PyTorch（二）Intermediate

• Convolutional Neural Network

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# Hyper parameters
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001

# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='../../data/',
                                           train=True,
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='../../data/',
                                          train=False,
                                          transform=transforms.ToTensor())

# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)

# Convolutional neural network (two convolutional layers)
class ConvNet(nn.Module):
    def __init__(self, input_channel, num_classes):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(input_channel, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        ) # 28*28*1 -> 14*14*16
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        ) # 14*14*16 -> 7*7*32
        self.fc = nn.Linear(7*7*32, num_classes)

    def forward(self, input):
        out = self.layer1(input)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

model = ConvNet(1, num_classes).to(device)

# Construct Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
model.train()
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# Test the model
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')

• Deep Residual Network

# ---------------------------------------------------------------------------- #
# An implementation of https://arxiv.org/pdf/1512.03385.pdf                    #
# See section 4.2 for the model architecture on CIFAR-10                       #
# Some part of the code was referenced from below                              #
# https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py   #
# ---------------------------------------------------------------------------- #

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyper-parameters
num_epochs = 80
learning_rate = 0.001

# Image preprocessing modules
transform = transforms.Compose([
    transforms.Pad(4),
    transforms.RandomHorizontalFlip(),
    transforms.RandomCrop(32),
    transforms.ToTensor()])

# CIFAR-10 dataset
train_dataset = torchvision.datasets.CIFAR10(root='../../data/',
                                             train=True,
                                             transform=transform,
                                             download=True)

test_dataset = torchvision.datasets.CIFAR10(root='../../data/',
                                            train=False,
                                            transform=transforms.ToTensor())

# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=100,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=100,
                                          shuffle=False)

# 3x3 convolution
def conv3x3(in_channels, out_channels, stride=1):
    return nn.Conv2d(in_channels, out_channels, kernel_size=3,
                     stride=stride, padding=1, bias=False)

# Residual block
class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample

    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

# ResNet
class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 16
        self.conv = conv3x3(3, 16)
        self.bn = nn.BatchNorm2d(16)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self.make_layer(block, 16, layers[0])
        self.layer2 = self.make_layer(block, 32, layers[0], 2)
        self.layer3 = self.make_layer(block, 64, layers[1], 2)
        self.avg_pool = nn.AvgPool2d(8)
        self.fc = nn.Linear(64, num_classes)

    def make_layer(self, block, out_channels, blocks, stride=1):
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels):
            downsample = nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                nn.BatchNorm2d(out_channels))
        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels
        for i in range(1, blocks):
            layers.append(block(out_channels, out_channels))
        return nn.Sequential(*layers)

    def forward(self, x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out

model = ResNet(ResidualBlock, [2, 2, 2, 2]).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# For updating learning rate
def update_lr(optimizer, lr):
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr

# Train the model
total_step = len(train_loader)
curr_lr = learning_rate
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print ("Epoch [{}/{}], Step [{}/{}] Loss: {:.4f}"
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

    # Decay learning rate
    if (epoch+1) % 20 == 0:
        curr_lr /= 3
        update_lr(optimizer, curr_lr)

# Test the model
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'resnet.ckpt')

# from torchsummary import summary
# summary(model, (3, 32, 32))

# https://github.com/lanpa/tensorboardX
# from tensorboardX import SummaryWriter
# dummy_input = torch.rand(1, 3, 32, 32).to(device)
# with SummaryWriter(comment='residual') as w:
#     w.add_graph(model, (dummy_input, ))

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1           [-1, 16, 32, 32]             432
       BatchNorm2d-2           [-1, 16, 32, 32]              32
              ReLU-3           [-1, 16, 32, 32]               0
            Conv2d-4           [-1, 16, 32, 32]           2,304
       BatchNorm2d-5           [-1, 16, 32, 32]              32
              ReLU-6           [-1, 16, 32, 32]               0
            Conv2d-7           [-1, 16, 32, 32]           2,304
       BatchNorm2d-8           [-1, 16, 32, 32]              32
              ReLU-9           [-1, 16, 32, 32]               0
    ResidualBlock-10           [-1, 16, 32, 32]               0
           Conv2d-11           [-1, 16, 32, 32]           2,304
      BatchNorm2d-12           [-1, 16, 32, 32]              32
             ReLU-13           [-1, 16, 32, 32]               0
           Conv2d-14           [-1, 16, 32, 32]           2,304
      BatchNorm2d-15           [-1, 16, 32, 32]              32
             ReLU-16           [-1, 16, 32, 32]               0
    ResidualBlock-17           [-1, 16, 32, 32]               0
           Conv2d-18           [-1, 32, 16, 16]           4,608
      BatchNorm2d-19           [-1, 32, 16, 16]              64
             ReLU-20           [-1, 32, 16, 16]               0
           Conv2d-21           [-1, 32, 16, 16]           9,216
      BatchNorm2d-22           [-1, 32, 16, 16]              64
           Conv2d-23           [-1, 32, 16, 16]           4,608
      BatchNorm2d-24           [-1, 32, 16, 16]              64
             ReLU-25           [-1, 32, 16, 16]               0
    ResidualBlock-26           [-1, 32, 16, 16]               0
           Conv2d-27           [-1, 32, 16, 16]           9,216
      BatchNorm2d-28           [-1, 32, 16, 16]              64
             ReLU-29           [-1, 32, 16, 16]               0
           Conv2d-30           [-1, 32, 16, 16]           9,216
      BatchNorm2d-31           [-1, 32, 16, 16]              64
             ReLU-32           [-1, 32, 16, 16]               0
    ResidualBlock-33           [-1, 32, 16, 16]               0
           Conv2d-34             [-1, 64, 8, 8]          18,432
      BatchNorm2d-35             [-1, 64, 8, 8]             128
             ReLU-36             [-1, 64, 8, 8]               0
           Conv2d-37             [-1, 64, 8, 8]          36,864
      BatchNorm2d-38             [-1, 64, 8, 8]             128
           Conv2d-39             [-1, 64, 8, 8]          18,432
      BatchNorm2d-40             [-1, 64, 8, 8]             128
             ReLU-41             [-1, 64, 8, 8]               0
    ResidualBlock-42             [-1, 64, 8, 8]               0
           Conv2d-43             [-1, 64, 8, 8]          36,864
      BatchNorm2d-44             [-1, 64, 8, 8]             128
             ReLU-45             [-1, 64, 8, 8]               0
           Conv2d-46             [-1, 64, 8, 8]          36,864
      BatchNorm2d-47             [-1, 64, 8, 8]             128
             ReLU-48             [-1, 64, 8, 8]               0
    ResidualBlock-49             [-1, 64, 8, 8]               0
        AvgPool2d-50             [-1, 64, 1, 1]               0
           Linear-51                   [-1, 10]             650
================================================================
Total params: 195,738
Trainable params: 195,738
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.01
Forward/backward pass size (MB): 3.63
Params size (MB): 0.75
Estimated Total Size (MB): 4.38
----------------------------------------------------------------

• Recurrent Neural Network

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyper-parameters
sequence_length = 28
input_size = 28
hidden_size = 128
num_layers = 2
num_classes = 10
batch_size = 100
num_epochs = 2
learning_rate = 0.01

# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='../../data/',
                                           train=True,
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='../../data/',
                                          train=False,
                                          transform=transforms.ToTensor())

# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)

# Recurrent neural network (many-to-one)
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, num_classes)

    def forward(self, x):
        # Set initial hidden and cell states
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)

        # Forward propagate LSTM
        out, _ = self.lstm(x, (h0, c0))  # out: tensor of shape (batch_size, seq_length, hidden_size)

        # Decode the hidden state of the last time step
        out = self.fc(out[:, -1, :])
        return out

model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# Test the model
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total)) 

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')

• Bidirectional Recurrent Neural Network

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyper-parameters
sequence_length = 28
input_size = 28
hidden_size = 128
num_layers = 2
num_classes = 10
batch_size = 100
num_epochs = 2
learning_rate = 0.003

# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='../../data/',
                                           train=True,
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='../../data/',
                                          train=False,
                                          transform=transforms.ToTensor())

# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)

# Bidirectional recurrent neural network (many-to-one)
class BiRNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(BiRNN, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True, bidirectional=True)
        self.fc = nn.Linear(hidden_size*2, num_classes)  # 2 for bidirection

    def forward(self, x):
        # Set initial states
        h0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device) # 2 for bidirection
        c0 = torch.zeros(self.num_layers*2, x.size(0), self.hidden_size).to(device)

        # Forward propagate LSTM
        out, _ = self.lstm(x, (h0, c0))  # out: tensor of shape (batch_size, seq_length, hidden_size*2)

        # Decode the hidden state of the last time step
        out = self.fc(out[:, -1, :])
        return out

model = BiRNN(input_size, hidden_size, num_layers, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# Test the model
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total)) 

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')

• Language Model (RNN-LM)

# Some part of the code was referenced from below.
# https://github.com/pytorch/examples/tree/master/word_language_model
import torch
import torch.nn as nn
import numpy as np
from torch.nn.utils import clip_grad_norm
from data_utils import Dictionary, Corpus

# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyper-parameters
embed_size = 128
hidden_size = 1024
num_layers = 1
num_epochs = 5
num_samples = 1000     # number of words to be sampled
batch_size = 20
seq_length = 30
learning_rate = 0.002

# Load "Penn Treebank" dataset
corpus = Corpus()
ids = corpus.get_data('data/train.txt', batch_size)
vocab_size = len(corpus.dictionary)
num_batches = ids.size(1) // seq_length

# RNN based language model
class RNNLM(nn.Module):
    def __init__(self, vocab_size, embed_size, hidden_size, num_layers):
        super(RNNLM, self).__init__()
        self.embed = nn.Embedding(vocab_size, embed_size)
        self.lstm = nn.LSTM(embed_size, hidden_size, num_layers, batch_first=True)
        self.linear = nn.Linear(hidden_size, vocab_size)

    def forward(self, x, h):
        # Embed word ids to vectors
        x = self.embed(x)

        # Forward propagate LSTM
        out, (h, c) = self.lstm(x, h)

        # Reshape output to (batch_size*sequence_length, hidden_size)
        out = out.reshape(out.size(0)*out.size(1), out.size(2))

        # Decode hidden states of all time steps
        out = self.linear(out)
        return out, (h, c)

model = RNNLM(vocab_size, embed_size, hidden_size, num_layers).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Truncated backpropagation
def detach(states):
    return [state.detach() for state in states] 

# Train the model
for epoch in range(num_epochs):
    # Set initial hidden and cell states
    states = (torch.zeros(num_layers, batch_size, hidden_size).to(device),
              torch.zeros(num_layers, batch_size, hidden_size).to(device))

    for i in range(0, ids.size(1) - seq_length, seq_length):
        # Get mini-batch inputs and targets
        inputs = ids[:, i:i+seq_length].to(device)
        targets = ids[:, (i+1):(i+1)+seq_length].to(device)

        # Forward pass
        states = detach(states)
        outputs, states = model(inputs, states)
        loss = criterion(outputs, targets.reshape(-1))

        # Backward and optimize
        model.zero_grad()
        loss.backward()
        clip_grad_norm(model.parameters(), 0.5)
        optimizer.step()

        step = (i+1) // seq_length
        if step % 100 == 0:
            print ('Epoch [{}/{}], Step[{}/{}], Loss: {:.4f}, Perplexity: {:5.2f}'
                   .format(epoch+1, num_epochs, step, num_batches, loss.item(), np.exp(loss.item())))

# Test the model
with torch.no_grad():
    with open('sample.txt', 'w') as f:
        # Set intial hidden ane cell states
        state = (torch.zeros(num_layers, 1, hidden_size).to(device),
                 torch.zeros(num_layers, 1, hidden_size).to(device))

        # Select one word id randomly
        prob = torch.ones(vocab_size)
        input = torch.multinomial(prob, num_samples=1).unsqueeze(1).to(device)

        for i in range(num_samples):
            # Forward propagate RNN
            output, state = model(input, state)

            # Sample a word id
            prob = output.exp()
            word_id = torch.multinomial(prob, num_samples=1).item()

            # Fill input with sampled word id for the next time step
            input.fill_(word_id)

            # File write
            word = corpus.dictionary.idx2word[word_id]
            word = '\n' if word == '<eos>' else word + ' '
            f.write(word)

            if (i+1) % 100 == 0:
                print('Sampled [{}/{}] words and save to {}'.format(i+1, num_samples, 'sample.txt'))

# Save the model checkpoints
torch.save(model.state_dict(), 'model.ckpt')

import torch
import os

class Dictionary(object):
    def __init__(self):
        self.word2idx = {}
        self.idx2word = {}
        self.idx = 0

    def add_word(self, word):
        if not word in self.word2idx:
            self.word2idx[word] = self.idx
            self.idx2word[self.idx] = word
            self.idx += 1

    def __len__(self):
        return len(self.word2idx)

class Corpus(object):
    def __init__(self):
        self.dictionary = Dictionary()

    def get_data(self, path, batch_size=20):
        # Add words to the dictionary
        with open(path, 'r') as f:
            tokens = 0
            for line in f:
                words = line.split() + ['<eos>']
                tokens += len(words)
                for word in words:
                    self.dictionary.add_word(word)  

        # Tokenize the file content
        ids = torch.LongTensor(tokens)
        token = 0
        with open(path, 'r') as f:
            for line in f:
                words = line.split() + ['<eos>']
                for word in words:
                    ids[token] = self.dictionary.word2idx[word]
                    token += 1
        num_batches = ids.size(0) // batch_size
        ids = ids[:num_batches*batch_size]
        return ids.view(batch_size, -1)