官方所有教程的地址:pytorch.org/tutorials
以下是基于实例来入门pytorch
Learning PyTorch with Examples
This tutorial introduces the fundamental concepts ofPyTorchthrough self-containedexamples.
At its core, PyTorch provides two main features:
--An n-dimensional Tensor, similar to numpy but can run on GPUs
--Automatic differentiation for building and training neural networks
We will use a fully-connected ReLU network as our running example. The network will have a single hidden layer, and will be trained with
gradient descent to fit random data by minimizing the Euclidean distance between the network output and the true output.
Note
You can browse the individual examples at the end of this page.
Table of Contents
PyTorch: Variables and autograd
PyTorch: Defining new autograd functions
Tensors
Before introducing PyTorch, we will first implement the network using numpy.
Numpy provides an n-dimensional array object, and many functions for manipulating these arrays. Numpy is a generic framework for scientific computing; it does not know anything about computation graphs, or deep learning, or gradients. However we can easily use numpy to fit a two-layer network to random data by manually implementing the forward and backward passes through the network using numpy operations:
# -*- coding: utf-8 -*-
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
PyTorch: Tensors
Numpy is a great framework, but it cannot utilize GPUs to accelerate itsnumerical computations. For modern deep neural networks, GPUs oftenprovide speedups of 50x or greater, sounfortunately numpy won’t be enough for modern deep learning.
Here we introduce the most fundamental PyTorch concept: theTensor.A PyTorch Tensor is conceptually identical to a numpy array: a Tensor isan n-dimensional array, and PyTorch provides many functions foroperating on these Tensors. Like numpy arrays, PyTorch Tensors do notknow anything about deep learning or computational graphs or gradients;they are a generic tool for scientific computing.
However unlike numpy, PyTorch Tensors can utilize GPUs to accelerate their numeric computations. To run a PyTorch Tensor on GPU, you simply need to cast it to a new datatype.
Here we use PyTorch Tensors to fit a two-layer network to random data.
Like the numpy example above we need to manually implement the forward and backward passes through the network:
# -*- coding: utf-8 -*-
import torch
dtype = torch.FloatTensor
# dtype = torch.cuda.FloatTensor # 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).type(dtype)
y = torch.randn(N, D_out).type(dtype)
# Randomly initialize weights
w1 = torch.randn(D_in, H).type(dtype)
w2 = torch.randn(H, D_out).type(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()
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
PyTorch: Variables and autograd
In the above examples, we had to manually implement both the forward and
backward passes of our neural network. Manually implementing the
backward pass is not a big deal for a small two-layer network, but can quickly get very hairy for large complex networks.
Thankfully, we can useautomatic differentiationto automate the computation of backward passes in neural networks. Theautogradpackage in PyTorch provides exactly this functionality.When using autograd, the forward pass of your network will define acomputational graph; nodes in the graph will be Tensors, and edgeswill be functions that produce output Tensors from input Tensors.Backpropagating through this graph then allows you to easily computegradients.
This sounds complicated, it’s pretty simple to use in practice. We wrapour PyTorch Tensors inVariableobjects; a Variable represents anode in a computational graph. Ifxis a Variable thenx.dataisa Tensor, andx.gradis another Variable holding the gradient ofxwith respect to some scalar value.
PyTorch Variables have the same API as PyTorch Tensors: (almost) any operation that you can perform on a Tensor also works on Variables; the difference is that using Variables defines a computational graph, allowing you to automatically compute gradients.
Here we use PyTorch Variables and autograd to implement our two-layer network; now we no longer need to manually implement the backward pass through the network:
# -*- coding: utf-8 -*-
import torch
from torch.autograd import Variable
dtype = torch.FloatTensor
# dtype = torch.cuda.FloatTensor # 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, and wrap them in Variables.
# Setting requires_grad=False indicates that we do not need to compute gradients
# with respect to these Variables during the backward pass.
x = Variable(torch.randn(N, D_in).type(dtype), requires_grad=False)
y = Variable(torch.randn(N, D_out).type(dtype), requires_grad=False)
# Create random Tensors for weights, and wrap them in Variables.
# Setting requires_grad=True indicates that we want to compute gradients with
# respect to these Variables during the backward pass.
w1 = Variable(torch.randn(D_in, H).type(dtype), requires_grad=True)
w2 = Variable(torch.randn(H, D_out).type(dtype), requires_grad=True)
learning_rate = 1e-6
for t in range(500):
# Forward pass: compute predicted y using operations on Variables; these
# are exactly the same operations we used to compute the forward pass using
# Tensors, but we do not need to keep references to intermediate values since
# we are not implementing the backward pass by hand.
y_pred = x.mm(w1).clamp(min=0).mm(w2)
# Compute and print loss using operations on Variables.
# Now loss is a Variable of shape (1,) and loss.data is a Tensor of shape
# (1,); loss.data[0] is a scalar value holding the loss.
loss = (y_pred - y).pow(2).sum()
print(t, loss.data[0])
# Use autograd to compute the backward pass. This call will compute the
# gradient of loss with respect to all Variables with requires_grad=True.
# After this call w1.grad and w2.grad will be Variables holding the gradient
# of the loss with respect to w1 and w2 respectively.
loss.backward()
# Update weights using gradient descent; w1.data and w2.data are Tensors,
# w1.grad and w2.grad are Variables and w1.grad.data and w2.grad.data are
# Tensors.
w1.data -= learning_rate * w1.grad.data
w2.data -= learning_rate * w2.grad.data
# Manually zero the gradients after updating weights
w1.grad.data.zero_()
w2.grad.data.zero_()
PyTorch: Defining new autograd functions
Under the hood, each primitive autograd operator is really two functionsthat operate on Tensors. Theforwardfunction computes outputTensors from input Tensors. Thebackwardfunction receives thegradient of the output Tensors with respect to some scalar value, andcomputes the gradient of the input Tensors with respect to that samescalar value.
In PyTorch we can easily define our own autograd operator by defining asubclass oftorch.autograd.Functionand implementing theforwardandbackwardfunctions. We can then use our new autograd operator byconstructing an instance and calling it like a function, passingVariables containing input data.
In this example we define our own custom autograd function for
performing the ReLU nonlinearity, and use it to implement our two-layer
network:
# -*- coding: utf-8 -*-
import torch
from torch.autograd import Variable
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.
"""
def forward(self, input):
"""
In the forward pass we receive a Tensor containing the input and return a
Tensor containing the output. You can cache arbitrary Tensors for use in the
backward pass using the save_for_backward method.
"""
self.save_for_backward(input)
return input.clamp(min=0)
def backward(self, grad_output):
"""
In the backward pass we receive a Tensor containing the gradient of the loss
with respect to the output, and we need to compute the gradient of the loss
with respect to the input.
"""
input, = self.saved_tensors
grad_input = grad_output.clone()
grad_input[input < 0] = 0
return grad_input
dtype = torch.FloatTensor
# dtype = torch.cuda.FloatTensor # 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, and wrap them in Variables.
x = Variable(torch.randn(N, D_in).type(dtype), requires_grad=False)
y = Variable(torch.randn(N, D_out).type(dtype), requires_grad=False)
# Create random Tensors for weights, and wrap them in Variables.
w1 = Variable(torch.randn(D_in, H).type(dtype), requires_grad=True)
w2 = Variable(torch.randn(H, D_out).type(dtype), requires_grad=True)
learning_rate = 1e-6
for t in range(500):
# Construct an instance of our MyReLU class to use in our network
relu = MyReLU()
# Forward pass: compute predicted y using operations on Variables; we compute
# ReLU using our custom autograd operation.
y_pred = relu(x.mm(w1)).mm(w2)
# Compute and print loss
loss = (y_pred - y).pow(2).sum()
print(t, loss.data[0])
# Use autograd to compute the backward pass.
loss.backward()
# Update weights using gradient descent
w1.data -= learning_rate * w1.grad.data
w2.data -= learning_rate * w2.grad.data
# Manually zero the gradients after updating weights
w1.grad.data.zero_()
w2.grad.data.zero_()
TensorFlow: Static Graphs
PyTorch autograd looks a lot like TensorFlow: in both frameworks wedefine a computational graph, and use automatic differentiation tocompute gradients. The biggest difference between the two is thatTensorFlow’s computational graphs arestaticand PyTorch usesdynamiccomputational graphs.
In TensorFlow, we define the computational graph once and then execute
the same graph over and over again, possibly feeding different input
data to the graph. In PyTorch, each forward pass defines a new
computational graph.
Static graphs are nice because you can optimize the graph up front; for
example a framework might decide to fuse some graph operations for
efficiency, or to come up with a strategy for distributing the graph
across many GPUs or many machines. If you are reusing the same graph
over and over, then this potentially costly up-front optimization can be
amortized as the same graph is rerun over and over.
One aspect where static and dynamic graphs differ is control flow. Forsome models we may wish to perform different computation for each datapoint; for example a recurrent network might be unrolled for differentnumbers of time steps for each data point; this unrolling can beimplemented as a loop. With a static graph the loop construct needs tobe a part of the graph; for this reason TensorFlow provides operatorssuch astf.scanfor embedding loops into the graph. With dynamicgraphs the situation is simpler: since we build graphs on-the-fly foreach example, we can use normal imperative flow control to performcomputation that differs for each input.
To contrast with the PyTorch autograd example above, here we use
TensorFlow to fit a simple two-layer net:
# -*- coding: utf-8 -*-
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)
nnmodule
Computational graphs and autograd are a very powerful paradigm for
defining complex operators and automatically taking derivatives; however
for large neural networks raw autograd can be a bit too low-level.
When building neural networks we frequently think of arranging thecomputation intolayers, some of which havelearnable parameterswhich will be optimized during learning.
In TensorFlow, packages likeKeras,TensorFlow-Slim,andTFLearnprovide higher-level abstractionsover raw computational graphs that are useful for building neuralnetworks.
In PyTorch, thennpackage serves this same purpose. Thennpackage defines a set ofModules, which are roughly equivalent toneural network layers. A Module receives input Variables and computesoutput Variables, but may also hold internal state such as Variablescontaining learnable parameters. Thennpackage also defines a setof useful loss functions that are commonly used when training neuralnetworks.
In this example we use thennpackage to implement our two-layernetwork:
# -*- coding: utf-8 -*-
import torch
from torch.autograd import Variable
# 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, and wrap them in Variables.
x = Variable(torch.randn(N, D_in))
y = Variable(torch.randn(N, D_out), requires_grad=False)
# 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 Variables 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(size_average=False)
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 Variable of input data to the Module and it produces
# a Variable of output data.
y_pred = model(x)
# Compute and print loss. We pass Variables containing the predicted and true
# values of y, and the loss function returns a Variable containing the
# loss.
loss = loss_fn(y_pred, y)
print(t, loss.data[0])
# 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 Variables 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 Variable, so
# we can access its data and gradients like we did before.
for param in model.parameters():
param.data -= learning_rate * param.grad.data
PyTorch: optim
Up to this point we have updated the weights of our models by manuallymutating the.datamember for Variables holding learnableparameters. This is not a huge burden for simple optimization algorithmslike stochastic gradient descent, but in practice we often train neuralnetworks using more sophisticated optimizers like AdaGrad, RMSProp,Adam, etc.
Theoptimpackage in PyTorch abstracts the idea of an optimizationalgorithm and provides implementations of commonly used optimizationalgorithms.
In this example we will use thennpackage to define our model asbefore, but we will optimize the model using the Adam algorithm providedby theoptimpackage:
# -*- coding: utf-8 -*-
import torch
from torch.autograd import Variable
# 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, and wrap them in Variables.
x = Variable(torch.randn(N, D_in))
y = Variable(torch.randn(N, D_out), requires_grad=False)
# 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(size_average=False)
# 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 Variables 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.data[0])
# 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)
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: Custom nn Modules
Sometimes you will want to specify models that are more complex than asequence of existing Modules; for these cases you can define your ownModules by subclassingnn.Moduleand defining aforwardwhichreceives input Variables and produces output Variables using othermodules or other autograd operations on Variables.
In this example we implement our two-layer network as a custom Module
subclass:
# -*- coding: utf-8 -*-
import torch
from torch.autograd import Variable
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 Variable of input data and we must return
a Variable of output data. We can use Modules defined in the constructor as
well as arbitrary operators on Variables.
"""
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, and wrap them in Variables
x = Variable(torch.randn(N, D_in))
y = Variable(torch.randn(N, D_out), requires_grad=False)
# 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(size_average=False)
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.data[0])
# Zero gradients, perform a backward pass, and update the weights.
optimizer.zero_grad()
loss.backward()
optimizer.step()
PyTorch: Control Flow + Weight Sharing
As an example of dynamic graphs and weight sharing, we implement a very
strange model: a fully-connected ReLU network that on each forward pass
chooses a random number between 1 and 4 and uses that many hidden
layers, reusing the same weights multiple times to compute the innermost
hidden layers.
For this model we can use normal Python flow control to implement the loop,
and we can implement weight sharing among the innermost layers by simply
reusing the same Module multiple times when defining the forward pass.
We can easily implement this model as a Module subclass:
# -*- coding: utf-8 -*-
import random
import torch
from torch.autograd import Variable
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, and wrap them in Variables
x = Variable(torch.randn(N, D_in))
y = Variable(torch.randn(N, D_out), requires_grad=False)
# 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(size_average=False)
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.data[0])
# Zero gradients, perform a backward pass, and update the weights.
optimizer.zero_grad()
loss.backward()
optimizer.step()
