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")
image_shape = np.array(np.shape(image)[0:2])
#---------------------------------------------------------#
# 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)
#---------------------------------------------------------#
# 给图像增加灰条，实现不失真的resize
# 也可以直接resize进行识别
#---------------------------------------------------------#
image_data = resize_image(image,
(self.input_shape[1], self.input_shape[0]),
self.letterbox_image)
#---------------------------------------------------------#
# 添加上batch_size维度
#---------------------------------------------------------#
image_data = np.expand_dims(
np.transpose(
preprocess_input(np.array(image_data, dtype='float32')),
(2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.cuda()
#---------------------------------------------------------#
# 将图像输入网络当中进行预测！
#---------------------------------------------------------#
outputs = self.net(images)
outputs = self.bbox_util.decode_box(outputs)
#---------------------------------------------------------#
# 将预测框进行堆叠，然后进行非极大抑制
#---------------------------------------------------------#
results = self.bbox_util.non_max_suppression(
torch.cat(outputs, 1),
self.num_classes,
self.input_shape,
image_shape,
self.letterbox_image,
conf_thres=self.confidence,
nms_thres=self.nms_iou)
if results[0] is None:
return
top_label = np.array(results[0][:, 6], dtype='int32')
top_conf = results[0][:, 4] * results[0][:, 5]
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):
image_shape = np.array(np.shape(image)[0:2])
#---------------------------------------------------------#
# 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)
#---------------------------------------------------------#
# 给图像增加灰条，实现不失真的resize
# 也可以直接resize进行识别
#---------------------------------------------------------#
image_data = resize_image(image,
(self.input_shape[1], self.input_shape[0]),
self.letterbox_image)
#---------------------------------------------------------#
# 添加上batch_size维度
#---------------------------------------------------------#
image_data = np.expand_dims(
np.transpose(
preprocess_input(np.array(image_data, dtype='float32')),
(2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.cuda()
#---------------------------------------------------------#
# 将图像输入网络当中进行预测！
#---------------------------------------------------------#
outputs = self.net(images)
outputs = self.bbox_util.decode_box(outputs)
#---------------------------------------------------------#
# 将预测框进行堆叠，然后进行非极大抑制
#---------------------------------------------------------#
results = self.bbox_util.non_max_suppression(
torch.cat(outputs, 1),
self.num_classes,
self.input_shape,
image_shape,
self.letterbox_image,
conf_thres=self.confidence,
nms_thres=self.nms_iou)
t1 = time.time()
for _ in range(test_interval):
with torch.no_grad():
#---------------------------------------------------------#
# 将图像输入网络当中进行预测！
#---------------------------------------------------------#
outputs = self.net(images)
outputs = self.bbox_util.decode_box(outputs)
#---------------------------------------------------------#
# 将预测框进行堆叠，然后进行非极大抑制
#---------------------------------------------------------#
results = self.bbox_util.non_max_suppression(
torch.cat(outputs, 1),
self.num_classes,
self.input_shape,
image_shape,
self.letterbox_image,
conf_thres=self.confidence,
nms_thres=self.nms_iou)
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
def __getitem__(self, index):
for i, global_index in enumerate(
range(index * self.batch_size, (index + 1) * self.batch_size)):
global_index = global_index % self.length
image, boxes, mask_gt, num_crowds, image_id = self.pull_item(
global_index)
#------------------------------#
# 获得种类
#------------------------------#
class_ids = boxes[:, -1]
#------------------------------#
# 获得框的坐标
#------------------------------#
boxes = boxes[:, :-1]
image, image_meta, gt_class_ids, gt_boxes, gt_masks = \
load_image_gt(image, mask_gt, boxes, class_ids, image_id, self.config, use_mini_mask=self.config.USE_MINI_MASK)
#------------------------------#
# 初始化用于训练的内容
#------------------------------#
if i == 0:
batch_image_meta = np.zeros(
(self.batch_size, ) + image_meta.shape,
dtype=image_meta.dtype)
batch_rpn_match = np.zeros(
[self.batch_size, self.anchors.shape[0], 1],
dtype=np.int32)
batch_rpn_bbox = np.zeros([
self.batch_size, self.config.RPN_TRAIN_ANCHORS_PER_IMAGE, 4
],
dtype=np.float32)
batch_images = np.zeros((self.batch_size, ) + image.shape,
dtype=np.float32)
batch_gt_class_ids = np.zeros(
(self.batch_size, self.config.MAX_GT_INSTANCES),
dtype=np.int32)
batch_gt_boxes = np.zeros(
(self.batch_size, self.config.MAX_GT_INSTANCES, 4),
dtype=np.int32)
batch_gt_masks = np.zeros(
(self.batch_size, gt_masks.shape[0], gt_masks.shape[1],
self.config.MAX_GT_INSTANCES),
dtype=gt_masks.dtype)
if not np.any(gt_class_ids > 0):
continue
# RPN Targets
rpn_match, rpn_bbox = build_rpn_targets(image.shape, self.anchors,
gt_class_ids, gt_boxes,
self.config)
#-----------------------------------------------------------------------#
# 如果某张图片里面物体的数量大于最大值的话，则进行筛选，防止过大
#-----------------------------------------------------------------------#
if gt_boxes.shape[0] > self.config.MAX_GT_INSTANCES:
ids = np.random.choice(np.arange(gt_boxes.shape[0]),
self.config.MAX_GT_INSTANCES,
replace=False)
gt_class_ids = gt_class_ids[ids]
gt_boxes = gt_boxes[ids]
gt_masks = gt_masks[:, :, ids]
#------------------------------#
# 将当前信息加载进batch
#------------------------------#
batch_image_meta[i] = image_meta
batch_rpn_match[i] = rpn_match[:, np.newaxis]
batch_rpn_bbox[i] = rpn_bbox
batch_images[i] = preprocess_input(image.astype(np.float32))
batch_gt_class_ids[i, :gt_class_ids.shape[0]] = gt_class_ids
batch_gt_boxes[i, :gt_boxes.shape[0]] = gt_boxes
batch_gt_masks[i, :, :, :gt_masks.shape[-1]] = gt_masks
return [batch_images, batch_image_meta, batch_rpn_match, batch_rpn_bbox, batch_gt_class_ids, batch_gt_boxes, batch_gt_masks], \
[np.zeros(self.batch_size), np.zeros(self.batch_size), np.zeros(self.batch_size), np.zeros(self.batch_size), np.zeros(self.batch_size)]
def detect_image(self, image):
image_shape = np.array(np.shape(image)[0:2])
#---------------------------------------------------------#
# 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)
#---------------------------------------------------------#
# 给图像增加灰条，实现不失真的resize
# 也可以直接resize进行识别
#---------------------------------------------------------#
image_data = resize_image(image,
(self.input_shape[1], self.input_shape[0]),
self.letterbox_image)
#---------------------------------------------------------#
# 添加上batch_size维度
#---------------------------------------------------------#
image_data = np.expand_dims(
np.transpose(
preprocess_input(np.array(image_data, dtype='float32')),
(2, 0, 1)), 0)
with torch.no_grad():
images = torch.from_numpy(image_data)
if self.cuda:
images = images.cuda()
#---------------------------------------------------------#
# 将图像输入网络当中进行预测！
#---------------------------------------------------------#
outputs = self.net(images)
outputs = self.bbox_util.decode_box(outputs)
#---------------------------------------------------------#
# 将预测框进行堆叠，然后进行非极大抑制
#---------------------------------------------------------#
results = self.bbox_util.non_max_suppression(
torch.cat(outputs, 1),
self.num_classes,
self.input_shape,
image_shape,
self.letterbox_image,
conf_thres=self.confidence,
nms_thres=self.nms_iou)
if results[0] is None:
return image
top_label = np.array(results[0][:, 6], dtype='int32')
top_conf = results[0][:, 4] * results[0][:, 5]
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 * image.size[1] +
0.5).astype('int32'))
thickness = int(
max((image.size[0] + image.size[1]) // np.mean(self.input_shape),
1))
#---------------------------------------------------------#
# 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):
#---------------------------------------------------#
# 获得输入图片的高和宽
#---------------------------------------------------#
image_shape = np.array(np.shape(image)[0:2])
#---------------------------------------------------------#
# 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)
#---------------------------------------------------------#
# 给图像增加灰条，实现不失真的resize
# 也可以直接resize进行识别
#---------------------------------------------------------#
image_data = resize_image(image, (self.input_shape[1], self.input_shape[0]), self.letterbox_image)
#---------------------------------------------------------#
# 添加上batch_size维度，图片预处理，归一化。
#---------------------------------------------------------#BBoxUtility
image_data = np.expand_dims(preprocess_input(np.array(image_data, dtype='float32')), 0)
outputs = self.get_pred(image_data).numpy()
#--------------------------------------------------------------------------------------------#
# centernet后处理的过程，包括门限判断和传统非极大抑制。
# 对于centernet网络来讲，确立中心非常重要。对于大目标而言，会存在许多的局部信息。
# 此时大目标中心点比较难以确定。使用最大池化的非极大抑制方法无法去除局部框
# 这里面存在传统的nms处理方法，可以选择关闭和开启。
# 实际测试中，hourglass为主干网络时有无额外的nms相差不大，resnet相差较大。BBoxUtility
#--------------------------------------------------------------------------------------------#
results = self.bbox_util.postprocess(outputs, self.nms, image_shape, self.input_shape, self.letterbox_image, confidence=self.confidence)
#--------------------------------------#
# 如果没有检测到物体，则返回原图
#--------------------------------------#
if results[0] is None:
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]) // self.input_shape[0], 1)
#---------------------------------------------------------#
# 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