numpy和torch.tensor的转化
# Create a numpy array.
x = np.array([[1, 2], [3, 4]])
# Convert the numpy array to a torch tensor.
y = torch.from_numpy(x)
# Convert the torch tensor to a numpy array.
z = y.numpy()
pytorch的自动求导
# Create tensors.
x = torch.tensor(1., requires_grad=True)
w = torch.tensor(2., requires_grad=True)
b = torch.tensor(3., requires_grad=True)
# Build a computational graph.
y = w * x + b # y = 2 * x + 3
# Compute gradients.
y.backward() #自动向后求导，求导的数必须require_grad=True
# Print out the gradients.
print(x.grad) # x.grad = 2
print(w.grad) # w.grad = 1
print(b.grad) # b.grad = 1
# Create tensors of shape (10, 3) and (10, 2).
x = torch.randn(10, 3)
y = torch.randn(10, 2)
# Build a fully connected layer.
linear = nn.Linear(3, 2)
print ('w: ', linear.weight)
print ('b: ', linear.bias)
# Build loss function and optimizer.
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(linear.parameters(), lr=0.01)
# Forward pass.
pred = linear(x)
# Compute loss.
loss = criterion(pred, y)
print('loss: ', loss.item())
# Backward pass.
optimizer.zero_grad() #计算最好清空优化器中导数的缓存，不然导数会一直累加
loss.backward() #计算loss对参数的导数
# Print out the gradients.
print ('dL/dw: ', linear.weight.grad)
print ('dL/db: ', linear.bias.grad)
# 1-step gradient descent. #梯度下降一步，更新参数
optimizer.step()
# You can also perform gradient descent at the low level.
# linear.weight.data.sub_(0.01 * linear.weight.grad.data)
# linear.bias.data.sub_(0.01 * linear.bias.grad.data)
# Print out the loss after 1-step gradient descent.
pred = linear(x)
loss = criterion(pred, y)
print('loss after 1 step optimization: ', loss.item())
加载自带的格式化的数据集
# Download and construct CIFAR-10 dataset.
train_dataset = torchvision.datasets.CIFAR10(root='../../data/', 放在和Projects并列的data文件夹下,Projects中含有各种project_i，里面含有我们写的程序
train=True,
transform=transforms.ToTensor(),
download=True)
# Fetch one data pair (read data from disk).
image, label = train_dataset[0]
print (image.size())
print (label)
# Data loader (this provides queues and threads in a very simple way).
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=64,
shuffle=True)
# When iteration starts, queue and thread start to load data from files.
data_iter = iter(train_loader)
# Mini-batch images and labels.
images, labels = data_iter.next()
# Actual usage of the data loader is as below.
for images, labels in train_loader:
# Training code should be written here.
pass
DIY自己的数据集
# You should build your custom dataset as below.
class CustomDataset(torch.utils.data.Dataset):
def __init__(self):
# TODO
# 1. Initialize file paths or a list of file names.
pass
def __getitem__(self, index):
# TODO
# 1. Read one data from file (e.g. using numpy.fromfile, PIL.Image.open).
# 2. Preprocess the data (e.g. torchvision.Transform).
# 3. Return a data pair (e.g. image and label).
pass
def __len__(self):
# You should change 0 to the total size of your dataset.
return 0
# You can then use the prebuilt data loader.
custom_dataset = CustomDataset() #导入缓冲区
train_loader = torch.utils.data.DataLoader(dataset=custom_dataset, #开始加载数据
batch_size=64,
shuffle=True)
预处理模型
# Download and load the pretrained ResNet-18.
resnet = torchvision.models.resnet18(pretrained=True)
# If you want to finetune only the top layer of the model, set as below.
for param in resnet.parameters():
param.requires_grad = False
# Replace the top layer for finetuning.
resnet.fc = nn.Linear(resnet.fc.in_features, 100) # 100 is an example. #fc表示front cover最上层，这里用线性模型替换了，输入保持不变，只是输出变了
# Forward pass.
images = torch.randn(64, 3, 224, 224) #生成一个64张通道数为3，长宽为224和224的图片
outputs = resnet(images)
print (outputs.size()) # (64, 100)
保存模型及其参数，加载模型、参数
# Save and load the entire model.
torch.save(resnet, 'model.ckpt')
model = torch.load('model.ckpt')
# Save and load only the model parameters (recommended).
torch.save(resnet.state_dict(), 'params.ckpt')
resnet.load_state_dict(torch.load('params.ckpt'))