def visualzation(model_path, img_path):
model = tf.saved_model.load(model_path)
perdictor = model.signatures['serving_default']
image = Image.open(img_path)
# (batch, 2)
image_shape = np.expand_dims(np.array([image.size[1], image.size[0]],
dtype='float32'),
axis=0)
# letter box
image_letter = letterbox_image(image, (416, 416))
image_array = np.expand_dims(np.array(image_letter, dtype='float32') /
255.0,
axis=0)
image_constant = tf.constant(image_array, dtype=tf.float32)
image_shape = tf.constant(image_shape, dtype=tf.float32)
# infer
results = perdictor(input_2=image_constant,
input_3=image_shape) # dictionary
results_ = []
for key, value in results.items():
results_.append(value)
# -------------------------------------------------------------------------------------
# visualize
boxes = results_[0]
scores = results_[1]
classes = results_[2]
# starting draw bounding boxes
font = ImageFont.truetype(font='font/simhei.ttf',
size=np.floor(2e-2 * image.size[1] +
0.5).astype('int32'))
# thickness of bounding box and this thickness is changing according to img_size
thickness = (image.size[0] + image.size[1]) // 500
for i, c in list(enumerate(classes)):
predicted_class = class_names[c]
box = boxes[i]
score = scores[i]
top, left, bottom, right = box
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
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'))
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
# print(label)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for j in range(thickness):
draw.rectangle([left + j, top + j, right - j, bottom - j],
outline=(0, 0, 255))
draw.rectangle([tuple(text_origin),
tuple(text_origin + label_size)],
fill=(128, 128, 128))
draw.text(text_origin, str(label, 'UTF-8'), fill=(0, 0, 0), font=font)
del draw
return image
class_ = tf.concat(class_, axis=0)
total_model = keras.Model([inputs, image_shape], [boxes_, scores_, class_])
# 5.save model
tf.saved_model.save(total_model, save_path)
return total_model
if __name__ == '__main__':
inputs_ = keras.Input(shape=(416, 416, 3))
img_shape = keras.Input(shape=())
model = save_model(inputs_,
img_shape,
(416, 416, 3),
num_anchors,
num_classes,
score,
iou)
# test model
# and through testing, the decoding codes are usable.
image = Image.open(img_path)
image_shape = np.array([image.size[1], image.size[0]], dtype='float32')
image = letterbox_image(image, (416, 416))
image_array = np.expand_dims(np.array(image, dtype='float32') / 255.0, axis=0)
boxes, scores, classes = model([image_array, image_shape])
print(classes)
print(scores)
print(boxes)
def detect_image(self, image, htimes=0):
start = timer()
# 调整图片使其符合输入要求
new_image_size = (image.width - (image.width % 32),
image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size) # 得到灰度图片
image_data = np.array(boxed_image, dtype='float32')
image_data /= 255.
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
# 预测结果
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'))
# for i in out_classes:
# if i==0:
# htimes+=1
# break
# if(htimes>2):
# p= Process( target=winsound.PlaySound,args=("1.wav",winsound.SND_ALIAS))
# p.start()
# htimes=0
# # p进程执行f函数，参数为'Qbob'，注意后面的“,”
# break
# htimes = 0
# 设置字体
font = ImageFont.truetype(font='font/simhei.ttf',
size=np.floor(3e-2 * image.size[1] +
0.5).astype('int32'))
thickness = (image.size[0] + image.size[1]) // 300
small_pic = []
for i, c in list(enumerate(out_classes)):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
top, left, bottom, right = box
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
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'))
# 画框框
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label)
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,
str(label, 'UTF-8'),
fill=(0, 0, 0),
font=font)
del draw
end = timer()
print(end - start)
return image, htimes