【PyTorch】构建简单神经网络的两种方式

需要理解过程以及每个模块的作用 

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

class Net(nn.Module):
    def __init__(self,n_feature, n_hidden, n_output):
        super(Net,self).__init__()
        self.hidden = nn.Linear(n_feature,n_hidden)
        self.predict = nn.Linear(n_hidden,n_output)

    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x
net1 = Net(1,10,1)
print(net1)

net2 = nn.Sequential(
    nn.Linear(1,10),
    nn.ReLU(),   #实例化对象
    nn.Linear(10,1)
)
print(net2)

输出：

Net(
  (hidden): Linear(in_features=1, out_features=10, bias=True)
  (predict): Linear(in_features=10, out_features=1, bias=True)
)
Sequential(
  (0): Linear(in_features=1, out_features=10, bias=True)
  (1): ReLU()
  (2): Linear(in_features=10, out_features=1, bias=True)
)

实现mnist手写数字识别

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.nn.functional as F
import torch.optim as optim
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
import numpy as np

EPOCH = 1               # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 50
LR = 0.001              # learning rate
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                                     # this is training data
    transform=torchvision.transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                                    # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST                        # download it if you don't have it
)

# print(train_data.train_data.size())     #[60000,28,28]
# print(train_data.train_labels.size())   #[60000]

train_loader = Data.DataLoader(
    dataset=train_data,
    batch_size=BATCH_SIZE,
    shuffle=True,
    num_workers=0
)
# convert test data into Variable, pick 2000 samples to speed up testing
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
#使用unsqueeze对数据进行维度增加
test_x = Variable(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( #[bacth_size,1,28,28]
            nn.Conv2d(1,16,5,1,2),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2) #[batch_size,16,14,14]
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(16,32,5,1,2),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2) #[batch_size,32,7,7]
        )
        self.out = nn.Linear(32*7*7,10)

    def forward(self,x):
        x = self.conv1(x)
        x = self.conv2(x)
        #x = x.view(-1,32*7*7)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        return output,x

cnn = CNN()
print(cnn)

optimizer = optim.Adam(cnn.parameters(),lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step, (x,y) in enumerate(train_loader):
        b_x = Variable(x)
        b_y = Variable(y)
        output = cnn(b_x)[0]
        loss = loss_func(output,b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        if step % 100 == 0:
            test_output, last_layer = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.squeeze()
            accuracy = (pred_y == test_y).sum().item() / float(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')

out:

CNN(
  (conv1): Sequential(
    (0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU()
    (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (conv2): Sequential(
    (0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU()
    (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (out): Linear(in_features=1568, out_features=10, bias=True)
)
Epoch:  0 | train loss: 2.3072 | test accuracy: 0.10
Epoch:  0 | train loss: 0.1293 | test accuracy: 0.89
Epoch:  0 | train loss: 0.1760 | test accuracy: 0.94
Epoch:  0 | train loss: 0.1097 | test accuracy: 0.96
Epoch:  0 | train loss: 0.0499 | test accuracy: 0.96
Epoch:  0 | train loss: 0.0317 | test accuracy: 0.97
Epoch:  0 | train loss: 0.1660 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0486 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0068 | test accuracy: 0.98
Epoch:  0 | train loss: 0.0150 | test accuracy: 0.98
Epoch:  0 | train loss: 0.1158 | test accuracy: 0.98
Epoch:  0 | train loss: 0.1373 | test accuracy: 0.98
[7 2 1 0 4 1 4 9 5 9] prediction number
[7 2 1 0 4 1 4 9 5 9] real number