def detect_image(self, image_id, image):
self.confidence = 0.01
self.bbox_util._nms_thresh = 0.5
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],
self.model_image_size[2]
]))
preds = self.retinanet_model.predict(photo)
# 将预测结果进行解码
results = self.bbox_util.detection_out(
preds, self.prior, confidence_threshold=self.confidence)
if len(results[0]) <= 0:
return image
results = np.array(results)
# 筛选出其中得分高于confidence的框
det_label = results[0][:, 5]
det_conf = results[0][:, 4]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 0], results[
0][:, 1], results[0][:, 2], results[0][:, 3]
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 = retinanet_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)]
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
self.iou = 0.5
f = open("./input/detection-results/" + image_id + ".txt", "w")
image_shape = np.array(np.shape(image)[0:2])
crop_img = np.array(letterbox_image(image, self.image_size))
photo = np.array(crop_img, dtype=np.float32)
photo = np.transpose(preprocess_input(photo), (2, 0, 1))
images = []
images.append(photo)
images = np.asarray(images)
with torch.no_grad():
images = torch.from_numpy(images)
if self.cuda:
images = images.cuda()
_, regression, classification, anchors = self.net(images)
regression = decodebox(regression, anchors, images)
detection = torch.cat([regression, classification], axis=-1)
batch_detections = non_max_suppression(detection,
len(self.class_names),
conf_thres=self.confidence,
nms_thres=0.3)
try:
batch_detections = batch_detections[0].cpu().numpy()
except:
return image
top_index = batch_detections[:, 4] > self.confidence
top_conf = batch_detections[top_index, 4]
top_label = np.array(batch_detections[top_index, -1], np.int32)
top_bboxes = np.array(batch_detections[top_index, :4])
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
top_bboxes[:, 0],
-1), np.expand_dims(top_bboxes[:, 1], -1), np.expand_dims(
top_bboxes[:, 2], -1), np.expand_dims(top_bboxes[:, 3], -1)
# 去掉灰条
boxes = retinanet_correct_boxes(top_ymin, top_xmin, top_ymax, top_xmax,
np.array(self.image_size), image_shape)
for i, c in enumerate(top_label):
predicted_class = self.class_names[c]
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])
#---------------------------------------------------------#
# 给图像增加灰条，实现不失真的resize
#---------------------------------------------------------#
crop_img = np.array(
letterbox_image(image, [self.input_shape[1], self.input_shape[0]]))
photo = np.array(crop_img, dtype=np.float32)
photo = np.transpose(preprocess_input(photo), (2, 0, 1))
with torch.no_grad():
images = torch.from_numpy(np.asarray([photo]))
if self.cuda:
images = images.cuda()
#---------------------------------------------------------#
# 传入网络当中进行预测
#---------------------------------------------------------#
_, regression, classification, anchors = self.net(images)
#-----------------------------------------------------------#
# 将预测结果进行解码
#-----------------------------------------------------------#
regression = decodebox(regression, anchors, images)
detection = torch.cat([regression, classification], axis=-1)
batch_detections = non_max_suppression(detection,
len(self.class_names),
conf_thres=self.confidence,
nms_thres=self.iou)
#--------------------------------------#
# 如果没有检测到物体，则返回原图
#--------------------------------------#
try:
batch_detections = batch_detections[0].cpu().numpy()
except:
return image
#-----------------------------------------------------------#
# 筛选出其中得分高于confidence的框
#-----------------------------------------------------------#
top_index = batch_detections[:, 4] > self.confidence
top_conf = batch_detections[top_index, 4]
top_label = np.array(batch_detections[top_index, -1], np.int32)
top_bboxes = np.array(batch_detections[top_index, :4])
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
top_bboxes[:, 0],
-1), np.expand_dims(top_bboxes[:, 1], -1), np.expand_dims(
top_bboxes[:, 2],
-1), np.expand_dims(top_bboxes[:, 3], -1)
#-----------------------------------------------------------#
# 去掉灰条部分
#-----------------------------------------------------------#
boxes = retinanet_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='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):
predicted_class = self.class_names[c]
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[self.class_names.index(
predicted_class)])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=self.colors[self.class_names.index(predicted_class)])
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_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],
self.model_image_size[2]
]))
preds = self.retinanet_model.predict(photo)
# 将预测结果进行解码
results = self.bbox_util.detection_out(
preds, self.prior, confidence_threshold=self.confidence)
if len(results[0]) <= 0:
return image
results = np.array(results)
# 筛选出其中得分高于confidence的框
det_label = results[0][:, 5]
det_conf = results[0][:, 4]
det_xmin, det_ymin, det_xmax, det_ymax = results[0][:, 0], results[
0][:, 1], results[0][:, 2], results[0][:, 3]
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 = retinanet_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)]
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)])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=self.colors[int(c)])
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
#---------------------------------------------------------#
crop_img = np.array(
letterbox_image(image, [self.input_shape[1], self.input_shape[0]]))
photo = np.array(crop_img, dtype=np.float32)
photo = np.transpose(preprocess_input(photo), (2, 0, 1))
with torch.no_grad():
images = torch.from_numpy(np.asarray([photo]))
if self.cuda:
images = images.cuda()
_, regression, classification, anchors = self.net(images)
regression = decodebox(regression, anchors, images)
detection = torch.cat([regression, classification], axis=-1)
batch_detections = non_max_suppression(detection,
len(self.class_names),
conf_thres=self.confidence,
nms_thres=self.iou)
try:
batch_detections = batch_detections[0].cpu().numpy()
top_index = batch_detections[:, 4] > self.confidence
top_conf = batch_detections[top_index, 4]
top_label = np.array(batch_detections[top_index, -1], np.int32)
top_bboxes = np.array(batch_detections[top_index, :4])
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
top_bboxes[:, 0],
-1), np.expand_dims(top_bboxes[:, 1], -1), np.expand_dims(
top_bboxes[:, 2],
-1), np.expand_dims(top_bboxes[:, 3], -1)
boxes = retinanet_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.input_shape[0], self.input_shape[1]]),
image_shape)
except:
pass
t1 = time.time()
for _ in range(test_interval):
with torch.no_grad():
_, regression, classification, anchors = self.net(images)
regression = decodebox(regression, anchors, images)
detection = torch.cat([regression, classification], axis=-1)
batch_detections = non_max_suppression(
detection,
len(self.class_names),
conf_thres=self.confidence,
nms_thres=self.iou)
try:
batch_detections = batch_detections[0].cpu().numpy()
top_index = batch_detections[:, 4] > self.confidence
top_conf = batch_detections[top_index, 4]
top_label = np.array(batch_detections[top_index, -1],
np.int32)
top_bboxes = np.array(batch_detections[top_index, :4])
top_xmin, top_ymin, top_xmax, top_ymax = np.expand_dims(
top_bboxes[:, 0], -1), np.expand_dims(
top_bboxes[:, 1], -1), np.expand_dims(
top_bboxes[:, 2],
-1), np.expand_dims(top_bboxes[:, 3], -1)
boxes = retinanet_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.input_shape[0], self.input_shape[1]]),
image_shape)
except:
pass
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
