pytorch 神经网络训练demo
数据集:MNIST
该数据集的内容是手写数字识别,其分为两部分,分别含有60000张训练图片和10000张测试图片
图片来源:https://tensornews.cn/mnist_intro/
神经网络:RNN, GRU, LSTM文章来源:https://www.toymoban.com/news/detail-554591.html
# Imports
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import DataLoader
import torchvision.datasets as datasets
import torchvision.transforms as transforms
# Set device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# Hyperparameters
input_size = 28
sequence_length = 28
num_layers = 2
hidden_size = 256
num_classes = 10
learning_rate = 0.001
batch_size = 64
num_epochs = 2
# Create a RNN
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.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
self.fc = nn.Linear(hidden_size*sequence_length, num_classes) # fully connected
def forward(self, x):
h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
# Forward Prop
out, _ = self.rnn(x, h0)
out = out.reshape(out.shape[0], -1)
out = self.fc(out)
return out
# Create a GRU
class RNN_GRU(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(RNN_GRU, self).__init__()
self.hidden_size = hidden_size
self.num_layers = num_layers
self.gru = nn.GRU(input_size, hidden_size, num_layers, batch_first=True)
self.fc = nn.Linear(hidden_size*sequence_length, num_classes) # fully connected
def forward(self, x):
h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
# Forward Prop
out, _ = self.gru(x, h0)
out = out.reshape(out.shape[0], -1)
out = self.fc(out)
return out
# Create a LSTM
class RNN_LSTM(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(RNN_LSTM, 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*sequence_length, num_classes) # fully connected
def forward(self, x):
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 Prop
out, _ = self.lstm(x, (h0, c0))
out = out.reshape(out.shape[0], -1)
out = self.fc(out)
return out
# Load data
train_dataset = datasets.MNIST(root='dataset/',
train=True,
transform=transforms.ToTensor(),
download=True)
train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_dataset = datasets.MNIST(root='dataset/',
train=False,
transform=transforms.ToTensor(),
download=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True)
# Initialize network 选择一个即可
model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)
# model = RNN_GRU(input_size, hidden_size, num_layers, num_classes).to(device)
# model = RNN_LSTM(input_size, hidden_size, num_layers, num_classes).to(device)
# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
# Train network
for epoch in range(num_epochs):
# data: images, targets: labels
for batch_idx, (data, targets) in enumerate(train_loader):
# Get data to cuda if possible
data = data.to(device).squeeze(1) # 删除一个张量中所有维数为1的维度 (N, 1, 28, 28) -> (N, 28, 28)
targets = targets.to(device)
# forward
scores = model(data) # 64*10
loss = criterion(scores, targets)
# backward
optimizer.zero_grad()
loss.backward()
# gradient descent or adam step
optimizer.step()
# Check accuracy on training & test to see how good our model
def check_accuracy(loader, model):
if loader.dataset.train:
print("Checking accuracy on training data")
else:
print("Checking accuracy on test data")
num_correct = 0
num_samples = 0
model.eval()
with torch.no_grad(): # 不计算梯度
for x, y in loader:
x = x.to(device).squeeze(1)
y = y.to(device)
# x = x.reshape(x.shape[0], -1) # 64*784
scores = model(x)# 64*10
_, predictions = scores.max(dim=1) #dim=1,表示对每行取最大值,每行代表一个样本。
num_correct += (predictions == y).sum()
num_samples += predictions.size(0) # 64
print(f'Got {num_correct} / {num_samples} with accuracy {float(num_correct)/float(num_samples)*100:.2f}%')
model.train()
check_accuracy(train_loader, model)
check_accuracy(test_loader, model)
Result
RNN Result
Checking accuracy on training data
Got 57926 / 60000 with accuracy 96.54%
Checking accuracy on test data
Got 9640 / 10000 with accuracy 96.40%
GRU Result
Checking accuracy on training data
Got 59058 / 60000 with accuracy 98.43%
Checking accuracy on test data
Got 9841 / 10000 with accuracy 98.41%
LSTM Result
Checking accuracy on training data
Got 59248 / 60000 with accuracy 98.75%
Checking accuracy on test data
Got 9849 / 10000 with accuracy 98.49%
参考来源
【1】https://www.youtube.com/watch?v=Gl2WXLIMvKA&list=PLhhyoLH6IjfxeoooqP9rhU3HJIAVAJ3Vz&index=5文章来源地址https://www.toymoban.com/news/detail-554591.html
到了这里,关于PyTorch训练RNN, GRU, LSTM:手写数字识别的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!