基于pytorch的CNN识别sklearn自带手写体数据，准确率贼高

import torch
from torch.autograd import Variable
import matplotlib.pyplot as plt
from sklearn import datasets
from torch import nn
from sklearn.model_selection import train_test_split

digits = datasets.load_digits()

X = digits.images
y = digits.target

X_train = X[:1700, :, :]
Y_train = y[:1700]

X_test = X[1700:, :, :]
y_test = y[1700:]


X_train = torch.Tensor(X_train).unsqueeze(0).unsqueeze(0).view(-1, 1, 8, 8)
Y_train = torch.Tensor(Y_train).long()

X_test = torch.Tensor(X_test).unsqueeze(0).unsqueeze(0).view(-1, 1, 8, 8)
y_test = torch.Tensor(y_test).long()

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 25, kernel_size=(2, 2)),
            nn.BatchNorm2d(25),
            nn.ReLU(inplace=True)
        )

        self.layer2 = nn.Sequential(
            nn.MaxPool2d(kernel_size=(1, 1), stride=2)
        )

        self.layer3 = nn.Sequential(
            nn.Conv2d(25, 50, kernel_size=(1, 1)),
            nn.BatchNorm2d(50),
            nn.ReLU(inplace=True)
        )

        self.layer4 = nn.Sequential(
            nn.MaxPool2d(kernel_size=2, stride=2)
        )

        self.fc = nn.Sequential(
            nn.Linear(200, 1024),
            nn.ReLU(inplace=True),
            nn.Linear(1024, 128),
            nn.ReLU(inplace=True),
            nn.Linear(128, 10)
        )

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

model = CNN()
print(model)
loss_func = torch.nn.CrossEntropyLoss()
opt = torch.optim.Adam(model.parameters(), lr=0.001)

loss_count = []
for epoch in range(1):
    for i in range(500):
        batch_x = Variable(X_train)             # torch.Size([128, 1, 28, 28])
        batch_y = Variable(Y_train).view(-1)    # torch.Size([128])

        out = model(batch_x)              # torch.Size([128,10])
        # 获取损失
        loss = loss_func(out, batch_y)
        # 使用优化器优化损失
        opt.zero_grad()   # 清空上一步残余更新参数值
        loss.backward()   # 误差反向传播，计算参数更新值
        opt.step()        # 将参数更新值施加到net的parmeters上

        loss_count.append(loss)
        print('{}:\t'.format(i), loss.item())
        torch.save(model, r'C:\Users\Administrator\PycharmProjects\data\cnn')

plt.figure('PyTorch_CNN_Loss')
plt.plot(loss_count, label='Loss')
plt.legend()
plt.show()

model = torch.load(r'C:\Users\Administrator\PycharmProjects\data\cnn')
accuracy_sum = []

test_x = Variable(X_test)
test_y = Variable(y_test)
out = model(test_x)

accuracy = torch.max(out, 1)[1].numpy() == test_y.numpy()
accuracy_sum.append(accuracy.mean())
print('accuracy:\t', accuracy.mean())

print('总准确率：\t', sum(accuracy_sum)/len(accuracy_sum))
# 精确率图
print('总准确率：\t', sum(accuracy_sum)/len(accuracy_sum))
plt.figure('Accuracy')
plt.plot(accuracy_sum, 'o', label='accuracy')
plt.title('Pytorch_CNN_Accuracy')
plt.legend()
plt.show()