torch07：RNN--MNIST识别和自己数据集
MachineLP的Github（欢迎follow）：https://github.com/MachineLP
MachineLP的博客目录：小鹏的博客目录
本小节使用torch搭建RNN模型，训练和测试：
（1）定义模型超参数：rnn的输入，rnn隐含单元，rnn层数，迭代次数、批量大小、学习率。
（2）定义训练数据，加餐部分是使用自己的数据集：（可参考：https://blog.csdn.net/u014365862/article/details/80506147）
（3）定义模型（定义需要的RNN结构）。
（4）定义损失函数，选用适合的损失函数。
（5）定义优化算法（SGD、Adam等）。
（6）保存模型。
---------------------------------我是可爱的分割线---------------------------------
代码部分：
# coding=utf-8
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# 判定GPU是否存在
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# 定义超参数
# RNN的输入是一个序列，sequence_length为序列长度，input_size为序列每个长度。
sequence_length = 28
input_size = 28
# 定义RNN隐含单元的大小。
hidden_size = 128
# 定义rnn的层数
num_layers = 2
# 识别的类别数量
num_classes = 10
# 批的大小
batch_size = 100
# 定义迭代次数
num_epochs = 2
# 定义学习率
learning_rate = 0.01
# MNIST 数据集
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())
# 构建数据管道， 使用自己的数据集请参考：https://blog.csdn.net/u014365862/article/details/80506147
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)
# 定义RNN（LSTM）
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
# 定义模型
model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)
# 损失函数和优化算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 训练模型
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)
# 前向传播+计算loss
outputs = model(images)
loss = criterion(outputs, labels)
# 后向传播+调整参数
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 每100个batch打印一次数据
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
# 模型测试部分
# 测试阶段不需要计算梯度，注意
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))
# 保存模型参数
torch.save(model.state_dict(), 'model.ckpt')加餐1：在自己数据集上使用：
其中，train.txt中的数据格式：
gender/0male/0(2).jpg 1
gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0
test.txt中的数据格式如下：
gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0
gender/1female/1(6).jpg 1
代码部分：
# coding=utf-8
import torch
import torch.nn as nn
import torchvision
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
from PIL import Image
# 判定GPU是否存在
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# 定义超参数
# RNN的输入是一个序列，sequence_length为序列长度，input_size为序列每个长度。
sequence_length = 28*3
input_size = 28
# 定义RNN隐含单元的大小。
hidden_size = 128
# 定义rnn的层数
num_layers = 2
# 识别的类别数量
num_classes = 10
# 批的大小
batch_size = 16
# 定义迭代次数
num_epochs = 2
# 定义学习率
learning_rate = 0.01
def default_loader(path):
# 注意要保证每个batch的tensor大小时候一样的。
return Image.open(path).convert('RGB')
class MyDataset(Dataset):
def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):
fh = open(txt, 'r')
imgs = []
for line in fh:
line = line.strip('\n')
# line = line.rstrip()
words = line.split(' ')
imgs.append((words[0],int(words[1])))
self.imgs = imgs
self.transform = transform
self.target_transform = target_transform
self.loader = loader
def __getitem__(self, index):
fn, label = self.imgs[index]
img = self.loader(fn)
if self.transform is not None:
img = self.transform(img)
return img,label
def __len__(self):
return len(self.imgs)
def get_loader(dataset='train.txt', crop_size=128, image_size=28, batch_size=2, mode='train', num_workers=1):
"""Build and return a data loader."""
transform = []
if mode == 'train':
transform.append(transforms.RandomHorizontalFlip())
transform.append(transforms.CenterCrop(crop_size))
transform.append(transforms.Resize(image_size))
transform.append(transforms.ToTensor())
transform.append(transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)))
transform = transforms.Compose(transform)
train_data=MyDataset(txt=dataset, transform=transform)
data_loader = DataLoader(dataset=train_data,
batch_size=batch_size,
shuffle=(mode=='train'),
num_workers=num_workers)
return data_loader
# 注意要保证每个batch的tensor大小时候一样的。
# data_loader = DataLoader(train_data, batch_size=2,shuffle=True)
train_loader = get_loader('train.txt', batch_size=batch_size)
print(len(train_loader))
test_loader = get_loader('test.txt', batch_size=batch_size)
print(len(test_loader))
# 定义RNN（LSTM）
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
# 定义模型
model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)
# 损失函数和优化算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 训练模型
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)
# 前向传播+计算loss
outputs = model(images)
loss = criterion(outputs, labels)
# 后向传播+调整参数
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 每100个batch打印一次数据
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
# 模型测试部分
# 测试阶段不需要计算梯度，注意
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))
# 保存模型参数
torch.save(model.state_dict(), 'model.ckpt')加餐2：BIRNN
# coding=utf-8
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# 判定GPU是否存在
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# 定义超参数
# RNN的输入是一个序列，sequence_length为序列长度，input_size为序列每个长度。
sequence_length = 28
input_size = 28
# 定义RNN隐含单元的大小。
hidden_size = 128
# 定义rnn的层数
num_layers = 2
num_classes = 10
batch_size = 100
num_epochs = 2
learning_rate = 0.003
# MNIST 数据集
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())
# 构建数据管道， 使用自己的数据集请参考：https://blog.csdn.net/u014365862/article/details/80506147
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)
# 定义RNN（LSTM）
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
# 定义模型
model = BiRNN(input_size, hidden_size, num_layers, num_classes).to(device)
# 损失函数和优化算法
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 训练模型
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)
# 前向传播+计算loss
outputs = model(images)
loss = criterion(outputs, labels)
# 后向传播+调整参数
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 每100个batch打印一次数据
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
# 模型测试部分
# 测试阶段不需要计算梯度，注意
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))
# 保存模型参数
torch.save(model.state_dict(), 'model.ckpt')---------------------------------我是可爱的分割线---------------------------------
总结：
本节使用RNN训练MNIST识别、自己数据的识别。
上面加餐部分需要生成自己的txt文件（数据+标签），可以参考这个，自己以前调试用的：https://github.com/MachineLP/py_workSpace/blob/master/g_img_path.py
torch系列：
1. torch01：torch基础
2. torch02：logistic regression--MNIST识别
3. torch03：linear_regression
4. torch04：全连接神经网络--MNIST识别和自己数据集
5. torch05：CNN--MNIST识别和自己数据集
6. torch06：ResNet--Cifar识别和自己数据集