CNN卷积神经网络(数字分类)

CNN卷积神经网络——手写数字识别

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt

torch.manual_seed(1)

# Hyper parameters
EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

# Mnist 手写数字
train_data = torchvision.datasets.MNIST(
    root='./mnist/',  # 保存或者提取位置
    train=True,  # this is training data
    transform=torchvision.transforms.ToTensor(),  # 转换 PIL.Image or numpy.ndarray 成
    # torch.FloatTensor (C x H x W), 训练的时候 normalize 成 [0.0, 1.0] 区间
    download=DOWNLOAD_MNIST,  # 没下载就下载, 下载了就不用再下了
)

# print(train_data.train_data.size())
# print(train_data.train_labels.size())
# plt.imshow(train_data.train_data[0].numpy, cmap='gray')
# plt.title("%i" % train_data.train_data[0])
# plt.show()

# 载入数据
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
# 批训练 50 samples, 1 channel, 28x28 (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# 为了节约时间, 我们测试时只测试前2000个
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[
         :2000] / 255.  # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
test_y = test_data.test_labels[:2000]


# 建立CNN模型
#  CNN 整体流程是 卷积(Conv2d) -> 激励函数(ReLU) -> 池化, 向下采样 (MaxPooling) -> 再来一遍 -> 展平多维的卷积成的特征图 -> 接入全连接层 (Linear) -> 输出
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=1,  # 图片的输入的高度(层)
                out_channels=16,  # filter过滤器的个数=提取得到的特征数
                kernel_size=5,  # filter过滤器的大小
                stride=1,  # 每隔多少步跳(跳度)
                padding=2,  # 如果想要 con2d 出来的图片长宽没有变化, padding=(kernel_size-1)/2 当 stride=1
            ),  # 相当于信息收集过滤器,大小=长*宽,高度 = 特征数 (16, 28, 28)
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),  # 在 2x2 空间里向下采样, output shape (16, 14, 14),变得更窄,但是高度(特征数)不变
        )
        self.conv2 = nn.Sequential(  # input shape (16, 14, 14)
            nn.Conv2d(16, 32, 5, 1, 2),  # output shape (32, 14, 14)
            nn.ReLU(),
            nn.MaxPool2d(2),  # output shape (32, 7, 7)
        )
        self.out = nn.Linear(32 * 7 * 7, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)  # (batch,32,7,7)
        x = x.view(x.size(0), -1)  # 展平多维的卷积图成 (batch_size, 32 * 7 * 7)
        output = self.out(x)
        return output


# 创建神经网络
cnn = CNN()
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()
# 训练神经网络
for epoch in range(EPOCH):
    for step, (x, y) in enumerate(train_loader):
        b_x = Variable(x)  # batch_x
        b_y = Variable(y)  # batch_y
        output = cnn(b_x)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        if step % 50 == 0:
            test_output = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.squeeze()
            accuracy = sum(pred_y == test_y) / test_y.size(0)
            print('Epoch:', epoch, '|train loss:%.4f' % loss.item(), '|test accuracy:%.2f' % accuracy)
test_output = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')

报错解决

IndexError: invalid index of a 0-dim tensor. Use `tensor.item()` in Python or `tensor.item<T>()` in C++ to convert a 0-dim tensor to a number
将loss.data[0]换成loss.item()