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
return out_boxes, out_scores
def get_training_data(annotation_path,
data_path,
input_shape,
max_boxes=100,
load_previous=True):
'''processes the data into standard shape
annotation row format: image_file_path box1 box2 ... boxN
box format: x_min,y_min,x_max,y_max,class_index (no space)
'''
if load_previous == True and os.path.isfile(data_path):
data = np.load(data_path)
print('Loading training data from ' + data_path)
return data['image_data'], data['box_data']
image_data = []
box_data = []
with open(annotation_path) as f:
for line in f.readlines():
line = line.split(' ')
filename = line[0]
image = Image.open(filename)
boxed_image = letterbox_image(image, tuple(reversed(input_shape)))
image_data.append(np.array(boxed_image, dtype='uint8'))
boxes = np.zeros((max_boxes, 5), dtype='int32')
for i, box in enumerate(line[1:]):
if i < max_boxes:
boxes[i] = np.array(list(map(int, box.split(','))))
else:
break
image_size = np.array(image.size)
input_size = np.array(input_shape[::-1])
new_size = (image_size *
np.min(input_size / image_size)).astype('int32')
boxes[:i + 1, 0:2] = (boxes[:i + 1, 0:2] * new_size / image_size +
(input_size - new_size) / 2).astype('int32')
boxes[:i + 1, 2:4] = (boxes[:i + 1, 2:4] * new_size / image_size +
(input_size - new_size) / 2).astype('int32')
box_data.append(boxes)
image_data = np.array(image_data)
box_data = np.array(box_data)
np.savez(data_path, image_data=image_data, box_data=box_data)
print('Saving training data into ' + data_path)
return image_data, box_data
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))
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
def detect_image(self, image, imageName):
start = timer()
if self.model_image_size != (None, None): #图片大小预判断
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.
#从model文件中获取boxes，scores，classes
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'))
#这是我写的方法，如果找不到人脸，就打印一行
if len(out_boxes) == 0:
with open('text.txt', 'a') as file:
Name = imageName
file.write(Name + ".jpg" + ",can not detect any boxes.\n")
#加载提示框的字体
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
#对于每一个box
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)
#对灰度图像进行RGB转换，否则会报错
image = image.convert('RGB')
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))
#这里返回的是每一个box的上下左右坐标值，位置对应之后打印到text.txt文件中
with open('text.txt', 'a') as file:
Name = imageName
file.write(Name + ".jpg," + str(left) + "," + str(top) + "," +
str(right) + "," + str(bottom) + "\n")
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