torch

1.从数据直接构建tensor

x = torch.tensor([5.5,3])

2.从已有的tensor构建一个tensor。这些方法会重用原来tensor的特征。

x = x.new_ones(5,3,dtype=torch.double)

torch.randn_like(x,dtype=torch.float)

3.得到tensor的形状

x.shape()

x.size()

4.tensor的运算

x = torch.rand(5,3)     y = torch.rand(5,3)

x+y    torch.add(x,y)

result = torch.empty(5,3)     result = x+y

y.add_()  #把结果保存到里面

5.numpy里面的indexing都可以在tensor使用

x[:,1:]

6.resizing(在numpy里面用reshape在torch里面用view)

x = torch.randn(4,4)   y = x.view(16)  z = x.view(-1,8)

7.如果只用一个元素的tensor 使用。item() 方法可以把里面的value 变成Python数值

x = torch.randn(1)     x.data   x.grad    x.item()    z.transpose(1,0)

8 .numpy和tensor 之间的转化

a = torch.ones(5)    b = a.numpy()  #a，b共享内存空间

a = np.ones(5)       b = torch.from_numpy(a)  #a，b共享内存空间

9.cuda tensor

if torch.cuda.is_available():
　　device = torch.device("cuda")

        y = torch.ones_like(x,device=device)

　　 x = x.to(device)

y.cpu().data.numpy()           y.to("cpu").data.numpy()  model = model.cuda()

10. 用numpy 实现两层神经网络

N , D_in, H, D_out = 64,1000,100,10

x = np.random.randn(N,D_in)
y = np.random.randn(N,D_out)
w1 = np.random.randn(D_in,H)
w2 = np.random.randn(H,D_out)
learning_rate = 1e-6
for t in range(500):
　　h = x.dot(w1)  #(N,H)
　　h_relu = np.maxinum(h,0)
　　y_pred = h_relu.dot(w2)
　　#compute loss
　　loss = np.square(y_pred - y).sum()
　　print(t,loss)
      grad_y_pred = 2.0*(y_pred-y)
      grad_w2 = h_relu.T.dot(grad_y_pred)
      grad_h_relu = grad_y_pred.dot(w2.T)
      grad_h = grad_h_relu.copy()
      grad_h[h<0] = 0
      grad_w1 = x.T.dot(grad_h)
      w1 -= learning_rate*grad_w1
      w2 -=learning_rate*grad_w2

11.用tensors 实现两层神经网络

  

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

autograd

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_()

optim

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()

自定义的nn Modules

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()