1、使用torch中内置的数据集
在定义的时候已经完成好了划分,不需要人为划分
train_dataset = datasets.CIFAR10(data_dir, train=True, download=True,
transform=apply_transform)
test_dataset = datasets.CIFAR10(data_dir, train=False, download=True,
transform=apply_transform)
2、使用train_test_split函数(交叉验证常用的函数)
train_test_split()函数是用来随机划分样本数据为训练集和测试集
(1)
train_X,test_X,train_y,test_y = train_test_split(train_data,train_target,test_size=0.3,random_state=5)
train_data:待划分样本数据
train_target:待划分样本数据的结果(标签)
test_size:测试数据占样本数据的比例,若整数则样本数量
random_state:设置随机数种子,保证每次都是同一个随机数。若为0或不填,则每次得到数据都不一样
(2)
x_train, x_val, label_train, label_val = train_test_split(x_data, label_data, test_size=0.1)
3、自定义read_split_data函数 实现数据集的划分
def read_split_data(root: str, val_rate: float = 0.2): #val_rate划分验证集所占所有用户的比例
random.seed(0) # 保证随机结果可复现
assert os.path.exists(root), "dataset root: {} does not exist.".format(root)#判断路径是否存在
# 遍历文件夹,一个文件夹对应一个类别
flower_class = [cla for cla in os.listdir(root) if os.path.isdir(os.path.join(root, cla))]
# 排序,保证顺序一致
flower_class.sort()
# 生成类别名称以及对应的数字索引
class_indices = dict((k, v) for v, k in enumerate(flower_class))
json_str = json.dumps(dict((val, key) for key, val in class_indices.items()), indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
train_images_path = [] # 存储训练集的所有图片路径
train_images_label = [] # 存储训练集图片对应索引信息
val_images_path = [] # 存储验证集的所有图片路径
val_images_label = [] # 存储验证集图片对应索引信息
every_class_num = [] # 存储每个类别的样本总数
supported = [".jpg", ".JPG", ".png", ".PNG"] # 支持的文件后缀类型
# 遍历每个文件夹下的文件
for cla in flower_class:
cla_path = os.path.join(root, cla)
# 遍历获取supported支持的所有文件路径
images = [os.path.join(root, cla, i) for i in os.listdir(cla_path)
if os.path.splitext(i)[-1] in supported]
# 获取该类别对应的索引
image_class = class_indices[cla]
# 记录该类别的样本数量
every_class_num.append(len(images))
# 按比例随机采样验证样本
val_path = random.sample(images, k=int(len(images) * val_rate))
for img_path in images:
if img_path in val_path: # 如果该路径在采样的验证集样本中则存入验证集
val_images_path.append(img_path)
val_images_label.append(image_class)
else: # 否则存入训练集
train_images_path.append(img_path)
train_images_label.append(image_class)
print("{} images were found in the dataset.".format(sum(every_class_num)))
print("{} images for training.".format(len(train_images_path)))
print("{} images for validation.".format(len(val_images_path)))
plot_image = False
#plot_image = True
if plot_image:
# 绘制每种类别个数柱状图
plt.bar(range(len(flower_class)), every_class_num, align='center')
# 将横坐标0,1,2,3,4替换为相应的类别名称
plt.xticks(range(len(flower_class)), flower_class)
# 在柱状图上添加数值标签
for i, v in enumerate(every_class_num):
plt.text(x=i, y=v + 5, s=str(v), ha='center')
# 设置x坐标
plt.xlabel('image class')
# 设置y坐标
plt.ylabel('number of images')
# 设置柱状图的标题
plt.title('flower class distribution')
plt.show()
return train_images_path, train_images_label, val_images_path, val_images_label