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
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(end - start)
return image, result_info
def close_session(self):
self.sess.close()