文章目录
- pytorch 神经网络训练demo
- 输出结果
- 来源
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
神经网络:全连接网络
# 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# Create Fully Connected Network
class NN(nn.Module):def __init__(self, input_size, num_classes): #(28 * 28 = 784)super(NN, self).__init__()self.fc1 = nn.Linear(input_size, 50)self.fc2 = nn.Linear(50, num_classes)def forward(self, x):x = F.relu(self.fc1(x))x = self.fc2(x)return xmodel = NN(784, 10)
x = torch.randn(64, 784)# Set device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')# Hyperparameters
input_size = 784
num_classes = 10
learning_rate = 0.001
batch_size = 64
num_epochs = 1# 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)
# print(f'train_loader: {train_loader}')
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
model = NN(input_size=input_size, num_classes=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: labelsfor batch_idx, (data, targets) in enumerate(train_loader):# Get data to cuda if possibledata = data.to(device)targets = targets.to(device)# Get to correct shape# print(data.shape) # (batch_size, input_channel, height, width)data = data.reshape(data.shape[0], -1) # 64*784# forwardscores = model(data) # 64*10# print(f'scores: {scores.shape}') # 64*10# print(f'targets: {targets.shape}') # 64*1loss = criterion(scores, targets)# backwardoptimizer.zero_grad()loss.backward()# gradient descent or adam stepoptimizer.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 = 0num_samples = 0model.eval()with torch.no_grad(): # 不计算梯度for x, y in loader:x = x.to(device)y = y.to(device)x = x.reshape(x.shape[0], -1) # 64*784scores = model(x)# 64*10# torch.max()这个函数返回的是两个值:#第一个值是具体的value(我们用下划线_表示)#第二个值是value所在的index(也就是predictions)。# 我们不关心最大值是什么,而关心最大值对应的index是什么,所以选用下划线代表不需要用到的变量。# 比如在图像分类任务中,index就对应着图片的类别,这里我们只关心网络预测的类别是什么,而不关心该类别的预测概率。_, 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) # 64print(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)
输出结果
Checking accuracy on training data
Got 55770 / 60000 with accuracy 92.95%
Checking accuracy on test data
Got 9316 / 10000 with accuracy 93.16%
来源
【1】https://www.youtube.com/watch?v=Jy4wM2X21u0&list=PLhhyoLH6IjfxeoooqP9rhU3HJIAVAJ3Vz&index=3