def get_FPS(self, image, test_interval):
# 调整图片使其符合输入要求
image_shape = np.array(np.shape(image)[0:2])
crop_img,x_offset,y_offset = letterbox_image(image, (self.model_image_size[0],self.model_image_size[1]))
photo = np.array(crop_img,dtype = np.float64)
# 图片预处理，归一化
photo = preprocess_input(np.reshape(photo,[1,self.model_image_size[0],self.model_image_size[1],3]))
preds = self.ssd_model.predict(photo)
# 将预测结果进行解码
results = self.bbox_util.detection_out(preds, confidence_threshold=self.confidence)
if len(results[0])>0:
# 筛选出其中得分高于confidence的框
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 2], results[0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [i for i, conf in enumerate(det_conf) if conf >= self.confidence]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(det_xmin[top_indices],-1),np.expand_dims(det_ymin[top_indices],-1),np.expand_dims(det_xmax[top_indices],-1),np.expand_dims(det_ymax[top_indices],-1)
# 去掉灰条
boxes = ssd_correct_boxes(top_ymin,top_xmin,top_ymax,top_xmax,np.array([self.model_image_size[0],self.model_image_size[1]]),image_shape)
t1 = time.time()
for _ in range(test_interval):
# 调整图片使其符合输入要求
image_shape = np.array(np.shape(image)[0:2])
crop_img,x_offset,y_offset = letterbox_image(image, (self.model_image_size[0],self.model_image_size[1]))
photo = np.array(crop_img,dtype = np.float64)
# 图片预处理，归一化
photo = preprocess_input(np.reshape(photo,[1,self.model_image_size[0],self.model_image_size[1],3]))
preds = self.ssd_model.predict(photo)
# 将预测结果进行解码
results = self.bbox_util.detection_out(preds, confidence_threshold=self.confidence)
if len(results[0])>0:
# 筛选出其中得分高于confidence的框
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 2], results[0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [i for i, conf in enumerate(det_conf) if conf >= self.confidence]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(det_xmin[top_indices],-1),np.expand_dims(det_ymin[top_indices],-1),np.expand_dims(det_xmax[top_indices],-1),np.expand_dims(det_ymax[top_indices],-1)
# 去掉灰条
boxes = ssd_correct_boxes(top_ymin,top_xmin,top_ymax,top_xmax,np.array([self.model_image_size[0],self.model_image_size[1]]),image_shape)
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
def detect_image(self, image_id, image):
self.confidence = 0.01
f = open("./input/detection-results/" + image_id + ".txt", "w")
image_shape = np.array(np.shape(image)[0:2])
crop_img, x_offset, y_offset = letterbox_image(
image, (self.model_image_size[0], self.model_image_size[1]))
photo = np.array(crop_img, dtype=np.float64)
# 图片预处理，归一化
photo = preprocess_input(
np.reshape(
photo,
[1, self.model_image_size[0], self.model_image_size[1], 3]))
preds = self.ssd_model.predict(photo)
# 将预测结果进行解码
results = self.bbox_util.detection_out(
preds, confidence_threshold=self.confidence)
if len(results[0]) <= 0:
f.close()
return
# 筛选出其中得分高于confidence的框
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 2], results[
0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [
i for i, conf in enumerate(det_conf) if conf >= self.confidence
]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
det_xmin[top_indices],
-1), np.expand_dims(det_ymin[top_indices], -1), np.expand_dims(
det_xmax[top_indices],
-1), np.expand_dims(det_ymax[top_indices], -1)
# 去掉灰条
boxes = ssd_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.model_image_size[0], self.model_image_size[1]]),
image_shape)
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c) - 1]
score = str(top_conf[i])
top, left, bottom, right = boxes[i]
f.write("%s %s %s %s %s %s\n" %
(predicted_class, score[:6], str(int(left)), str(
int(top)), str(int(right)), str(int(bottom))))
f.close()
return
def detect_image(self,image_id,image):
self.confidence = 0.01
f = open("./input/detection-results/"+image_id+".txt","w")
image_shape = np.array(np.shape(image)[0:2])
#---------------------------------------------------------#
# 给图像增加灰条，实现不失真的resize
# 也可以直接resize进行识别
#---------------------------------------------------------#
if self.letterbox_image:
crop_img = np.array(letterbox_image(image, (self.input_shape[1],self.input_shape[0])))
else:
crop_img = image.convert('RGB')
crop_img = crop_img.resize((self.input_shape[1],self.input_shape[0]), Image.BICUBIC)
photo = np.array(crop_img,dtype = np.float64)
# 图片预处理，归一化
photo = preprocess_input(np.reshape(photo,[1,self.input_shape[0],self.input_shape[1],3]))
preds = self.ssd_model.predict(photo)
# 将预测结果进行解码
results = self.bbox_util.detection_out(preds, confidence_threshold=self.confidence)
if len(results[0])<=0:
f.close()
return
# 筛选出其中得分高于confidence的框
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 2], results[0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [i for i, conf in enumerate(det_conf) if conf >= self.confidence]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(det_xmin[top_indices],-1),np.expand_dims(det_ymin[top_indices],-1),np.expand_dims(det_xmax[top_indices],-1),np.expand_dims(det_ymax[top_indices],-1)
#-----------------------------------------------------------#
# 去掉灰条部分
#-----------------------------------------------------------#
if self.letterbox_image:
boxes = ssd_correct_boxes(top_ymin,top_xmin,top_ymax,top_xmax,np.array([self.input_shape[0],self.input_shape[1]]),image_shape)
else:
top_xmin = top_xmin * image_shape[1]
top_ymin = top_ymin * image_shape[0]
top_xmax = top_xmax * image_shape[1]
top_ymax = top_ymax * image_shape[0]
boxes = np.concatenate([top_ymin,top_xmin,top_ymax,top_xmax], axis=-1)
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c)-1]
score = str(top_conf[i])
top, left, bottom, right = boxes[i]
f.write("%s %s %s %s %s %s\n" % (predicted_class, score[:6], str(int(left)), str(int(top)), str(int(right)),str(int(bottom))))
f.close()
return
def detect_image(self, image):
image_shape = np.array(np.shape(image)[0:2])
crop_img, x_offset, y_offset = letterbox_image(image, (300, 300))
photo = np.array(crop_img, dtype=np.float64)
self.predict_all = []
# 图片预处理，归一化
photo = tf.keras.applications.imagenet_utils.preprocess_input(
np.reshape(photo, [1, 300, 300, 3]))
#self.ssd_model.summary()
preds = self.ssd_model.predict(photo)
# 将预测结果进行解码
results = self.bbox_util.detection_out(preds)
if len(results[0]) <= 0:
return image
# 筛选出其中得分高于confidence的框
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 2], results[
0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [
i for i, conf in enumerate(det_conf) if conf >= self.confidence
]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
det_xmin[top_indices],
-1), np.expand_dims(det_ymin[top_indices], -1), np.expand_dims(
det_xmax[top_indices],
-1), np.expand_dims(det_ymax[top_indices], -1)
boxes = ssd_correct_boxes(top_ymin, top_xmin, top_ymax, top_xmax,
np.array([300, 300]), image_shape)
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] +
0.5).astype('int32'))
thickness = (np.shape(image)[0] + np.shape(image)[1]) // 300
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c) - 1]
score = top_conf[i]
top, left, bottom, right = boxes[i]
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(
np.shape(image)[0],
np.floor(bottom + 0.5).astype('int32'))
right = min(
np.shape(image)[1],
np.floor(right + 0.5).astype('int32'))
self.result_ = '{} {} {} {} {} {}'.format(
"".join(predicted_class.split(" ")), score, left, top, right,
bottom)
self.predict_all.append(self.result_)
# 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=255)
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=255)
draw.text(text_origin, str(label, 'UTF-8'), fill=0, font=font)
del draw
return image
def detect_image(self, image):
image_shape = np.array(np.shape(image)[0:2])
#---------------------------------------------------------#
# 给图像增加灰条，实现不失真的resize
# 也可以直接resize进行识别
#---------------------------------------------------------#
if self.letterbox_image:
crop_img = np.array(
letterbox_image(image,
(self.input_shape[1], self.input_shape[0])))
else:
crop_img = image.convert('RGB')
crop_img = crop_img.resize(
(self.input_shape[1], self.input_shape[0]), Image.BICUBIC)
photo = np.array(crop_img, dtype=np.float64)
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
photo = preprocess_input(
np.reshape(photo,
[1, self.input_shape[0], self.input_shape[1], 3]))
preds = self.ssd_model.predict(photo)
#-----------------------------------------------------------#
# 将预测结果进行解码
#-----------------------------------------------------------#
results = self.bbox_util.detection_out(
preds, confidence_threshold=self.confidence)
#--------------------------------------#
# 如果没有检测到物体，则返回原图
#--------------------------------------#
if len(results[0]) <= 0:
return image
#-----------------------------------------------------------#
# 筛选出其中得分高于confidence的框
#-----------------------------------------------------------#
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 2], results[
0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [
i for i, conf in enumerate(det_conf) if conf >= self.confidence
]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
det_xmin[top_indices],
-1), np.expand_dims(det_ymin[top_indices], -1), np.expand_dims(
det_xmax[top_indices],
-1), np.expand_dims(det_ymax[top_indices], -1)
#-----------------------------------------------------------#
# 去掉灰条部分
#-----------------------------------------------------------#
if self.letterbox_image:
boxes = ssd_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.input_shape[0], self.input_shape[1]]),
image_shape)
else:
top_xmin = top_xmin * image_shape[1]
top_ymin = top_ymin * image_shape[0]
top_xmax = top_xmax * image_shape[1]
top_ymax = top_ymax * image_shape[0]
boxes = np.concatenate([top_ymin, top_xmin, top_ymax, top_xmax],
axis=-1)
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] +
0.5).astype('int32'))
thickness = max(
(np.shape(image)[0] + np.shape(image)[1]) // self.input_shape[0],
1)
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c) - 1]
score = top_conf[i]
top, left, bottom, right = boxes[i]
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(
np.shape(image)[0],
np.floor(bottom + 0.5).astype('int32'))
right = min(
np.shape(image)[1],
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, top, left, bottom, right)
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[int(c) - 1])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=self.colors[int(c) - 1])
draw.text(text_origin,
str(label, 'UTF-8'),
fill=(0, 0, 0),
font=font)
del draw
return image
def detect_image(self, image):
if type(image) is np.ndarray:
image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
image_shape = np.array(np.shape(image)[0:2])
crop_img, x_offset, y_offset = letterbox_image(
image, (self.model_image_size[0], self.model_image_size[1]))
photo = np.array(crop_img, dtype=np.float64)
# 图片预处理，归一化
photo = preprocess_input(
np.reshape(
photo,
[1, self.model_image_size[0], self.model_image_size[1], 3]))
preds = self.ssd_model.predict(photo)
# 将预测结果进行解码
results = self.bbox_util.detection_out(
preds, confidence_threshold=self.confidence)
if len(results[0]) <= 0:
return image
# 筛选出其中得分高于confidence的框
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 2], results[
0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [
i for i, conf in enumerate(det_conf) if conf >= self.confidence
]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
det_xmin[top_indices],
-1), np.expand_dims(det_ymin[top_indices], -1), np.expand_dims(
det_xmax[top_indices],
-1), np.expand_dims(det_ymax[top_indices], -1)
# 去掉灰条
boxes = ssd_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.model_image_size[0], self.model_image_size[1]]),
image_shape)
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] +
0.5).astype('int32'))
thickness = (np.shape(image)[0] +
np.shape(image)[1]) // self.model_image_size[0]
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c) - 1]
score = top_conf[i]
top, left, bottom, right = boxes[i]
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(
np.shape(image)[0],
np.floor(bottom + 0.5).astype('int32'))
right = min(
np.shape(image)[1],
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[int(c) - 1])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=self.colors[int(c) - 1])
draw.text(text_origin,
str(label, 'UTF-8'),
fill=(0, 0, 0),
font=font)
del draw
return image
def detect_image(self, image):
image_shape = np.array(np.shape(image)[0:2])
crop_image,x_offset,y_offset = letterbox_image(image, (self.input_shape[0], self.input_shape[1]))
photo = np.array(crop_image, dtype=np.float64)
# Normalization
photo = preprocess_input(np.reshape(photo, [1, self.input_shape[0], self.input_shape[1], 3]))
preds = self.get_pred(photo).numpy()
# Decode
results = self.bbox_util.detection_out(preds, confidence_threshold=config.CONFIDENCE)
if len(results[0]) <= 0:
return image
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:,2], results[0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [i for i, conf in enumerate(det_conf) if conf >= config.CONFIDENCE]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin = np.expand_dims(det_xmin[top_indices], axis=-1)
top_ymin = np.expand_dims(det_ymin[top_indices], axis=-1)
top_xmax = np.expand_dims(det_xmax[top_indices], axis=-1)
top_ymax = np.expand_dims(det_ymax[top_indices], axis=-1)
boxes = ssd_correct_boxes(top_ymin, top_xmin, top_ymax, top_xmax, np.array((self.input_shape[0], self.input_shape[1])), image_shape)
font = ImageFont.truetype(font='simhei.ttf',size=np.floor(3e-2 * np.shape(image)[1] + 0.5).astype('int32'))
thickness = (np.shape(image)[0] + np.shape(image)[1]) // self.input_shape[0]
for i, c in enumerate(top_label_indices):
predicted_class = self.classes[int(c) - 1]
score = top_conf[i]
ymin, xmin, ymax, xmax = boxes[i]
ymin = ymin - 5
xmin = xmin - 5
ymax = ymax - 5
xmax = xmax - 5
ymin = max(0, np.floor(ymin + 0.5).astype('int32'))
xmin = max(0, np.floor(xmin + 0.5).astype('int32'))
ymax = min(np.shape(image)[0], np.floor(ymax + 0.5).astype('int32'))
xmax = min(np.shape(image)[1], np.floor(xmax + 0.5).astype('int32'))
# draw Bounding box
label = "{}:{:.2f}".format(predicted_class, score)
print(label)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
if ymin - label_size[1] >= 0:
text_origin = np.array((xmin, ymin - label_size[1]))
else:
text_origin = np.array((xmin, ymin + 1))
for i in range(thickness):
draw.rectangle(
[xmin + i, ymin + i, xmax - i, ymax - i],
outline=self.colors[int(c)-1])
draw.rectangle(
[tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[int(c)-1])
draw.text(text_origin, str(label, 'UTF-8'), fill=(0, 0, 0), font=font)
del draw
return image
def get_FPS(self, image, test_interval):
image_shape = np.array(np.shape(image)[0:2])
#---------------------------------------------------------#
# 给图像增加灰条，实现不失真的resize
# 也可以直接resize进行识别
#---------------------------------------------------------#
if self.letterbox_image:
crop_img = np.array(
letterbox_image(image,
(self.input_shape[1], self.input_shape[0])))
else:
crop_img = image.convert('RGB')
crop_img = crop_img.resize(
(self.input_shape[1], self.input_shape[0]), Image.BICUBIC)
photo = np.array(crop_img, dtype=np.float64)
photo = preprocess_input(
np.reshape(photo,
[1, self.input_shape[0], self.input_shape[1], 3]))
preds = self.ssd_model.predict(photo)
results = self.bbox_util.detection_out(
preds, confidence_threshold=self.confidence)
if len(results[0]) > 0:
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 2], results[
0][:, 3], results[0][:, 4], results[0][:, 5]
top_indices = [
i for i, conf in enumerate(det_conf) if conf >= self.confidence
]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
det_xmin[top_indices],
-1), np.expand_dims(det_ymin[top_indices], -1), np.expand_dims(
det_xmax[top_indices],
-1), np.expand_dims(det_ymax[top_indices], -1)
#-----------------------------------------------------------#
# 去掉灰条部分
#-----------------------------------------------------------#
if self.letterbox_image:
boxes = ssd_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.input_shape[0], self.input_shape[1]]),
image_shape)
else:
top_xmin = top_xmin * image_shape[1]
top_ymin = top_ymin * image_shape[0]
top_xmax = top_xmax * image_shape[1]
top_ymax = top_ymax * image_shape[0]
boxes = np.concatenate(
[top_ymin, top_xmin, top_ymax, top_xmax], axis=-1)
t1 = time.time()
for _ in range(test_interval):
preds = self.ssd_model.predict(photo)
results = self.bbox_util.detection_out(
preds, confidence_threshold=self.confidence)
if len(results[0]) > 0:
det_label = results[0][:, 0]
det_conf = results[0][:, 1]
det_xmin, det_ymin, det_xmax, det_ymax = results[
0][:, 2], results[0][:, 3], results[0][:, 4], results[0][:,
5]
top_indices = [
i for i, conf in enumerate(det_conf)
if conf >= self.confidence
]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
det_xmin[top_indices], -1), np.expand_dims(
det_ymin[top_indices], -1), np.expand_dims(
det_xmax[top_indices],
-1), np.expand_dims(det_ymax[top_indices], -1)
#-----------------------------------------------------------#
# 去掉灰条部分
#-----------------------------------------------------------#
if self.letterbox_image:
boxes = ssd_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.input_shape[0], self.input_shape[1]]),
image_shape)
else:
top_xmin = top_xmin * image_shape[1]
top_ymin = top_ymin * image_shape[0]
top_xmax = top_xmax * image_shape[1]
top_ymax = top_ymax * image_shape[0]
boxes = np.concatenate(
[top_ymin, top_xmin, top_ymax, top_xmax], axis=-1)
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time