Simple examples to introduce PyTorch

# Code in file tensor/two_layer_net_numpy.py
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
  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

# Code in file tensor/two_layer_net_tensor.py
import torch

device = torch.device('cpu')
# device = torch.device('cuda') # 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)
y = torch.randn(N, D_out, device=device)

# Randomly initialize weights
w1 = torch.randn(D_in, H, device=device)
w2 = torch.randn(H, D_out, device=device)

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 is a scalar, and is stored in a PyTorch Tensor
  # of shape (); we can get its value as a Python number with loss.item().
  loss = (y_pred - y).pow(2).sum()
  print(t, loss.item())

  # 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

# Code in file autograd/two_layer_net_autograd.py
import torch

device = torch.device('cpu')
# device = torch.device('cuda') # 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 Tensors to hold input and outputs
x = torch.randn(N, D_in, device=device)
y = torch.randn(N, D_out, device=device)

# Create random Tensors for weights; setting requires_grad=True means that we
# want to compute gradients for these Tensors during the backward pass.
w1 = torch.randn(D_in, H, device=device, requires_grad=True)
w2 = torch.randn(H, D_out, device=device, requires_grad=True)

learning_rate = 1e-6
for t in range(500):
  # Forward pass: compute predicted y using operations on Tensors. Since w1 and
  # w2 have requires_grad=True, operations involving these Tensors will cause
  # PyTorch to build a computational graph, allowing automatic computation of
  # gradients. Since we are no longer implementing the backward pass by hand we
  # don't need to keep references to intermediate values.
  y_pred = x.mm(w1).clamp(min=0).mm(w2)
  
  # Compute and print loss. Loss is a Tensor of shape (), and loss.item()
  # is a Python number giving its value.
  loss = (y_pred - y).pow(2).sum()
  print(t, loss.item())

  # Use autograd to compute the backward pass. This call will compute the
  # gradient of loss with respect to all Tensors with requires_grad=True.
  # After this call w1.grad and w2.grad will be Tensors holding the gradient
  # of the loss with respect to w1 and w2 respectively.
  loss.backward()

  # Update weights using gradient descent. For this step we just want to mutate
  # the values of w1 and w2 in-place; we don't want to build up a computational
  # graph for the update steps, so we use the torch.no_grad() context manager
  # to prevent PyTorch from building a computational graph for the updates
  with torch.no_grad():
    w1 -= learning_rate * w1.grad
    w2 -= learning_rate * w2.grad

    # Manually zero the gradients after running the backward pass
    w1.grad.zero_()
    w2.grad.zero_()

# Code in file autograd/two_layer_net_custom_function.py
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


device = torch.device('cpu')
# device = torch.device('cuda') # 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 Tensors to hold input and output
x = torch.randn(N, D_in, device=device)
y = torch.randn(N, D_out, device=device)

# Create random Tensors for weights.
w1 = torch.randn(D_in, H, device=device, requires_grad=True)
w2 = torch.randn(H, D_out, device=device, requires_grad=True)

learning_rate = 1e-6
for t in range(500):
  # Forward pass: compute predicted y using operations on Tensors; we call our
  # custom ReLU implementation using the MyReLU.apply function
  y_pred = MyReLU.apply(x.mm(w1)).mm(w2)
 
  # Compute and print loss
  loss = (y_pred - y).pow(2).sum()
  print(t, loss.item())

  # Use autograd to compute the backward pass.
  loss.backward()

  with torch.no_grad():
    # Update weights using gradient descent
    w1 -= learning_rate * w1.grad
    w2 -= learning_rate * w2.grad

    # Manually zero the gradients after running the backward pass
    w1.grad.zero_()
    w2.grad.zero_()

# Code in file autograd/tf_two_layer_net.py
import tensorflow as tf
import numpy as np

# First we set up the computational graph:

# 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 placeholders for the input and target data; these will be filled
# with real data when we execute the graph.
x = tf.placeholder(tf.float32, shape=(None, D_in))
y = tf.placeholder(tf.float32, shape=(None, D_out))

# Create Variables for the weights and initialize them with random data.
# A TensorFlow Variable persists its value across executions of the graph.
w1 = tf.Variable(tf.random_normal((D_in, H)))
w2 = tf.Variable(tf.random_normal((H, D_out)))

# Forward pass: Compute the predicted y using operations on TensorFlow Tensors.
# Note that this code does not actually perform any numeric operations; it
# merely sets up the computational graph that we will later execute.
h = tf.matmul(x, w1)
h_relu = tf.maximum(h, tf.zeros(1))
y_pred = tf.matmul(h_relu, w2)

# Compute loss using operations on TensorFlow Tensors
loss = tf.reduce_sum((y - y_pred) ** 2.0)

# Compute gradient of the loss with respect to w1 and w2.
grad_w1, grad_w2 = tf.gradients(loss, [w1, w2])

# Update the weights using gradient descent. To actually update the weights
# we need to evaluate new_w1 and new_w2 when executing the graph. Note that
# in TensorFlow the the act of updating the value of the weights is part of
# the computational graph; in PyTorch this happens outside the computational
# graph.
learning_rate = 1e-6
new_w1 = w1.assign(w1 - learning_rate * grad_w1)
new_w2 = w2.assign(w2 - learning_rate * grad_w2)

# Now we have built our computational graph, so we enter a TensorFlow session to
# actually execute the graph.
with tf.Session() as sess:
  # Run the graph once to initialize the Variables w1 and w2.
  sess.run(tf.global_variables_initializer())

  # Create numpy arrays holding the actual data for the inputs x and targets y
  x_value = np.random.randn(N, D_in)
  y_value = np.random.randn(N, D_out)
  for _ in range(500):
    # Execute the graph many times. Each time it executes we want to bind
    # x_value to x and y_value to y, specified with the feed_dict argument.
    # Each time we execute the graph we want to compute the values for loss,
    # new_w1, and new_w2; the values of these Tensors are returned as numpy
    # arrays.
    loss_value, _, _ = sess.run([loss, new_w1, new_w2],
                                feed_dict={x: x_value, y: y_value})
    print(loss_value)

# Code in file nn/two_layer_net_nn.py
import torch

device = torch.device('cpu')
# device = torch.device('cuda') # 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 Tensors to hold inputs and outputs
x = torch.randn(N, D_in, device=device)
y = torch.randn(N, D_out, device=device)

# 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.
# After constructing the model we use the .to() method to move it to the
# desired device.
model = torch.nn.Sequential(
          torch.nn.Linear(D_in, H),
          torch.nn.ReLU(),
          torch.nn.Linear(H, D_out),
        ).to(device)

# The nn package also contains definitions of popular loss functions; in this
# case we will use Mean Squared Error (MSE) as our loss function. Setting
# reduction='sum' means that we are computing the *sum* of squared errors rather
# than the mean; this is for consistency with the examples above where we
# manually compute the loss, but in practice it is more common to use mean
# squared error as a loss by setting reduction='elementwise_mean'.
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 data and gradients like we did before.
  with torch.no_grad():
    for param in model.parameters():
      param.data -= learning_rate * param.grad

# Code in file nn/two_layer_net_optim.py
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 algorithms. 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 Tensors it will update (which are the learnable weights
  # of the model)
  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()

# Code in file nn/two_layer_net_module.py
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 (differentiable) operations 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.
loss_fn = 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 = loss_fn(y_pred, y)
  print(t, loss.item())

  # Zero gradients, perform a backward pass, and update the weights.
  optimizer.zero_grad()
  loss.backward()
  optimizer.step()

# Code in file nn/dynamic_net.py
import random
import torch

class DynamicNet(torch.nn.Module):
  def __init__(self, D_in, H, D_out):
    """
    In the constructor we construct three nn.Linear instances that we will use
    in the forward pass.
    """
    super(DynamicNet, self).__init__()
    self.input_linear = torch.nn.Linear(D_in, H)
    self.middle_linear = torch.nn.Linear(H, H)
    self.output_linear = torch.nn.Linear(H, D_out)

  def forward(self, x):
    """
    For the forward pass of the model, we randomly choose either 0, 1, 2, or 3
    and reuse the middle_linear Module that many times to compute hidden layer
    representations.

    Since each forward pass builds a dynamic computation graph, we can use normal
    Python control-flow operators like loops or conditional statements when
    defining the forward pass of the model.

    Here we also see that it is perfectly safe to reuse the same Module many
    times when defining a computational graph. This is a big improvement from Lua
    Torch, where each Module could be used only once.
    """
    h_relu = self.input_linear(x).clamp(min=0)
    for _ in range(random.randint(0, 3)):
      h_relu = self.middle_linear(h_relu).clamp(min=0)
    y_pred = self.output_linear(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 = DynamicNet(D_in, H, D_out)

# Construct our loss function and an Optimizer. Training this strange model with
# vanilla stochastic gradient descent is tough, so we use momentum
criterion = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.SGD(model.parameters(), lr=1e-4, momentum=0.9)
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()