PyTorch: Tensors
这次我们使用PyTorch tensors来创建前向神经网络,计算损失,以及反向传播。
一个PyTorch Tensor很像一个numpy的ndarray。但是它和numpy ndarray最大的区别是,PyTorch Tensor可以在CPU或者GPU上运算。如果想要在GPU上运算,就需要把Tensor换成cuda类型。
import torch
dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random input and output data
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)
# Randomly initialize weights
w1 = torch.randn(D_in, H, device=device, dtype=dtype)
w2 = torch.randn(H, D_out, device=device, dtype=dtype)
learning_rate = 1e-6
for t in range(500):
# Forward pass: compute predicted y
h = x.mm(w1)
h_relu = h.clamp(min=0)
y_pred = h_relu.mm(w2)
# Compute and print loss
loss = (y_pred - y).pow(2).sum().item()
print(t, loss)
# Backprop to compute gradients of w1 and w2 with respect to loss
grad_y_pred = 2.0 * (y_pred - y)
grad_w2 = h_relu.t().mm(grad_y_pred)
grad_h_relu = grad_y_pred.mm(w2.t())
grad_h = grad_h_relu.clone()
grad_h[h < 0] = 0
grad_w1 = x.t().mm(grad_h)
# Update weights using gradient descent
w1 -= learning_rate * grad_w1
w2 -= learning_rate * grad_w2
简单的autograd
# 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()
# Print out the gradients.
print(x.grad) # x.grad = 2
print(w.grad) # w.grad = 1
print(b.grad) # b.grad = 1
# 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()
# Print out the gradients.
print(x.grad) # x.grad = 2
print(w.grad) # w.grad = 1
print(b.grad) # b.grad = 1
PyTorch: Tensor和autograd
PyTorch的一个重要功能就是autograd,也就是说只要定义了forward pass(前向神经网络),计算了loss之后,PyTorch可以自动求导计算模型所有参数的梯度。
一个PyTorch的Tensor表示计算图中的一个节点。如果x是一个Tensor并且x.requires_grad=True那么x.grad是另一个储存着x当前梯度(相对于一个scalar,常常是loss)的向量。
import torch
dtype = torch.float
device = torch.device("cpu")
# device = torch.device("cuda:0") # Uncomment this to run on GPU
# N 是 batch size; D_in 是 input dimension;
# H 是 hidden dimension; D_out 是 output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# 创建随机的Tensor来保存输入和输出
# 设定requires_grad=False表示在反向传播的时候我们不需要计算gradient
x = torch.randn(N, D_in, device=device, dtype=dtype)
y = torch.randn(N, D_out, device=device, dtype=dtype)
# 创建随机的Tensor和权重。
# 设置requires_grad=True表示我们希望反向传播的时候计算Tensor的gradient
w1 = torch.randn(D_in, H, device=device, dtype=dtype, requires_grad=True)
w2 = torch.randn(H, D_out, device=device, dtype=dtype, requires_grad=True)
learning_rate = 1e-6
for t in range(500):
# 前向传播:通过Tensor预测y;这个和普通的神经网络的前向传播没有任何不同,
# 但是我们不需要保存网络的中间运算结果,因为我们不需要手动计算反向传播。
y_pred = x.mm(w1).clamp(min=0).mm(w2)
# 通过前向传播计算loss
# loss是一个形状为(1,)的Tensor
# loss.item()可以给我们返回一个loss的scalar
loss = (y_pred - y).pow(2).sum()
print(t, loss.item())
# PyTorch给我们提供了autograd的方法做反向传播。如果一个Tensor的requires_grad=True,
# backward会自动计算loss相对于每个Tensor的gradient。在backward之后,
# w1.grad和w2.grad会包含两个loss相对于两个Tensor的gradient信息。
loss.backward()
# 我们可以手动做gradient descent(后面我们会介绍自动的方法)。
# 用torch.no_grad()包含以下statements,因为w1和w2都是requires_grad=True,
# 但是在更新weights之后我们并不需要再做autograd。
# 另一种方法是在weight.data和weight.grad.data上做操作,这样就不会对grad产生影响。
# tensor.data会我们一个tensor,这个tensor和原来的tensor指向相同的内存空间,
# 但是不会记录计算图的历史。
with torch.no_grad():
w1 -= learning_rate * w1.grad
w2 -= learning_rate * w2.grad
# Manually zero the gradients after updating weights
w1.grad.zero_()
w2.grad.zero_()
PyTorch: nn
这次我们使用PyTorch中nn这个库来构建网络。 用PyTorch autograd来构建计算图和计算gradients, 然后PyTorch会帮我们自动计算gradient。
import torch
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
# Use the nn package to define our model as a sequence of layers. nn.Sequential
# is a Module which contains other Modules, and applies them in sequence to
# produce its output. Each Linear Module computes output from input using a
# linear function, and holds internal Tensors for its weight and bias.
model = torch.nn.Sequential(
torch.nn.Linear(D_in, H),
torch.nn.ReLU(),
torch.nn.Linear(H, D_out),
)
# The nn package also contains definitions of popular loss functions; in this
# case we will use Mean Squared Error (MSE) as our loss function.
loss_fn = torch.nn.MSELoss(reduction='sum')
learning_rate = 1e-4
for t in range(500):
# Forward pass: compute predicted y by passing x to the model. Module objects
# override the __call__ operator so you can call them like functions. When
# doing so you pass a Tensor of input data to the Module and it produces
# a Tensor of output data.
y_pred = model(x)
# Compute and print loss. We pass Tensors containing the predicted and true
# values of y, and the loss function returns a Tensor containing the
# loss.
loss = loss_fn(y_pred, y)
print(t, loss.item())
# Zero the gradients before running the backward pass.
model.zero_grad()
# Backward pass: compute gradient of the loss with respect to all the learnable
# parameters of the model. Internally, the parameters of each Module are stored
# in Tensors with requires_grad=True, so this call will compute gradients for
# all learnable parameters in the model.
loss.backward()
# Update the weights using gradient descent. Each parameter is a Tensor, so
# we can access its gradients like we did before.
with torch.no_grad():
for param in model.parameters():
param -= learning_rate * param.grad
PyTorch: optim
这一次我们不再手动更新模型的weights,而是使用optim这个包来帮助我们更新参数。 optim这个package提供了各种不同的模型优化方法,包括SGD+momentum, RMSProp, Adam等等。
import torch
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
# Use the nn package to define our model and loss function.
model = torch.nn.Sequential(
torch.nn.Linear(D_in, H),
torch.nn.ReLU(),
torch.nn.Linear(H, D_out),
)
loss_fn = torch.nn.MSELoss(reduction='sum')
# Use the optim package to define an Optimizer that will update the weights of
# the model for us. Here we will use Adam; the optim package contains many other
# optimization algoriths. The first argument to the Adam constructor tells the
# optimizer which Tensors it should update.
learning_rate = 1e-4
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
for t in range(500):
# Forward pass: compute predicted y by passing x to the model.
y_pred = model(x)
# Compute and print loss.
loss = loss_fn(y_pred, y)
print(t, loss.item())
# Before the backward pass, use the optimizer object to zero all of the
# gradients for the variables it will update (which are the learnable
# weights of the model). This is because by default, gradients are
# accumulated in buffers( i.e, not overwritten) whenever .backward()
# is called. Checkout docs of torch.autograd.backward for more details.
optimizer.zero_grad()
# Backward pass: compute gradient of the loss with respect to model
# parameters
loss.backward()
# Calling the step function on an Optimizer makes an update to its
# parameters
optimizer.step()
PyTorch: 自定义 nn Modules
我们可以定义一个模型,这个模型继承自nn.Module类。如果需要定义一个比Sequential模型更加复杂的模型,就需要定义nn.Module模型。
import torch
class TwoLayerNet(torch.nn.Module):
def __init__(self, D_in, H, D_out):
"""
In the constructor we instantiate two nn.Linear modules and assign them as
member variables.
"""
super(TwoLayerNet, self).__init__()
self.linear1 = torch.nn.Linear(D_in, H)
self.linear2 = torch.nn.Linear(H, D_out)
def forward(self, x):
"""
In the forward function we accept a Tensor of input data and we must return
a Tensor of output data. We can use Modules defined in the constructor as
well as arbitrary operators on Tensors.
"""
h_relu = self.linear1(x).clamp(min=0)
y_pred = self.linear2(h_relu)
return y_pred
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random Tensors to hold inputs and outputs
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
# Construct our model by instantiating the class defined above
model = TwoLayerNet(D_in, H, D_out)
# Construct our loss function and an Optimizer. The call to model.parameters()
# in the SGD constructor will contain the learnable parameters of the two
# nn.Linear modules which are members of the model.
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-4)
for t in range(500):
# Forward pass: Compute predicted y by passing x to the model
y_pred = model(x)
# Compute and print loss
loss = criterion(y_pred, y)
print(t, loss.item())
# Zero gradients, perform a backward pass, and update the weights.
optimizer.zero_grad()
loss.backward()
optimizer.step()