利用卷积神经网络实现MNIST手写数据识别

时间：2023-03-09 20:49:23
利用卷积神经网络实现MNIST手写数据识别

代码：

import torch

import torch.nn as nn

import torch.utils.data as Data

import torchvision      # 数据库模块

import matplotlib.pyplot as plt

torch.manual_seed()    # reproducible

# Hyper Parameters

EPOCH =            # 训练整批数据多少次, 为了节约时间, 我们只训练一次

BATCH_SIZE =

LR = 0.001          # 学习率

DOWNLOAD_MNIST = False  # 如果你已经下载好了mnist数据就写上 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

)

#plot one example

# print(train_data.test_data.shape)#torch.Size([, , ])

# print(train_data.train_labels.shape)#torch.Size([])

# print(train_data.train_data[].shape)#torch.Size([, ])

#

# plt.imshow(train_data.train_data[],cmap='gray')

# plt.title('%d'%train_data.train_labels[])

# plt.show()

#测试数据

test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)

# print(test_data.test_data.shape)#torch.Size([, , ])

# 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=).type(torch.FloatTensor)[:]   # /.shape from (, , ) to (, , , ), value in range(,)

test_y = test_data.test_labels[:]

# 批训练 50samples,  channel, 28x28 (, , , )

train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

class CNN(nn.Module):

    def __init__(self):

        super(CNN, self).__init__()

        self.conv1=nn.Sequential(

            nn.Conv2d(

                in_channels=,

                out_channels=,#n_filters

                kernel_size=,  # filter size

                stride=,  # filter movement/step

                padding=,  # 如果想要 con2d 出来的图片长宽没有变化, padding=(kernel_size-)/ 当 stride=

            ),# output shape (, , )

            nn.ReLU(),

            nn.MaxPool2d(kernel_size=)# output shape (, , )

        )

        self.conv2=nn.Sequential(

            nn.Conv2d(,,,,),# output shape (, , )

            nn.ReLU(),

            nn.MaxPool2d()# output shape (, , )

        )

        self.out=nn.Linear(**,)# fully connected layer, output  classes

    def forward(self, x):

        x=self.conv1(x)

        x=self.conv2(x)

        #print(x.shape)#output:torch.Size([, , , ])

        x = x.view(x.size(), -) # 展平多维的卷积图成 (batch_size,  *  * )

        # print(x.shape)#output:torch.Size([, ])

        output = self.out(x)

        return output

cnn=CNN()

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)   # optimize all cnn parameters

loss_func = nn.CrossEntropyLoss()   # the target label is not one-hotted

# training and testing

for epoch in range(EPOCH):

    for step, (b_x, b_y) in enumerate(train_loader):   # 分配 batch data, normalize x when iterate train_loader

        print('step:',step)

        output = cnn(b_x)               # cnn output

        loss = loss_func(output, b_y)   # cross entropy loss

        optimizer.zero_grad()           # clear gradients for this training step

        loss.backward()                 # backpropagation, compute gradients

        optimizer.step()                # apply gradients

test_output = cnn(test_x[:])

#test_x[:].shape=torch.Size([, , , ])

#test_output.shape=torch.Size([, ])

print('test_output：',test_output)

# test_output： tensor([[-1383.2828, -1148.1272,   311.1780,   153.0877, -3062.3340,  -886.6730,

#          -5819.7256,  3619.9558, -1544.4225,   193.6745],

#         [  282.6339,   647.2642,  3027.1570,  -379.0817, -3403.5310, -2406.4951,

#          -1117.4684, -4085.4429,  -306.6578, -3844.1602],

#         [-1329.7642,  1895.3890,  -755.7719, -1378.9316,  -314.2351, -1607.4249,

#          -1026.8795,  -428.1658,  -385.1328, -1404.5205],

#         [ 2991.5627, -3583.5374,  -554.1349, -2472.6204, -1712.7700, -1092.7367,

#            148.9156, -1580.6696, -1126.8331,  -477.7481],

#         [-1818.9655, -1502.3574, -1620.6603, -2142.3472,  2529.0496, -2008.2731,

#          -1585.5699,  -786.7817, -1372.2627,   848.0875],

#         [-1415.7609,  2248.9607,  -909.5534, -1656.6108,  -311.2874, -2255.2163,

#          -1643.2495,  -149.4040,  -342.9626, -1372.8961],

#         [-3766.0422,  -484.8116, -1971.9016, -2483.8538,  1448.3118, -1048.7388,

#          -2411.9790, -1089.5471,   422.1722,   249.8736],

#         [-2933.3752,  -877.4833,  -671.7119,  -573.4670,    63.9295,  -497.9561,

#          -2236.4597, -1218.2463,  -296.5850,  1256.0739],

#         [-2187.7292, -4899.0063, -2404.6597, -2595.0764, -2987.9624,  2052.1494,

#            335.9461, -2942.6995,   275.7964,  -551.2797],

#         [-1903.9233, -3449.5530, -1652.7020, -1087.9016,  -515.1445, -1170.5551,

#          -3734.2666,   628.9314,    69.0235,  2096.6257]],

#        grad_fn=<AddmmBackward>)

print('test_output.shape：',test_output.shape)

# test_output.shape： torch.Size([, ])

pred_y = torch.max(test_output, )[].data.numpy().squeeze()

print(pred_y, 'prediction number')

print(test_y[:].numpy(), 'real number')

相关文章