import numpy as np

# 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 = np.random.randn(N, D_in)
y = np.random.randn(N, D_out)

# Randomly initialize weights
w1 = np.random.randn(D_in, H)
w2 = np.random.randn(H, D_out)

learning_rate = 1e-6
for t in range(500):
    # Forward pass: compute predicted y
    h = x.dot(w1)
    h_relu = np.maximum(h, 0)
    y_pred = h_relu.dot(w2)

    # Compute and print loss
    loss = np.square(y_pred - y).sum()
    print(t, loss)

    # Backprop to compute gradients of w1 and w2 with respect to loss
    
    # loss = (y_pred - y) ** 2
    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)

    # Update weights
    w1 -= learning_rate * grad_w1
    w2 -= learning_rate * grad_w2

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

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_()

import torch

class MyReLU(torch.autograd.Function):
  """
  We can implement our own custom autograd Functions by subclassing
  torch.autograd.Function and implementing the forward and backward passes
  which operate on Tensors.
  """
  @staticmethod
  def forward(ctx, x):
    """
    In the forward pass we receive a context object and a Tensor containing the
    input; we must return a Tensor containing the output, and we can use the
    context object to cache objects for use in the backward pass.
    """
    ctx.save_for_backward(x)
    return x.clamp(min=0)

  @staticmethod
  def backward(ctx, grad_output):
    """
    In the backward pass we receive the context object and a Tensor containing
    the gradient of the loss with respect to the output produced during the
    forward pass. We can retrieve cached data from the context object, and must
    compute and return the gradient of the loss with respect to the input to the
    forward function.
    """
    x, = ctx.saved_tensors
    grad_x = grad_output.clone()
    grad_x[x < 0] = 0
    return grad_x


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；
    # 使用自定义的ReLU
    y_pred = MyReLU.apply(x.mm(w1)).mm(w2)
   
    # 通过前向传播计算loss
    loss = (y_pred - y).pow(2).sum()
    print(t, loss.item())

    loss.backward()

    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_()

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

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')

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)

    # 计算损失
    loss = loss_fn(y_pred, y)
    print(t, loss.item())
    # 梯度清零
    optimizer.zero_grad()
    # 反向过程：计算梯度
    loss.backward()

    # 更新参数
    optimizer.step()

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

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()