分割数据预处理
作者：互联网
日常报错（累~）：
小编最近用yolact对BraTS数据集做预测，验证结果如下：
发现ET对于Dice和PPV太小了，根据公式，我一开始以为是模型预测的区域过多导致的。
后面生成图片观察：
忽然之间，意识到，是自己的target生成错了。笔者对这个三个区域，首先是采用边缘提取，获取边缘的坐标，之后进行一次判断，只保留点数大于20的区域，所以就可能出现上述图片的情况。我们真是target是由ET区域（黄色区域），但我最后生成的target是没有ET区域的。
所以再模型预测的阶段，也不会预测出ET，造成的PPV值偏小，进而Dice偏小。
如下是我生成边缘坐标（改进后，每个if价格else：continue）的部分代码：
f=open('F:/DATA/train_mask4.txt','w')
for r in tqdm(range(len(image_traintest_paths))):
# for r in tqdm(range(4)):
# 获取路径
a=0
b=0
c=0
# fold_path=mask_train_paths[r]
fold_path=mask_traintest_paths[r]
npmask=np.load(fold_path)
#print(npmask.shape)
txt_line = ''
vertices_list_WT=[]
vertices_list_ET=[]
vertices_list_TC=[]
# 获取边缘
WT_Label = npmask.copy()
WT_Label[npmask == 1] = 1.
WT_Label[npmask == 2] = 1.
WT_Label[npmask == 4] = 1.
WT_Label=WT_Label.astype(np.uint8)
WT_Label=WT_Label*255
TC_Label = npmask.copy()
TC_Label[npmask == 1] = 1.
TC_Label[npmask == 2] = 0.
TC_Label[npmask == 4] = 1.
TC_Label=TC_Label.astype(np.uint8)
TC_Label=TC_Label*255
ET_Label = npmask.copy()
ET_Label[npmask == 1] = 0.
ET_Label[npmask == 2] = 0.
ET_Label[npmask == 4] = 1
ET_Label=ET_Label.astype(np.uint8)
ET_Label=ET_Label*255
# 写入到text line
path_forward=fold_path.split('\\')[-1]
txt_line=txt_line+path_forward+" "
# 获取WT边缘坐标
detected_edges = cv2.Canny(WT_Label, lowThreshold, lowThreshold+10 * ratio, apertureSize=kernel_size)
# print(detected_edges.shape)
if SumNum(detected_edges)>20:
a=1
for i in range(detected_edges.shape[0]):
for j in range(detected_edges.shape[1]):
if detected_edges[i,j] !=0:
vertices_list_WT.append([j,i])
vertices_list_WT=np.array(vertices_list_WT)
# 获取WTbounding box
max_x_WT=np.max(vertices_list_WT[:,0])
max_y_WT=np.max(vertices_list_WT[:,1])
min_x_WT=np.min(vertices_list_WT[:,0])
min_y_WT=np.min(vertices_list_WT[:,1])
# 添加WT bounding box , vertices
txt_line=txt_line+ str(min_x_WT)+','+str(min_y_WT)+','+str(max_x_WT)+','+str(max_y_WT)+','+'1'+','
for i in range(len(vertices_list_WT)):
txt_line=txt_line+str(vertices_list_WT[i][0])+','
txt_line=txt_line+str(vertices_list_WT[i][1])+','
txt_line=txt_line[:-1]+" "
else:continue
# 获取TC边缘坐标
detected_edges = cv2.Canny(TC_Label, lowThreshold, lowThreshold+10 * ratio, apertureSize=kernel_size)
if SumNum(detected_edges)>20:
b=1
for i in range(detected_edges.shape[0]):
for j in range(detected_edges.shape[1]):
if detected_edges[i,j] !=0:
vertices_list_TC.append([j,i])
vertices_list_TC=np.array(vertices_list_TC)
max_x_TC=np.max(vertices_list_TC[:,0])
max_y_TC=np.max(vertices_list_TC[:,1])
min_x_TC=np.min(vertices_list_TC[:,0])
min_y_TC=np.min(vertices_list_TC[:,1])
# 添加TC bounding box, vertices
txt_line=txt_line+ str(min_x_TC)+','+str(min_y_TC)+','+str(max_x_TC)+','+str(max_y_TC)+','+'2'+','
for i in range(len(vertices_list_TC)):
txt_line=txt_line+str(vertices_list_TC[i][0])+','
txt_line=txt_line+str(vertices_list_TC[i][1])+','
txt_line=txt_line[:-1]+" "
else:continue
# 获取ET边缘坐标
detected_edges = cv2.Canny(ET_Label, lowThreshold, lowThreshold+10 * ratio, apertureSize=kernel_size)
if SumNum(detected_edges)>20:
c=1
for i in range(detected_edges.shape[0]):
for j in range(detected_edges.shape[1]):
if detected_edges[i,j] !=0:
vertices_list_ET.append([j,i])
vertices_list_ET=np.array(vertices_list_ET)
max_x_ET=np.max(vertices_list_ET[:,0])
max_y_ET=np.max(vertices_list_ET[:,1])
min_x_ET=np.min(vertices_list_ET[:,0])
min_y_ET=np.min(vertices_list_ET[:,1])
# 添加ET bounding box, vertices
txt_line=txt_line+ str(min_x_ET)+','+str(min_y_ET)+','+str(max_x_ET)+','+str(max_y_ET)+','+'3'+','
for i in range(len(vertices_list_ET)):
txt_line=txt_line+str(vertices_list_ET[i][0])+','
txt_line=txt_line+str(vertices_list_ET[i][1])+','
else:continue
txt_line=txt_line[:-1]+'\n'
if (a==b==c==0):
continue
f.write(txt_line)
f.close()
不知再次训练结果会怎样。。。
标签：分割,list,vertices,TC,WT,ET,txt,数据,预处理 来源： https://www.cnblogs.com/a-runner/p/14878741.html