Pytorch torch.autograd 与torch.optim的区别//一个求模型里面的梯度,一个通过再梯度来更新模型参数权重
#更新权重值,更新过程使用下面的公式:
weight = weight + learning_rate * gradient
1.Pytorch autograd,backward详解//这两个函数都是求参数梯度的
Pytorch autograd,backward详解 - 知乎
2.Pytorch学习记录|torch.autograd和torch.optim//纯手写的理论笔记也很好
Pytorch学习记录|torch.autograd和torch.optim_Zhengzhenghe的博客-CSDN博客
3.PyTorch——torch.autograd和Variable,torch.nn,torch.optim//通过代码来讲解,真心不错
PyTorch——torch.autograd和Variable,torch.nn,torch.optim_Albert的博客-CSDN博客
一般每次epoch要将计算得到的各个参数节点的梯度值通过grad.data.zero_()全部置零,如果不置零,则计算的梯度值会被一直累加,这样就会影响到后续的计算,只不过optimizer优化器会自动执行这一步在链接3里面可以看到使用优化器和不使用的对比。
这里给一份feedforward代码供大家理论结合实践:
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
input_size = 784
hidden_size = 500
num_classes = 10
num_epochs = 5
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)
# Fully connected neural network with one hidden layer
class NeuralNet(nn.Module):
def __init__(self, input_size, hidden_size, num_classes):
super(NeuralNet, self).__init__()
self.fc1 = nn.Linear(input_size, hidden_size)
self.relu = nn.ReLU()
self.fc2 = nn.Linear(hidden_size, num_classes)
def forward(self, x):
out = self.fc1(x)
out = self.relu(out)
out = self.fc2(out)
return out
model = NeuralNet(input_size, hidden_size, 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):
# Move tensors to the configured device
images = images.reshape(-1, 28*28).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()
#打印每个epoch的训练情况
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
# Test the model
# In test phase, we don't need to compute gradients (for memory efficiency)
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.reshape(-1, 28*28).to(device)#因为第一次是784的全连接层,需要改变一下数据的shape
labels = labels.to(device)#store data on relative hardware,generally cpu or gpu.
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))
# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')
'''
optimizer.zero_grad()
# 要将本次计算得到的各个参数节点的梯度值通过grad.data.zero_()全部置零,如果不置零,
# 则计算的梯度值会被一直累加,这样就会影响到后续的计算
loss.backward()
# 误差反向传播
autograd,backward
#详解//这两个函数都是求参数梯度的
loss.backward()
#这个函数的功能在于让模 型根据计算图自动计算每个节点的梯度值并根据需求进行保留
optimzer.step
#功能是使用计算得到的梯度值对各个节点的参数进行梯度更新
'''
若有疑问,欢迎讨论。