EPOCH_LENGTH = 2000
NUM_CLASSES = 20
IMAGE_SHAPE = [600,600,3]
BACKBONE = "resnet50"
model = FasterRCNN(NUM_CLASSES,backbone=BACKBONE).cuda()
#-------------------------------------------#
# 权值文件的下载请看README
#-------------------------------------------#
print('Loading weights into state dict...')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model_dict = model.state_dict()
pretrained_dict = torch.load("model_data/voc_weights_resnet.pth", map_location=device)
pretrained_dict = {k: v for k, v in pretrained_dict.items() if np.shape(model_dict[k]) == np.shape(v)}
model_dict.update(pretrained_dict)
model.load_state_dict(model_dict)
print('Finished!')
cudnn.benchmark = True
# 0.1用于验证，0.9用于训练
val_split = 0.1
with open(annotation_path) as f:
lines = f.readlines()
np.random.seed(10101)
np.random.shuffle(lines)
np.random.seed(None)
num_val = int(len(lines)*val_split)
num_train = len(lines) - num_val
class FRCNN2(object):
_defaults = {
"model_path": 'logs/Epoch49-Total_Loss0.3838-Val_Loss0.4336.pth',
"classes_path": 'model_data/voc_classes.txt',
"confidence": 0.6,
"backbone": "resnet50"
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
# ---------------------------------------------------#
# 初始化faster RCNN
# ---------------------------------------------------#
def __init__(self, **kwargs):
self.__dict__.update(self._defaults)
self.class_names = self._get_class()
self.generate()
self.mean = torch.Tensor([0, 0, 0,
0]).cuda().repeat(self.num_classes + 1)[None]
self.std = torch.Tensor([0.1, 0.1, 0.2, 0.2
]).cuda().repeat(self.num_classes + 1)[None]
# ---------------------------------------------------#
# 获得所有的分类
# ---------------------------------------------------#
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
# ---------------------------------------------------#
# 获得所有的分类
# ---------------------------------------------------#
def generate(self):
# 计算总的种类
self.num_classes = len(self.class_names)
# 载入模型，如果原来的模型里已经包括了模型结构则直接载入。
# 否则先构建模型再载入
self.model = FasterRCNN(self.num_classes,
"predict",
backbone=self.backbone).cuda()
self.model.load_state_dict(torch.load(self.model_path))
cudnn.benchmark = True
print('{} model, anchors, and classes loaded.'.format(self.model_path))
# 画框设置不同的颜色
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
# ---------------------------------------------------#
# 检测图片
# ---------------------------------------------------#
def detect_image(self, image_id, image, savepath):
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])
photo = np.array(image, dtype=np.float32) / 255
photo = np.transpose(photo, (2, 0, 1))
with torch.no_grad():
images = []
images.append(photo)
images = np.asarray(images)
images = torch.from_numpy(images).cuda()
roi_cls_locs, roi_scores, rois, roi_indices, feature = self.model(
images)
decodebox = DecodeBox(self.std, self.mean, self.num_classes)
outputs = decodebox.forward(roi_cls_locs,
roi_scores,
rois,
feature,
height=height,
width=width,
score_thresh=self.confidence)
if len(outputs) == 0:
return old_image
if np.size(outputs, 0) > 4:
outputs = outputs[np.argsort(outputs[:, 4])]
outputs = outputs[-4:, :]
bbox = outputs[:, :4]
conf = outputs[:, 4]
label = outputs[:, 5]
f = outputs[:, 6:]
f_size = np.size(f, 0)
if f_size < 4:
k = 4 - f_size
cc = 0
for lab in label:
if (lab == 1) or (lab == 3) or (lab == 5):
conbin_f = f[cc, :]
conbin_f = conbin_f.reshape(1, 2048)
for num in range(0, k):
f = np.append(f, conbin_f, axis=0)
break
cc = cc + 1
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
bbox = np.array(bbox, np.int32)
f = np.array(f, np.float32).reshape((4, 2048))
print(np.size(f))
# 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
#
# image.save(savepath)
if np.size(f, 0) != 4:
print(
"xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
)
return {
'image_id': image_id,
'image_h': height,
'image_w': width,
'num_boxes': np.size(bbox, 0),
'boxes': base64.b64encode(bbox),
'features': base64.b64encode(f)
}
class FRCNN(object):
_defaults = {
"model_path": 'model_data/voc_weights_resnet.pth',
"classes_path": 'model_data/voc_classes.txt',
"confidence": 0.5,
"backbone": "resnet50"
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
#---------------------------------------------------#
# 初始化faster RCNN
#---------------------------------------------------#
def __init__(self, **kwargs):
self.__dict__.update(self._defaults)
self.class_names = self._get_class()
self.generate()
self.mean = torch.Tensor([0, 0, 0,
0]).cuda().repeat(self.num_classes + 1)[None]
self.std = torch.Tensor([0.1, 0.1, 0.2, 0.2
]).cuda().repeat(self.num_classes + 1)[None]
#---------------------------------------------------#
# 获得所有的分类
#---------------------------------------------------#
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
#---------------------------------------------------#
# 获得所有的分类
#---------------------------------------------------#
def generate(self):
# 计算总的种类
self.num_classes = len(self.class_names)
# 载入模型，如果原来的模型里已经包括了模型结构则直接载入。
# 否则先构建模型再载入
self.model = FasterRCNN(self.num_classes,
"predict",
backbone=self.backbone).cuda()
self.model.load_state_dict(torch.load(self.model_path))
cudnn.benchmark = True
print('{} model, anchors, and classes loaded.'.format(self.model_path))
# 画框设置不同的颜色
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
#---------------------------------------------------#
# 检测图片
#---------------------------------------------------#
def detect_image(self, image):
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])
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).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,
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
class FRCNN(object):
_defaults = {
"model_path": 'model_data/voc_weights_resnet.pth',
"classes_path": 'model_data/voc_classes.txt',
"confidence": 0.5,
"iou": 0.3,
"backbone": "resnet50",
"cuda": True,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
#初始化程序
def __init__(self, **kwargs):
self.__dict__.update(self._defaults)
self.class_names = self._get_class()
self.generate()
self.mean = torch.Tensor([0, 0, 0,
0]).repeat(self.num_classes + 1)[None]
self.std = torch.Tensor([0.1, 0.1, 0.2,
0.2]).repeat(self.num_classes + 1)[None]
if self.cuda:
self.mean = self.mean.cuda()
self.std = self.std.cuda()
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def generate(self):
self.num_classes = len(self.class_names)
#载入模型
self.model = FasterRCNN(self.num_classes,
"predict",
backbone=self.backbone)
print('Loading weights into state dict...')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
state_dict = torch.load(self.model_path, map_location=device)
self.model.load_state_dict(state_dict)
self.model = self.model.eval()
if self.cuda:
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
self.model = nn.DataParallel(self.model)
self.model = self.model.cuda()
print('{} model, anchors, and classes loaded.'.format(self.model_path))
#目标定位并画框
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
#检测图片
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()
#非凸性优化，边界框矫正
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'))
#图片输出
label = '{}'.format(predicted_class)
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
class FRCNN(object):
_defaults = {
"model_path": 'model_data/voc_weights_resnet.pth',
"classes_path": 'model_data/voc_classes.txt',
"confidence": 0.8,
"iou": 0.3,
"backbone": "vgg16",
"cuda": True,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
#---------------------------------------------------#
# 初始化faster RCNN
#---------------------------------------------------#
def __init__(self, **kwargs):
self.__dict__.update(self._defaults)
self.class_names = self._get_class()
self.generate()
self.mean = torch.Tensor([0, 0, 0,
0]).repeat(self.num_classes + 1)[None]
self.std = torch.Tensor([0.1, 0.1, 0.2,
0.2]).repeat(self.num_classes + 1)[None]
if self.cuda:
self.mean = self.mean.cuda()
self.std = self.std.cuda()
self.decodebox = DecodeBox(self.std, self.mean, self.num_classes)
#---------------------------------------------------#
# 获得所有的分类
#---------------------------------------------------#
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
#---------------------------------------------------#
# 载入模型
#---------------------------------------------------#
def generate(self):
#-------------------------------#
# 计算总的类的数量
#-------------------------------#
self.num_classes = len(self.class_names)
#-------------------------------#
# 载入模型与权值
#-------------------------------#
self.model = FasterRCNN(self.num_classes,
"predict",
backbone=self.backbone).eval()
print('Loading weights into state dict...')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
state_dict = torch.load(self.model_path, map_location=device)
self.model.load_state_dict(state_dict)
if self.cuda:
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
# self.model = nn.DataParallel(self.model)
self.model = self.model.cuda()
print('{} model, anchors, and classes loaded.'.format(self.model_path))
# 画框设置不同的颜色
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
#---------------------------------------------------#
# 检测图片
#---------------------------------------------------#
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'))
# draw bbox
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