def detect_image(self, image_id, image):
self.confidence = 0.05
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.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
with torch.no_grad():
photo = Variable(
torch.from_numpy(
np.expand_dims(np.transpose(crop_img - MEANS, (2, 0, 1)),
0)).type(torch.FloatTensor))
if self.cuda:
photo = photo.cuda()
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence:
score = preds[0, i, j, 0]
label_name = self.class_names[i - 1]
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
# 将预测结果进行解码
if len(top_conf) <= 0:
return image
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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 = 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):
predicted_class = c
score = str(float(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):
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)
with torch.no_grad():
photo = Variable(torch.from_numpy(np.expand_dims(np.transpose(photo - MEANS, (2,0,1)),0)).type(torch.FloatTensor))
if self.cuda:
photo = photo.cuda()
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence:
score = preds[0, i, j, 0]
label_name = self.class_names[i-1]
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
if len(top_conf)<=0:
return
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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
#-----------------------------------------------------------#
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):
predicted_class = c
score = str(float(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 = np.array(
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 = Variable(
torch.from_numpy(
np.expand_dims(np.transpose(crop_img - MEANS, (2, 0, 1)),
0)).cuda().type(torch.FloatTensor))
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence:
score = preds[0, i, j, 0]
label_name = self.class_names[i - 1]
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
# 将预测结果进行解码
if len(top_conf) <= 0:
return image
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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 = 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):
predicted_class = 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[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 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 = np.array(
letterbox_image(image, (self.input_shape[1], self.input_shape[0])))
photo = np.array(crop_img, dtype=np.float64)
# 图片预处理，归一化
with torch.no_grad():
photo = Variable(
torch.from_numpy(
np.expand_dims(np.transpose(crop_img - MEANS, (2, 0, 1)),
0)).type(torch.FloatTensor))
if self.cuda:
photo = photo.cuda()
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence:
score = preds[0, i, j, 0]
label_name = self.class_names[i - 1]
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
# 将预测结果进行解码
if len(top_conf) > 0:
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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 = ssd_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.input_shape[0], self.input_shape[1]]),
image_shape)
t1 = time.time()
for _ in range(test_interval):
with torch.no_grad():
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence:
score = preds[0, i, j, 0]
label_name = self.class_names[i - 1]
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
# 将预测结果进行解码
if len(top_conf) > 0:
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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 = ssd_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([self.input_shape[0], self.input_shape[1]]),
image_shape)
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])
#---------------------------------------------------#
# 不失真的resize，给图像周围增加灰条
#---------------------------------------------------#
crop_img = np.array(
letterbox_image(image, (self.input_shape[1], self.input_shape[0])))
with torch.no_grad():
#---------------------------------------------------#
# 图片预处理，归一化
#---------------------------------------------------#
photo = Variable(
torch.from_numpy(
np.expand_dims(np.transpose(crop_img - MEANS, (2, 0, 1)),
0)).type(torch.FloatTensor))
if self.cuda:
photo = photo.cuda()
#---------------------------------------------------#
# 传入网络进行预测
#---------------------------------------------------#
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
#---------------------------------------------------#
# preds的shape为 1, num_classes, top_k, 5
#---------------------------------------------------#
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence:
#---------------------------------------------------#
# score为当前预测框的得分
# label_name为预测框的种类
#---------------------------------------------------#
score = preds[0, i, j, 0]
label_name = self.class_names[i - 1]
#---------------------------------------------------#
# pt的shape为4, 当前预测框的左上角右下角
#---------------------------------------------------#
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
# 如果不存在满足门限的预测框，直接返回原图
if len(top_conf) <= 0:
return image
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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 = 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='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 = 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 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)
with torch.no_grad():
photo = Variable(torch.from_numpy(np.expand_dims(np.transpose(photo-MEANS,(2,0,1)),0)).type(torch.FloatTensor))
if self.cuda:
photo = photo.cuda()
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence:
score = preds[0, i, j, 0]
label_name = self.class_names[i-1]
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
if len(top_conf)>0:
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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
#-----------------------------------------------------------#
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):
with torch.no_grad():
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence:
score = preds[0, i, j, 0]
label_name = self.class_names[i-1]
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
if len(top_conf)>0:
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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
#-----------------------------------------------------------#
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
def run(self):
#计数
count = 0
# print('{} model, anchors, and classes loaded.'.format(self.Config["model_path"]))
image_shape = np.array(np.shape(self.image)[0:2])
# letterbox_image边缘加灰条仿失真，改变总体图片大小为300*300
crop_img = np.array(
letterbox_image(self.image, (self.Config["model_image_size"][0],
self.Config["model_image_size"][1])))
# 转化float64
photo = np.array(crop_img, dtype=np.float64)
# 图片预处理，归一化
# photo = Variable(torch.from_numpy(np.expand_dims(np.transpose(crop_img-MEANS,(2,0,1)),0)).type(torch.FloatTensor)) #将通道数从第三维度调整到第一维度 ！cudaGPU加速.cuda().type(torch.FloatTensor))
# crop_img - MEANS所有像素点-平均值 相当于标准化
photo = torch.from_numpy(
np.expand_dims(np.transpose(crop_img - MEANS, (2, 0, 1)),
0)).type(torch.FloatTensor)
# preds.shape(1,21,200,5)((这张图片)bacth_size,类别num_class,得分最高200框，参数)
preds = self.net(photo)
top_conf = []
top_label = []
top_bboxes = []
# 置信度筛选
for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.Config["confidence"]:
score = preds[0, i, j, 0]
label_name = self.class_names[i - 1]
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
# 将预测结果进行解码
if len(top_conf) <= 0:
self.msg.emit("图中一共有:0 个 目标对象")
self.set_image.emit("")
self.msg.emit("预测完成")
else:
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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 = ssd_correct_boxes(
top_ymin, top_xmin, top_ymax, top_xmax,
np.array([
self.Config["model_image_size"][0],
self.Config["model_image_size"][1]
]), image_shape)
# 字体
font = ImageFont.truetype(
font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(self.image)[1] +
0.5).astype('int32'))
# 厚度
thickness = (np.shape(self.image)[0] + np.shape(
self.image)[1]) // self.Config["model_image_size"][0]
for i, c in enumerate(top_label):
count += 1
predicted_class = 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(self.image)[0],
np.floor(bottom + 0.5).astype('int32'))
right = min(
np.shape(self.image)[1],
np.floor(right + 0.5).astype('int32'))
# 画框框
label = '{} {:.2f}-{}'.format(predicted_class, score, count)
draw = ImageDraw.Draw(self.image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
self.msg.emit(str(label.decode()))
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
self.msg.emit("图中一共有:" + str(count) + " 个 目标对象")
# 可更改
self.path = "neural_network/img/predict_output.png"
self.image.save(self.path)
self.set_image.emit(self.path)
self.msg.emit("预测完成")
def detect_image(self, image):
image_shape = np.array(
np.shape(image)[0:2]) # 获得图片的尺寸array([1330, 1330])
# 在检测中，需要把原始图像转换为，与目标尺寸匹配的图像，保持等比例，其余部分用灰色填充。
crop_img = np.array(
letterbox_image(
image, (self.model_image_size[0], self.model_image_size[1])))
# 以下这行代码多余
photo = np.array(crop_img, dtype=np.float64) # 类型转为dtype = np.float64
# 图片预处理，归一化
with torch.no_grad(
): # 表示不进行求导 即使张量的requires_grad = True，也不求梯度 参考链接: https://blog.csdn.net/weixin_43178406/article/details/89517008?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522159644470619195264563535%2522%252C%2522scm%2522%253A%252220140713.130102334..%2522%257D&request_id=159644470619195264563535&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~first_rank_ecpm_v3~pc_rank_v4-4-89517008.first_rank_ecpm_v3_pc_rank_v4&utm_term=with+torch.no_grad%28%29&spm=1018.2118.3001.4187
photo = Variable(
torch.from_numpy(
np.expand_dims(np.transpose(crop_img - MEANS, (2, 0, 1)),
0)).type(
torch.FloatTensor)) # 将颜色通道对应的维度调整到前面
# 标准化 通道维度调整到最前的维度 扩充维度 移动到GPU
# 【Python】 numpy.expand_dims的用法 参考链接: https://blog.csdn.net/qingzhuyuxian/article/details/90510203?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522159645220719195188351469%2522%252C%2522scm%2522%253A%252220140713.130102334..%2522%257D&request_id=159645220719195188351469&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~top_click~default-2-90510203.first_rank_ecpm_v3_pc_rank_v4&utm_term=np.expand_dims&spm=1018.2118.3001.4187
if self.cuda:
photo = photo.cuda() # torch.Size([1, 3, 300, 300])
preds = self.net(photo) # torch.Size([1, 3, 200, 5]) 1置信度+4位置信息
#
top_conf = [] # 保存单张图片中所有预测框的置信度
top_label = [] # 保存单张图片中所有预测框的物体类别
top_bboxes = [] # 保存单张图片中所有预测框的位置信息
for i in range(
1, preds.size(1)): # 循环遍历21个类 i=0,1,2...,20 # 跳过背景所在的类,0代表背景
# for i in range(1,preds.size(1)): for i in range(preds.size(1)):
j = 0
while preds[0, i, j, 0] >= self.confidence: # 对200个不同置信度的框的筛选
# while preds[0, i, j, 0] >= self.confidence and j < preds.size(2): # 我的修改 ************************************************************************************************************************************************************************************************************************************************************************************
score = preds[0, i, j, 0]
# print("cxqcxq 陈旭旗陈旭旗self.class_names ：",self.class_names) # cxqcxq 陈旭旗陈旭旗self.class_names ： ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']
label_name = self.class_names[
i -
1] # 有疑问 为什么不是 label_name = self.class_names[i]***************************************************************************************************************
pt = (preds[0, i, j, 1:]).detach().numpy()
coords = [pt[0], pt[1], pt[2], pt[3]]
top_conf.append(score)
top_label.append(label_name)
top_bboxes.append(coords)
j = j + 1
# 将预测结果进行解码
if len(top_conf) <= 0: # 表示没有检测到任何东西，即全是背景
return image
top_conf = np.array(top_conf)
top_label = np.array(top_label)
top_bboxes = np.array(top_bboxes)
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 = 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]
# 8
for i, c in enumerate(top_label):
predicted_class = 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) # (240, 40)
label = label.encode('utf-8')
print(label)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]
]) # array([460, 654])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness): # 用于对边框加粗,起始可以使用width参数
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