The first is a two-tier network, using the numpy version and the python version
In fact, if you compare carefully, the difference is not big. The amount of code is similar. Because there is no automatic gradient calculation using pytorch.
numpy version
# -*- 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 version
# -*- coding: utf-8 -*- 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
- Using autograd
The calculation of neural network will be transformed into calculation graph. The nodes in the graph will become tensor s, and the edge is the function from the output node to the next node.
use automatic differentiation to compute gradients
When using autograd, the forward pass of your network will define a computational graph; nodes in the graph will be Tensors, and edges will be functions that produce output Tensors from input Tensors.
# -*- coding: utf-8 -*- 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 Tensors to hold input and outputs. # Setting requires_grad=False indicates that we do not need to compute gradients # with respect to these Tensors during the backward pass. x = torch.randn(N, D_in, device=device, dtype=dtype) y = torch.randn(N, D_out, device=device, dtype=dtype) # Create random Tensors for weights. # Setting requires_grad=True indicates that we want to compute gradients with # respect to these Tensors during the backward pass. 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): # Forward pass: compute predicted y using operations on Tensors; 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 Tensors. # Now loss is a Tensor of shape (1,) # loss.item() gets the a scalar value held in the loss. 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() # Manually update weights using gradient descent. Wrap in torch.no_grad() # because weights have requires_grad=True, but we don't need to track this # in autograd. # An alternative way is to operate on weight.data and weight.grad.data. # Recall that tensor.data gives a tensor that shares the storage with # tensor, but doesn't track history. # You can also use torch.optim.SGD to achieve this. 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_()
Custom autograd function
You need to define a subclass of the torch.automatic.function and implement the forward and backward functions.
# -*- coding: utf-8 -*- 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, input): """ In the forward pass we receive a Tensor containing the input and return a Tensor containing the output. ctx is a context object that can be used to stash information for backward computation. You can cache arbitrary objects for use in the backward pass using the ctx.save_for_backward method. """ ctx.save_for_backward(input) return input.clamp(min=0) @staticmethod def backward(ctx, 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, = ctx.saved_tensors grad_input = grad_output.clone() grad_input[input < 0] = 0 return grad_input 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 Tensors to hold input and outputs. x = torch.randn(N, D_in, device=device, dtype=dtype) y = torch.randn(N, D_out, device=device, dtype=dtype) # Create random Tensors for weights. 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): # To apply our Function, we use Function.apply method. We alias this as 'relu'. relu = MyReLU.apply # Forward pass: compute predicted y using operations; 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.item()) # Use autograd to compute the backward pass. loss.backward() # Update weights using gradient descent 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_()
About calculation chart
-
In fact, tensorflow is very similar to pytorch, which uses graph to track calculation. The difference is that tensorflow uses static graphs, while pytorch uses dynamic graphs.
-
The advantage of static graph is that you can optimize the structure of graph in advance, which is good for repeated calculation.
-
The advantage of dynamic graphs is that you can use commands to perform different calculations for each data point.
TensorFlow version
# -*- 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)
About nn module
-
nn package defines a set of modules, which are roughly equivalent to the neural network layer.
-
The module receives the input tensor and calculates the output tensor, but it can also maintain the internal state, such as the tensor containing the learnable parameters.
-
nn package also defines a set of useful loss functions commonly used in neural network training.
nn version
# -*- coding: utf-8 -*- 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
optim in nn
- The optim package in PyTorch extracts the idea of optimization algorithm and provides the implementation of common optimization algorithm.
Using NN and nn.optim
# -*- coding: utf-8 -*- 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()
Custom module
- You can customize the network you want.
Custom module version
(pay attention to the difference between the previous definitions)
# -*- coding: utf-8 -*- 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) # Previous definition # model = torch.nn.Sequential( # torch.nn.Linear(D_in, H), # torch.nn.ReLU(), # torch.nn.Linear(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()