用pytorch对mnist手写数字进行分类
用pytorch对mnist手写数字进行分类
最近在学习pytorch框架，所以按照莫烦python的代码跑了一遍
github代码
整理手写数字数据
# 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 datatransform=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
)test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)# 批训练 50samples, 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]
数据是pytorch的对象数据
<torch.utils.data.dataloader.DataLoader object at 0x000002292CF4C160>
数据分为训练数据、测试数据、测试矩阵和测试标签
构建cnn网络
class CNN(nn.Module):def __init__(self):super(CNN, self).__init__()self.conv1 = nn.Sequential( # input shape (1, 28, 28)nn.Conv2d(in_channels=1, # input heightout_channels=16, # n_filterskernel_size=5, # filter sizestride=1, # filter movement/steppadding=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), # output shape (16, 28, 28)nn.ReLU(), # activationnn.MaxPool2d(kernel_size=2), # 在 2x2 空间里向下采样, output shape (16, 14, 14))self.conv2 = nn.Sequential( # input shape (16, 14, 14)nn.Conv2d(16, 32, 5, 1, 2), # output shape (32, 14, 14)nn.ReLU(), # activationnn.MaxPool2d(2), # output shape (32, 7, 7))self.out = nn.Linear(32 * 7 * 7, 10) # fully connected layer, output 10 classesdef forward(self, x):x = self.conv1(x)x = self.conv2(x)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
"""
CNN ((conv1): Sequential ((0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(1): ReLU ()(2): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)))(conv2): Sequential ((0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(1): ReLU ()(2): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)))(out): Linear (1568 -> 10)
)
"""
可以看到这个cnn网络这样构建的
由这个图可以看到28*28通道为1经过卷积核卷积得28*28\通道为16，再经过ReLu激活函数进行激活和MaxPool进行数据压缩，得出14*14通道为16
由这个图可以看到14*14通道为16经过卷积核卷积得14*14\通道为32，再经过ReLu激活函数进行激活和MaxPool进行数据压缩，得出7*7通道为32
最后展开一个32*7*7的向量，设置10个分类的向量
训练
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_loaderoutput = cnn(b_x) # cnn outputloss = loss_func(output, b_y) # cross entropy lossoptimizer.zero_grad() # clear gradients for this training steploss.backward() # backpropagation, compute gradientsoptimizer.step() # apply gradients
每次正向传播一次，要反向更新参数loss.backward()
loss_func 是计算损失的一个方式
测试
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')
输出结果：
[7 2 1 0 4 1 4 9 5 9] prediction number
[7 2 1 0 4 1 4 9 5 9] real number
保存模型
torch.save(cnn.state_dict(), 'net_params.pkl')
这个是将模型训练的参数保存，而不是这个网络
提取模型
cnn.load_state_dict(torch.load('net_params.pkl'))
这个这是提取网络参数，所以用之前先构建网络
完整代码
保存模型
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision # 数据库模块
import matplotlib.pyplot as plttorch.manual_seed(1) # reproducible# Hyper Parameters
EPOCH = 1 # 训练整批数据多少次, 为了节约时间, 我们只训练一次
BATCH_SIZE = 50
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 datatransform=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
)test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)# 批训练 50samples, 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]class CNN(nn.Module):def __init__(self):super(CNN, self).__init__()self.conv1 = nn.Sequential( # input shape (1, 28, 28)nn.Conv2d(in_channels=1, # input heightout_channels=16, # n_filterskernel_size=5, # filter sizestride=1, # filter movement/steppadding=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), # output shape (16, 28, 28)nn.ReLU(), # activationnn.MaxPool2d(kernel_size=2), # 在 2x2 空间里向下采样, output shape (16, 14, 14))self.conv2 = nn.Sequential( # input shape (16, 14, 14)nn.Conv2d(16, 32, 5, 1, 2), # output shape (32, 14, 14)nn.ReLU(), # activationnn.MaxPool2d(2), # output shape (32, 7, 7))self.out = nn.Linear(32 * 7 * 7, 10) # fully connected layer, output 10 classesdef forward(self, x):x = self.conv1(x)x = self.conv2(x)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 outputcnn = CNN()
print(cnn) # net architecture
"""
CNN ((conv1): Sequential ((0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(1): ReLU ()(2): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)))(conv2): Sequential ((0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(1): ReLU ()(2): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1)))(out): Linear (1568 -> 10)
)
"""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_loaderoutput = cnn(b_x) # cnn outputloss = loss_func(output, b_y) # cross entropy lossoptimizer.zero_grad() # clear gradients for this training steploss.backward() # backpropagation, compute gradientsoptimizer.step() # apply gradientstorch.save(cnn.state_dict(), 'net_params.pkl')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')
提取代码
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision # 数据库模块
import matplotlib.pyplot as plttorch.manual_seed(1) # reproducible# Hyper Parameters
EPOCH = 1 # 训练整批数据多少次, 为了节约时间, 我们只训练一次
BATCH_SIZE = 50
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 datatransform=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
)test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)# 批训练 50samples, 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]class CNN(nn.Module):def __init__(self):super(CNN, self).__init__()self.conv1 = nn.Sequential( # input shape (1, 28, 28)nn.Conv2d(in_channels=1, # input heightout_channels=16, # n_filterskernel_size=5, # filter sizestride=1, # filter movement/steppadding=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), # output shape (16, 28, 28)nn.ReLU(), # activationnn.MaxPool2d(kernel_size=2), # 在 2x2 空间里向下采样, output shape (16, 14, 14))self.conv2 = nn.Sequential( # input shape (16, 14, 14)nn.Conv2d(16, 32, 5, 1, 2), # output shape (32, 14, 14)nn.ReLU(), # activationnn.MaxPool2d(2), # output shape (32, 7, 7))self.out = nn.Linear(32 * 7 * 7, 10) # fully connected layer, output 10 classesdef forward(self, x):x = self.conv1(x)x = self.conv2(x)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 outputcnn = CNN()cnn.load_state_dict(torch.load('net_params.pkl'))
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')
总结
以上理解是个人理解，可能会有缺失或错误，请各位指教
莫烦python
最新文章
- Java中接口如何继承接口呢？
- 理解java中的反射
- jkd1.8 list.stream()练习
- centos5
- Spring
- 集群和均衡负载[摘]
- 使用Springboot实现Nginx均衡负载功能
- 系统测试常见类型及说明
- EmguCV学习（二）
- js的exports
- mysql 10931142
- mysql 1142 问题解决
- 数电和Verilog
- python thinker
- C语言升序与降序
- 数据库的升序降序排列
- Tensorflow学习之tf.keras(一) tf.keras.layers.Model(另附compile，fit)
- 自己写个双色球
- 【空指针异常，也不全是。】
- Lock(锁)