def detect_image(self, image_id, image):
self.confidence = 0.01
self.iou = 0.45
f = open("./input/detection-results/" + image_id + ".txt", "w")
image_shape = np.array(np.shape(image)[0:2])
old_width, old_height = image_shape[1], image_shape[0]
old_image = copy.deepcopy(image)
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
photo = np.transpose(
np.array(image, dtype=np.float32) / 255, (2, 0, 1))
with torch.no_grad():
images = torch.from_numpy(np.asarray([photo]))
if self.cuda:
images = images.cuda()
roi_cls_locs, roi_scores, rois, _ = self.model(images)
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
outputs = self.decodebox.forward(roi_cls_locs[0],
roi_scores[0],
rois,
height=height,
width=width,
nms_iou=self.iou,
score_thresh=self.confidence)
#---------------------------------------------------------#
# 如果没有检测出物体，返回原图
#---------------------------------------------------------#
if len(outputs) == 0:
return old_image
outputs = np.array(outputs)
bbox = outputs[:, :4]
label = outputs[:, 4]
conf = outputs[:, 5]
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
for i, c in enumerate(label):
predicted_class = self.class_names[int(c)]
score = str(conf[i])
left, top, right, bottom = bbox[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 get_FPS(self, image, test_interval):
image_shape = np.array(np.shape(image)[0:2])
old_width, old_height = image_shape[1], image_shape[0]
old_image = copy.deepcopy(image)
#---------------------------------------------------------#
# 给原图像进行resize，resize到短边为600的大小上
#---------------------------------------------------------#
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
photo = np.transpose(
np.array(image, dtype=np.float32) / 255, (2, 0, 1))
with torch.no_grad():
images = torch.from_numpy(np.asarray([photo]))
if self.cuda:
images = images.cuda()
roi_cls_locs, roi_scores, rois, _ = self.model(images)
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
outputs = self.decodebox.forward(roi_cls_locs[0],
roi_scores[0],
rois,
height=height,
width=width,
nms_iou=self.iou,
score_thresh=self.confidence)
#---------------------------------------------------------#
# 如果没有检测出物体，返回原图
#---------------------------------------------------------#
if len(outputs) > 0:
outputs = np.array(outputs)
bbox = outputs[:, :4]
label = outputs[:, 4]
conf = outputs[:, 5]
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
t1 = time.time()
for _ in range(test_interval):
with torch.no_grad():
roi_cls_locs, roi_scores, rois, _ = self.model(images)
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
outputs = self.decodebox.forward(roi_cls_locs[0],
roi_scores[0],
rois,
height=height,
width=width,
nms_iou=self.iou,
score_thresh=self.confidence)
#---------------------------------------------------------#
# 如果没有检测出物体，返回原图
#---------------------------------------------------------#
if len(outputs) > 0:
outputs = np.array(outputs)
bbox = outputs[:, :4]
label = outputs[:, 4]
conf = outputs[:, 5]
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
def detect_image(self, image):
image_shape = np.array(np.shape(image)[0:2])
old_width, old_height = image_shape[1], image_shape[0]
old_image = copy.deepcopy(image)
#---------------------------------------------------------#
# 给原图像进行resize，resize到短边为600的大小上
#---------------------------------------------------------#
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
photo = np.transpose(
np.array(image, dtype=np.float32) / 255, (2, 0, 1))
with torch.no_grad():
images = torch.from_numpy(np.asarray([photo]))
if self.cuda:
images = images.cuda()
roi_cls_locs, roi_scores, rois, _ = self.model(images)
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
outputs = self.decodebox.forward(roi_cls_locs[0],
roi_scores[0],
rois,
height=height,
width=width,
nms_iou=self.iou,
score_thresh=self.confidence)
#---------------------------------------------------------#
# 如果没有检测出物体，返回原图
#---------------------------------------------------------#
if len(outputs) == 0:
return old_image
outputs = np.array(outputs)
bbox = outputs[:, :4]
label = outputs[:, 4]
conf = outputs[:, 5]
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
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(old_image)[0] + np.shape(old_image)[1]) // old_width * 2,
1)
image = old_image
for i, c in enumerate(label):
predicted_class = self.class_names[int(c)]
score = conf[i]
left, top, right, bottom = bbox[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)])
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_map_txt(self, image_id, image, class_names, map_out_path):
f = open(
os.path.join(map_out_path,
"detection-results/" + image_id + ".txt"), "w")
#---------------------------------------------------#
# 计算输入图片的高和宽
#---------------------------------------------------#
image_shape = np.array(np.shape(image)[0:2])
input_shape = get_new_img_size(image_shape[0], image_shape[1])
#---------------------------------------------------------#
# 在这里将图像转换成RGB图像，防止灰度图在预测时报错。
# 代码仅仅支持RGB图像的预测，所有其它类型的图像都会转化成RGB
#---------------------------------------------------------#
image = cvtColor(image)
#---------------------------------------------------------#
# 给原图像进行resize，resize到短边为600的大小上
#---------------------------------------------------------#
image_data = resize_image(image, [input_shape[1], input_shape[0]])
#---------------------------------------------------------#
# 添加上batch_size维度
#---------------------------------------------------------#
image_data = np.expand_dims(
preprocess_input(np.array(image_data, dtype='float32')), 0)
#---------------------------------------------------------#
# 获得rpn网络预测结果和base_layer
#---------------------------------------------------------#
rpn_pred = self.model_rpn(image_data)
rpn_pred = [x.numpy() for x in rpn_pred]
#---------------------------------------------------------#
# 生成先验框并解码
#---------------------------------------------------------#
anchors = get_anchors(input_shape, self.backbone, self.anchors_size)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
#-------------------------------------------------------------#
# 利用建议框获得classifier网络预测结果
#-------------------------------------------------------------#
classifier_pred = self.model_classifier(
[rpn_pred[2], rpn_results[:, :, [1, 0, 3, 2]]])
classifier_pred = [x.numpy() for x in classifier_pred]
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(
classifier_pred, rpn_results, image_shape, input_shape,
self.confidence)
#--------------------------------------#
# 如果没有检测到物体，则返回原图
#--------------------------------------#
if len(results[0]) <= 0:
return
top_label = np.array(results[0][:, 5], dtype='int32')
top_conf = results[0][:, 4]
top_boxes = results[0][:, :4]
for i, c in list(enumerate(top_label)):
predicted_class = self.class_names[int(c)]
box = top_boxes[i]
score = str(top_conf[i])
top, left, bottom, right = box
if predicted_class not in class_names:
continue
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 get_FPS(self, image, test_interval):
#---------------------------------------------------#
# 计算输入图片的高和宽
#---------------------------------------------------#
image_shape = np.array(np.shape(image)[0:2])
input_shape = get_new_img_size(image_shape[0], image_shape[1])
#---------------------------------------------------------#
# 在这里将图像转换成RGB图像，防止灰度图在预测时报错。
# 代码仅仅支持RGB图像的预测，所有其它类型的图像都会转化成RGB
#---------------------------------------------------------#
image = cvtColor(image)
#---------------------------------------------------------#
# 给原图像进行resize，resize到短边为600的大小上
#---------------------------------------------------------#
image_data = resize_image(image, [input_shape[1], input_shape[0]])
#---------------------------------------------------------#
# 添加上batch_size维度
#---------------------------------------------------------#
image_data = np.expand_dims(
preprocess_input(np.array(image_data, dtype='float32')), 0)
#---------------------------------------------------------#
# 获得rpn网络预测结果和base_layer
#---------------------------------------------------------#
rpn_pred = self.model_rpn(image_data)
rpn_pred = [x.numpy() for x in rpn_pred]
#---------------------------------------------------------#
# 生成先验框并解码
#---------------------------------------------------------#
anchors = get_anchors(input_shape, self.backbone, self.anchors_size)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
#-------------------------------------------------------------#
# 利用建议框获得classifier网络预测结果
#-------------------------------------------------------------#
classifier_pred = self.model_classifier(
[rpn_pred[2], rpn_results[:, :, [1, 0, 3, 2]]])
classifier_pred = [x.numpy() for x in classifier_pred]
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(
classifier_pred, rpn_results, image_shape, input_shape,
self.confidence)
t1 = time.time()
for _ in range(test_interval):
#---------------------------------------------------------#
# 获得rpn网络预测结果和base_layer
#---------------------------------------------------------#
rpn_pred = self.model_rpn(image_data)
rpn_pred = [x.numpy() for x in rpn_pred]
#---------------------------------------------------------#
# 生成先验框并解码
#---------------------------------------------------------#
anchors = get_anchors(input_shape, self.backbone,
self.anchors_size)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
temp_ROIs = rpn_results[:, :, [1, 0, 3, 2]]
#-------------------------------------------------------------#
# 利用建议框获得classifier网络预测结果
#-------------------------------------------------------------#
classifier_pred = self.model_classifier([rpn_pred[2], temp_ROIs])
classifier_pred = [x.numpy() for x in classifier_pred]
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(
classifier_pred, rpn_results, image_shape, input_shape,
self.confidence)
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
def detect_image(self, image, crop=False):
#---------------------------------------------------#
# 计算输入图片的高和宽
#---------------------------------------------------#
image_shape = np.array(np.shape(image)[0:2])
#---------------------------------------------------#
# 计算输入到网络中进行运算的图片的高和宽
# 保证短边是600的
#---------------------------------------------------#
input_shape = get_new_img_size(image_shape[0], image_shape[1])
#---------------------------------------------------------#
# 在这里将图像转换成RGB图像，防止灰度图在预测时报错。
# 代码仅仅支持RGB图像的预测，所有其它类型的图像都会转化成RGB
#---------------------------------------------------------#
image = cvtColor(image)
#---------------------------------------------------------#
# 给原图像进行resize，resize到短边为600的大小上
#---------------------------------------------------------#
image_data = resize_image(image, [input_shape[1], input_shape[0]])
#---------------------------------------------------------#
# 添加上batch_size维度
#---------------------------------------------------------#
image_data = np.expand_dims(
preprocess_input(np.array(image_data, dtype='float32')), 0)
#---------------------------------------------------------#
# 获得rpn网络预测结果和base_layer
#---------------------------------------------------------#
rpn_pred = self.model_rpn(image_data)
rpn_pred = [x.numpy() for x in rpn_pred]
#---------------------------------------------------------#
# 生成先验框并解码
#---------------------------------------------------------#
anchors = get_anchors(input_shape, self.backbone, self.anchors_size)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
#-------------------------------------------------------------#
# 利用建议框获得classifier网络预测结果
#-------------------------------------------------------------#
classifier_pred = self.model_classifier(
[rpn_pred[2], rpn_results[:, :, [1, 0, 3, 2]]])
classifier_pred = [x.numpy() for x in classifier_pred]
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(
classifier_pred, rpn_results, image_shape, input_shape,
self.confidence)
if len(results[0]) == 0:
return image
top_label = np.array(results[0][:, 5], dtype='int32')
top_conf = results[0][:, 4]
top_boxes = results[0][:, :4]
#---------------------------------------------------------#
# 设置字体与边框厚度
#---------------------------------------------------------#
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]) // input_shape[0], 1)
#---------------------------------------------------------#
# 是否进行目标的裁剪
#---------------------------------------------------------#
if crop:
for i, c in list(enumerate(top_label)):
top, left, bottom, right = top_boxes[i]
top = max(0, np.floor(top).astype('int32'))
left = max(0, np.floor(left).astype('int32'))
bottom = min(image.size[1], np.floor(bottom).astype('int32'))
right = min(image.size[0], np.floor(right).astype('int32'))
dir_save_path = "img_crop"
if not os.path.exists(dir_save_path):
os.makedirs(dir_save_path)
crop_image = image.crop([left, top, right, bottom])
crop_image.save(os.path.join(dir_save_path,
"crop_" + str(i) + ".png"),
quality=95,
subsampling=0)
print("save crop_" + str(i) + ".png to " + dir_save_path)
#---------------------------------------------------------#
# 图像绘制
#---------------------------------------------------------#
for i, c in list(enumerate(top_label)):
predicted_class = self.class_names[int(c)]
box = top_boxes[i]
score = top_conf[i]
top, left, bottom, right = box
top = max(0, np.floor(top).astype('int32'))
left = max(0, np.floor(left).astype('int32'))
bottom = min(image.size[1], np.floor(bottom).astype('int32'))
right = min(image.size[0], np.floor(right).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, 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[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
return image
def detect_image(self, image):
with torch.no_grad():
start_time = time.time()
image_shape = np.array(np.shape(image)[0:2])
old_width = image_shape[1]
old_height = image_shape[0]
old_image = copy.deepcopy(image)
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
photo = np.array(image, dtype=np.float32) / 255
photo = np.transpose(photo, (2, 0, 1))
images = []
images.append(photo)
images = np.asarray(images)
images = torch.from_numpy(images)
if self.cuda:
images = images.cuda()
roi_cls_locs, roi_scores, rois, roi_indices = self.model(images)
decodebox = DecodeBox(self.std, self.mean, self.num_classes)
outputs = decodebox.forward(roi_cls_locs, roi_scores, rois, height=height, width=width, nms_iou=self.iou,
score_thresh=self.confidence)
if len(outputs) == 0:
return old_image
bbox = outputs[:, :4]
conf = outputs[:, 4]
label = outputs[:, 5]
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
bbox = np.array(bbox, np.int32)
image = old_image
thickness = (np.shape(old_image)[0] + np.shape(old_image)[1]) // old_width * 2
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] + 0.5).astype('int32'))
for i, c in enumerate(label):
predicted_class = self.class_names[int(c)]
score = conf[i]
left, top, right, bottom = bbox[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
print("time:", time.time() - start_time)
return image