医学图像九分类
发布时间
阅读量：
阅读量
在上一次分类的基础上将二分类扩展为九分类。
切割图片为2000*2000，space=2000，按类别放在patch文件夹中。
要将整个数据集划分为训练集和测试集。
下面是两种方法划分数据集：
方法1：将源文件夹和目标文件夹相互对应起来，根据图片在文件夹中的位置索引，来判断是放在训练集，还是测试集。
import os
import shutil
path="/home/cad429/code/yue/Week2/patch"
name_list=os.listdir(path)
print(name_list)
train_dir="/home/cad429/code/yue/Week2/train"
if not os.path.exists(train_dir):
os.makedirs(train_dir)
test_dir="/home/cad429/code/yue/Week2/test"
if not os.path.exists(test_dir):
os.makedirs(test_dir)
val_dir="/home/cad429/code/yue/Week2/val"
if not os.path.exists(val_dir):
os.makedirs(val_dir)
for i in range(len(name_list)):
patch_path=os.path.join(path,name_list[i])
print(patch_path)
patch_list=os.listdir(patch_path)
print(patch_list)
patch_name_list = [i.split('.')[0] for i in patch_list]
print(patch_name_list)
print(len(patch_name_list))
for j in range(len(patch_name_list)):
original_path = os.path.join(patch_path, patch_name_list[j] + ".png")
# print(original_path)
des_path = os.path.join(train_dir, name_list[i])
des_path2=os.path.join(test_dir,name_list[i])
if j%2==0:
#print(des_path)
shutil.copy(original_path,des_path)
else:
shutil.copy(original_path,des_path2)
AI写代码方法2：利用sklearn中带有的划分数据集的方法，将每个类别中的图片的名字按照一定的比例划分到x_train,x_test.
from sklearn.model_selection import train_test_split
import numpy as np
import os
import shutil
split_train="/home/cad429/code/yue/Week2/splittrain"
if not os.path.exists(split_train):
os.makedirs(split_train)
split_test="/home/cad429/code/yue/Week2/splittest"
if not os.path.exists(split_test):
os.makedirs(split_test)
Image_path="/home/cad429/code/yue/Week2/patch"
Image_list=os.listdir(Image_path)
for i in Image_list:#对应的0，1，2，3，4...
path=os.path.join(Image_path,i)
imag=os.listdir(path)
imag_name=[j.split('.')[0] for j in imag]
x_train,x_test=train_test_split(imag_name,test_size=0.3)
print("i:",i)
# print("x_train list:",x_train)
# print("x_test list:",x_test)
#将图片归到对应的train文件夹
for er in x_train:
train_image_path=os.path.join(split_train,i,er+".png")
train_image_original_path=os.path.join(path,er+".png")
#print("destination",train_image_path)
#print("original:",train_image_original_path)
shutil.copy(train_image_original_path,train_image_path)
for es in x_test:
test_image_path=os.path.join(split_test,i,es+".png")
test_image_original_path=os.path.join(path,es+".png")
shutil.copy(test_image_original_path,test_image_path)
# print("original:",test_image_original_path)
# print("destination:",test_image_path)
AI写代码图片大小为2000*2000，batch_size=2,learnning_rate=0.01，epoch=100,损失函数为CrossEntropyLoss，优化 函数为Adam时的训练结果：
测试的结果：
控制变量法做对比试验：将图片切为2000*2000，spacing=1000,learnning_rate=0.01,损失函数为CrossEntropyLoss，优化函数为Adam的
训练 结果：
测试结果：
测试结果显示，过拟合，要增加一个验证集，监控模型 是否发生过拟合，来决定是否停止训练。
将train的训练集的图片划分一部分到验证集。
import os
import shutil
import random
from sklearn.model_selection import train_test_split
def move_train_to_val(train_path,val_path,train2_path):
class_list=os.listdir(train_path)
print(class_list)
for i in class_list:
print(i)
class_path=os.path.join(train_path,i)
Image_list=os.listdir(class_path)
Image_len=len(Image_list)
Image_name=[j.split('.')[0] for j in Image_list]
train_name,val_name=train_test_split(Image_name)
for valname in val_name:
original=os.path.join(class_path,valname+".png")
val_image_path=os.path.join(val_path,i,valname+".png")
shutil.move(original,val_image_path)
# print("original:", original)
# print("vallllll:", val_image_path)
for trainname in train_name:
trainoriginal=os.path.join(class_path,trainname+".png")
#print("trainoriginal:",trainoriginal)
train2_image_path=os.path.join(train2_path,i,trainname+".png")
shutil.move(trainoriginal,train2_image_path)
# print("original",trainoriginal)
# print("train2",train2_image_path)
if __name__=="__main__":
train_path="/home/cad429/code/yue/Week2/train"
val_path="/home/cad429/code/yue/Week2/val"
train2_path="/home/cad429/code/yue/Week2/train2"
move_train_to_val(train_path,val_path,train2_path)
AI写代码将添加的新的验证集用来判断是否结束训练，然后用测试集来测试训练的模型。
结果：
全部评论 (0)
还没有任何评论哟~