In [ ]:

    

import torch
import torchvision
import torchvision.transforms as transforms
from torch.autograd import Variable


    

In [ ]:

    

x = Variable(torch.ones(2, 2), requires_grad=True)


    

In [ ]:

    

y = x + 2


    

In [ ]:

    

z = y * y * 3
out = z.mean()


    

In [ ]:

    

print(z)


    

In [ ]:

    

print(x.grad)


    

In [ ]:

    

out.backward()


    

In [ ]:

    

x.grad


    

In [ ]:

    

print(y.grad)


    

In [ ]:

    

print(z.grad)


    

In [ ]:

    

print(out.grad)


    

In [ ]:

    

x = torch.randn(3)


    

In [ ]:

    

x = Variable(x, requires_grad=True)


    

In [ ]:

    

y = x * 2


    

In [ ]:

    

while y.data.norm() < 1000:
    y = y * 2

print(y)


    

In [ ]:

    

gradients = torch.FloatTensor([0.1, 1.0, 0.0001])
y.backward(gradients)


    

In [ ]:

    

print(x.grad)


    

In [ ]:

    

print(y.grad)


    

In [ ]:

    

import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 100, 5)
        self.conv2 = nn.Conv2d(100, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


    

In [ ]:

    

import torch
import torchvision
import torchvision.transforms as transforms


    

In [ ]:

    

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')


    

In [ ]:

    

import matplotlib.pyplot as plt
import numpy as np

# functions to show an image


def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))


# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
plt.show()


    

In [ ]:

    

from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 200, 5, padding=2)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(200, 100, 5, padding=2)
#         self.pool2 = nn.MaxPool2d(2, 2)
        self.conv3 = nn.Conv2d(100, 50, 5, padding=2)
#         self.pool3 = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(800, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))
#         print(x.size())
        x = self.pool1(F.relu(self.conv2(x)))
#         print(x.size())
        x = self.pool1(F.relu(self.conv3(x)))
#         print(x.size())
        x = x.view(-1, 800)
#         print(x.size())
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = F.softmax(self.fc3(x))
        return x


net = Net()
net.cuda()


    

In [ ]:

    

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=.9)


    

In [ ]:

    

for epoch in range(2000):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        inputs, labels = data

        # wrap them in Variable
        inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.data[0]
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')


    

In [ ]:

    

dataiter = iter(testloader)
images, labels = dataiter.next()

# print images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
plt.show()


    

In [ ]:

    

images = images.cuda()
outputs = net(Variable(images))


    

In [ ]:

    

_, predicted = torch.max(outputs.data, 1)

print('Predicted: ', ' '.join('%5s' % classes[predicted[j][0]]
                              for j in range(4)))


    

In [ ]:

    

correct = 0
total = 0
for data in testloader:
    images, labels = data
    images = images.cuda()
    outputs = net(Variable(images))
    _, predicted = torch.max(outputs.data, 1)
    total += labels.size(0)
    correct += (predicted.cpu().numpy().ravel() ==
                labels.cpu().numpy().ravel()).sum()

print(('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total)))


    

In [ ]:

    

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
for data in testloader:
    images, labels = data
    images = images.cuda()
    outputs = net(Variable(images))
    _, predicted = torch.max(outputs.data, 1)
    c = (predicted.cpu().numpy().ravel() ==
         labels.cpu().numpy().ravel()).squeeze()
    for i in range(4):
        label = labels[i]
        class_correct[label] += c[i]
        class_total[label] += 1


for i in range(10):
    print('Accuracy of %5s : %2d %%' % (
        classes[i], 100 * class_correct[i] / class_total[i]))


    

In [ ]:

    

# 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


    

In [ ]:

    

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


    

In [ ]:

    

# -*- 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_()


    

In [ ]:

    

# -*- 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_()


    

In [ ]:

    

# -*- 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)


    

In [ ]:

    

# -*- 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


    

In [ ]:

    

# -*- 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()


    

In [ ]:

    

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()


    

In [ ]:

    

# -*- 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()


    

In [ ]:

    

# License: BSD
# Author: Sasank Chilamkurthy

from __future__ import print_function, division

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
from torch.autograd import Variable
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os

plt.ion()   # interactive mode


    

In [ ]:

    

# Data augmentation and normalization for training
# Just normalization for validation
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomSizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Scale(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

data_dir = 'hymenoptera_data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
dataloders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
                                             shuffle=True, num_workers=4)
              for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

use_gpu = torch.cuda.is_available()


    

In [ ]:

    

def imshow(inp, title=None):
    """Imshow for Tensor."""
    inp = inp.numpy().transpose((1, 2, 0))
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    inp = std * inp + mean
    plt.imshow(inp)
    if title is not None:
        plt.title(title)
    plt.pause(0.001)  # pause a bit so that plots are updated


# Get a batch of training data
inputs, classes = next(iter(dataloders['train']))

# Make a grid from batch
out = torchvision.utils.make_grid(inputs)

imshow(out, title=[class_names[x] for x in classes])


    

In [ ]:

    

def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = model.state_dict()
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                scheduler.step()
                model.train(True)  # Set model to training mode
            else:
                model.train(False)  # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for data in dataloders[phase]:
                # get the inputs
                inputs, labels = data

                # wrap them in Variable
                if use_gpu:
                    inputs = Variable(inputs.cuda())
                    labels = Variable(labels.cuda())
                else:
                    inputs, labels = Variable(inputs), Variable(labels)

                # zero the parameter gradients
                optimizer.zero_grad()

                # forward
                outputs = model(inputs)
                _, preds = torch.max(outputs.data, 1)
                loss = criterion(outputs, labels)

                # backward + optimize only if in training phase
                if phase == 'train':
                    loss.backward()
                    optimizer.step()

                # statistics
                running_loss += loss.data[0]
                running_corrects += torch.sum(preds == labels.data)

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects / dataset_sizes[phase]

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = model.state_dict()

        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model


    

In [ ]:

    

def visualize_model(model, num_images=6):
    images_so_far = 0
    fig = plt.figure()

    for i, data in enumerate(dataloders['val']):
        inputs, labels = data
        if use_gpu:
            inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())
        else:
            inputs, labels = Variable(inputs), Variable(labels)

        outputs = model(inputs)
        _, preds = torch.max(outputs.data, 1)

        for j in range(inputs.size()[0]):
            images_so_far += 1
            ax = plt.subplot(num_images//2, 2, images_so_far)
            ax.axis('off')
            ax.set_title('predicted: {}'.format(class_names[preds[j]]))
            imshow(inputs.cpu().data[j])

            if images_so_far == num_images:
                return


    

In [ ]:

    

model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)

if use_gpu:
    model_ft = model_ft.cuda()

criterion = nn.CrossEntropyLoss()

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)


    

In [ ]:

    

model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
                       num_epochs=25)


    

In [ ]:

    

visualize_model(model_ft)


    

In [ ]:

    

model_conv = torchvision.models.resnet18(pretrained=True)
for param in model_conv.parameters():
    param.requires_grad = False

# Parameters of newly constructed modules have requires_grad=True by default
num_ftrs = model_conv.fc.in_features
model_conv.fc = nn.Linear(num_ftrs, 2)

if use_gpu:
    model_conv = model_conv.cuda()

criterion = nn.CrossEntropyLoss()

# Observe that only parameters of final layer are being optimized as
# opoosed to before.
optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)


    

In [ ]:

    

model_conv = train_model(model_conv, criterion, optimizer_conv,
                         exp_lr_scheduler, num_epochs=25)


    

In [ ]:

    

visualize_model(model_conv)

plt.ioff()
plt.show()


    

In [ ]:

    

from __future__ import print_function, division
import os
import torch
import pandas as pd
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils

# Ignore warnings
import warnings
warnings.filterwarnings("ignore")

plt.ion()   # interactive mode


    

In [ ]:

    

landmarks_frame = pd.read_csv('faces/face_landmarks.csv')

n = 65
img_name = landmarks_frame.ix[n, 0]
landmarks = landmarks_frame.ix[n, 1:].as_matrix().astype('float')
landmarks = landmarks.reshape(-1, 2)

print('Image name: {}'.format(img_name))
print('Landmarks shape: {}'.format(landmarks.shape))
print('First 4 Landmarks: {}'.format(landmarks[:4]))


    

In [ ]:

    

def show_landmarks(image, landmarks):
    """Show image with landmarks"""
    plt.imshow(image)
    plt.scatter(landmarks[:, 0], landmarks[:, 1], s=10, marker='.', c='r')
    plt.pause(0.001)  # pause a bit so that plots are updated

plt.figure()
show_landmarks(io.imread(os.path.join('faces/', img_name)),
               landmarks)
plt.show()


    

In [ ]:

    

class FaceLandmarksDataset(Dataset):
    """Face Landmarks dataset."""

    def __init__(self, csv_file, root_dir, transform=None):
        """
        Args:
            csv_file (string): Path to the csv file with annotations.
            root_dir (string): Directory with all the images.
            transform (callable, optional): Optional transform to be applied
                on a sample.
        """
        self.landmarks_frame = pd.read_csv(csv_file)
        self.root_dir = root_dir
        self.transform = transform

    def __len__(self):
        return len(self.landmarks_frame)

    def __getitem__(self, idx):
        img_name = os.path.join(self.root_dir, self.landmarks_frame.ix[idx, 0])
        image = io.imread(img_name)
        landmarks = self.landmarks_frame.ix[idx, 1:].as_matrix().astype('float')
        landmarks = landmarks.reshape(-1, 2)
        sample = {'image': image, 'landmarks': landmarks}

        if self.transform:
            sample = self.transform(sample)

        return sample


    

In [ ]:

    

face_dataset = FaceLandmarksDataset(csv_file='faces/face_landmarks.csv',
                                    root_dir='faces/')

fig = plt.figure()

for i in range(len(face_dataset)):
    sample = face_dataset[i]

    print(i, sample['image'].shape, sample['landmarks'].shape)

    ax = plt.subplot(1, 4, i + 1)
    plt.tight_layout()
    ax.set_title('Sample #{}'.format(i))
    ax.axis('off')
    show_landmarks(**sample)

    if i == 3:
        plt.show()
        break


    

In [ ]:

    

class Rescale(object):
    """Rescale the image in a sample to a given size.

    Args:
        output_size (tuple or tuple): Desired output size. If tuple, output is
            matched to output_size. If int, smaller of image edges is matched
            to output_size keeping aspect ratio the same.
    """

    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        self.output_size = output_size

    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        h, w = image.shape[:2]
        if isinstance(self.output_size, int):
            if h > w:
                new_h, new_w = self.output_size * h / w, self.output_size
            else:
                new_h, new_w = self.output_size, self.output_size * w / h
        else:
            new_h, new_w = self.output_size

        new_h, new_w = int(new_h), int(new_w)

        img = transform.resize(image, (new_h, new_w))

        # h and w are swapped for landmarks because for images,
        # x and y axes are axis 1 and 0 respectively
        landmarks = landmarks * [new_w / w, new_h / h]

        return {'image': img, 'landmarks': landmarks}


class RandomCrop(object):
    """Crop randomly the image in a sample.

    Args:
        output_size (tuple or int): Desired output size. If int, square crop
            is made.
    """

    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        if isinstance(output_size, int):
            self.output_size = (output_size, output_size)
        else:
            assert len(output_size) == 2
            self.output_size = output_size

    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        h, w = image.shape[:2]
        new_h, new_w = self.output_size

        top = np.random.randint(0, h - new_h)
        left = np.random.randint(0, w - new_w)

        image = image[top: top + new_h,
                      left: left + new_w]

        landmarks = landmarks - [left, top]

        return {'image': image, 'landmarks': landmarks}


class ToTensor(object):
    """Convert ndarrays in sample to Tensors."""

    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']

        # swap color axis because
        # numpy image: H x W x C
        # torch image: C X H X W
        image = image.transpose((2, 0, 1))
        return {'image': torch.from_numpy(image),
                'landmarks': torch.from_numpy(landmarks)}


    

In [ ]:

    

scale = Rescale(256)
crop = RandomCrop(128)
composed = transforms.Compose([Rescale(256),
                               RandomCrop(224)])

# Apply each of the above transforms on sample.
fig = plt.figure()
sample = face_dataset[65]
for i, tsfrm in enumerate([scale, crop, composed]):
    transformed_sample = tsfrm(sample)

    ax = plt.subplot(1, 3, i + 1)
    plt.tight_layout()
    ax.set_title(type(tsfrm).__name__)
    show_landmarks(**transformed_sample)

plt.show()


    

In [ ]:

    

transformed_dataset = FaceLandmarksDataset(csv_file='faces/face_landmarks.csv',
                                           root_dir='faces/',
                                           transform=transforms.Compose([
                                               Rescale(256),
                                               RandomCrop(224),
                                               ToTensor()
                                           ]))

for i in range(len(transformed_dataset)):
    sample = transformed_dataset[i]

    print(i, sample['image'].size(), sample['landmarks'].size())

    if i == 3:
        break


    

In [ ]:

    

dataloader = DataLoader(transformed_dataset, batch_size=4,
                        shuffle=True, num_workers=4)


# Helper function to show a batch
def show_landmarks_batch(sample_batched):
    """Show image with landmarks for a batch of samples."""
    images_batch, landmarks_batch = \
            sample_batched['image'], sample_batched['landmarks']
    batch_size = len(images_batch)
    im_size = images_batch.size(2)

    grid = utils.make_grid(images_batch)
    plt.imshow(grid.numpy().transpose((1, 2, 0)))

    for i in range(batch_size):
        plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size,
                    landmarks_batch[i, :, 1].numpy(),
                    s=10, marker='.', c='r')

        plt.title('Batch from dataloader')

for i_batch, sample_batched in enumerate(dataloader):
    print(i_batch, sample_batched['image'].size(),
          sample_batched['landmarks'].size())

    # observe 4th batch and stop.
    if i_batch == 3:
        plt.figure()
        show_landmarks_batch(sample_batched)
        plt.axis('off')
        plt.ioff()
        plt.show()
        break


    

In [ ]:

    

import torch
import torch.autograd as autograd
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

torch.manual_seed(1)


    

In [ ]:

    

# Create a torch.Tensor object with the given data.  It is a 1D vector
V_data = [1., 2., 3.]
V = torch.Tensor(V_data)
print(V)

# Creates a matrix
M_data = [[1., 2., 3.], [4., 5., 6]]
M = torch.Tensor(M_data)
print(M)

# Create a 3D tensor of size 2x2x2.
T_data = [[[1., 2.], [3., 4.]],
          [[5., 6.], [7., 8.]]]
T = torch.Tensor(T_data)
print(T)


    

In [ ]:

    

# Index into V and get a scalar
print(V[0])

# Index into M and get a vector
print(M[0])

# Index into T and get a matrix
print(T[0])


    

In [ ]:

    

# Variables wrap tensor objects
x = autograd.Variable(torch.Tensor([1., 2., 3]), requires_grad=True)
# You can access the data with the .data attribute
print(x.data)

# You can also do all the same operations you did with tensors with Variables.
y = autograd.Variable(torch.Tensor([4., 5., 6]), requires_grad=True)
z = x + y
print(z.data)

# BUT z knows something extra.
print(z.grad_fn)


    

In [ ]:

    

z.grad_fn


    

In [ ]:

    

# Lets sum up all the entries in z
s = z.sum()
print(s)
print(s.grad_fn)


    

In [ ]:

    

# calling .backward() on any variable will run backprop, starting from it.
s.backward()
print(x.grad)


    

In [ ]:

    

x = torch.randn((2, 2))
y = torch.randn((2, 2))
z = x + y  # These are Tensor types, and backprop would not be possible

var_x = autograd.Variable(x)
var_y = autograd.Variable(y)
# var_z contains enough information to compute gradients, as we saw above
var_z = var_x + var_y
print(var_z.grad_fn)
print(var_z.data)

var_z_data = var_z.data  # Get the wrapped Tensor object out of var_z...
# Re-wrap the tensor in a new variable
new_var_z = autograd.Variable(var_z_data)

# ... does new_var_z have information to backprop to x and y?
# NO!
print(new_var_z.grad_fn)
# And how could it?  We yanked the tensor out of var_z (that is
# what var_z.data is).  This tensor doesn't know anything about
# how it was computed.  We pass it into new_var_z, and this is all the
# information new_var_z gets.  If var_z_data doesn't know how it was
# computed, theres no way new_var_z will.
# In essence, we have broken the variable away from its past history


    

In [ ]:

    

var_z_data


    

In [ ]:

    

import torch
import torch.autograd as autograd
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

torch.manual_seed(1)


    

In [ ]:

    

lin = nn.Linear(5, 3)  # maps from R^5 to R^3, parameters A, b
# data is 2x5.  A maps from 5 to 3... can we map "data" under A?
data = autograd.Variable(torch.randn(2, 5))
print(lin(data))  # yes


    

In [ ]:

    

# In pytorch, most non-linearities are in torch.functional (we have it imported as F)
# Note that non-linearites typically don't have parameters like affine maps do.
# That is, they don't have weights that are updated during training.
data = autograd.Variable(torch.randn(2, 2))
print(data)
print(F.relu(data))


    

In [ ]:

    

# Softmax is also in torch.functional
data = autograd.Variable(torch.randn(5))
print(data)
print(F.softmax(data))
print(F.softmax(data).sum())  # Sums to 1 because it is a distribution!
print(F.log_softmax(data))  # theres also log_softmax


    

In [ ]:

    

data = [("me gusta comer en la cafeteria".split(), "SPANISH"),
        ("Give it to me".split(), "ENGLISH"),
        ("No creo que sea una buena idea".split(), "SPANISH"),
        ("No it is not a good idea to get lost at sea".split(), "ENGLISH")]

test_data = [("Yo creo que si".split(), "SPANISH"),
             ("it is lost on me".split(), "ENGLISH")]

# word_to_ix maps each word in the vocab to a unique integer, which will be its
# index into the Bag of words vector
word_to_ix = {}
for sent, _ in data + test_data:
    for word in sent:
        if word not in word_to_ix:
            word_to_ix[word] = len(word_to_ix)
print(word_to_ix)

VOCAB_SIZE = len(word_to_ix)
NUM_LABELS = 2


class BoWClassifier(nn.Module):  # inheriting from nn.Module!

    def __init__(self, num_labels, vocab_size):
        # calls the init function of nn.Module.  Dont get confused by syntax,
        # just always do it in an nn.Module
        super(BoWClassifier, self).__init__()

        # Define the parameters that you will need.  In this case, we need A and b,
        # the parameters of the affine mapping.
        # Torch defines nn.Linear(), which provides the affine map.
        # Make sure you understand why the input dimension is vocab_size
        # and the output is num_labels!
        self.linear = nn.Linear(vocab_size, num_labels)

        # NOTE! The non-linearity log softmax does not have parameters! So we don't need
        # to worry about that here

    def forward(self, bow_vec):
        # Pass the input through the linear layer,
        # then pass that through log_softmax.
        # Many non-linearities and other functions are in torch.nn.functional
        return F.log_softmax(self.linear(bow_vec))


def make_bow_vector(sentence, word_to_ix):
    vec = torch.zeros(len(word_to_ix))
    for word in sentence:
        vec[word_to_ix[word]] += 1
    return vec.view(1, -1)


def make_target(label, label_to_ix):
    return torch.LongTensor([label_to_ix[label]])


model = BoWClassifier(NUM_LABELS, VOCAB_SIZE)

# the model knows its parameters.  The first output below is A, the second is b.
# Whenever you assign a component to a class variable in the __init__ function
# of a module, which was done with the line
# self.linear = nn.Linear(...)
# Then through some Python magic from the Pytorch devs, your module
# (in this case, BoWClassifier) will store knowledge of the nn.Linear's parameters
for param in model.parameters():
    print(param)

# To run the model, pass in a BoW vector, but wrapped in an autograd.Variable
sample = data[0]
bow_vector = make_bow_vector(sample[0], word_to_ix)
log_probs = model(autograd.Variable(bow_vector))
print(log_probs)


    

In [ ]:

    

label_to_ix = {"SPANISH": 0, "ENGLISH": 1}


    

In [ ]:

    

# Run on test data before we train, just to see a before-and-after
for instance, label in test_data:
    bow_vec = autograd.Variable(make_bow_vector(instance, word_to_ix))
    log_probs = model(bow_vec)
    print(log_probs)

# Print the matrix column corresponding to "creo"
print(next(model.parameters())[:, word_to_ix["creo"]])

loss_function = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Usually you want to pass over the training data several times.
# 100 is much bigger than on a real data set, but real datasets have more than
# two instances.  Usually, somewhere between 5 and 30 epochs is reasonable.
for epoch in range(100):
    for instance, label in data:
        # Step 1. Remember that Pytorch accumulates gradients.
        # We need to clear them out before each instance
        model.zero_grad()

        # Step 2. Make our BOW vector and also we must wrap the target in a
        # Variable as an integer. For example, if the target is SPANISH, then
        # we wrap the integer 0. The loss function then knows that the 0th
        # element of the log probabilities is the log probability
        # corresponding to SPANISH
        bow_vec = autograd.Variable(make_bow_vector(instance, word_to_ix))
        target = autograd.Variable(make_target(label, label_to_ix))

        # Step 3. Run our forward pass.
        log_probs = model(bow_vec)

        # Step 4. Compute the loss, gradients, and update the parameters by
        # calling optimizer.step()
        loss = loss_function(log_probs, target)
        loss.backward()
        optimizer.step()

for instance, label in test_data:
    bow_vec = autograd.Variable(make_bow_vector(instance, word_to_ix))
    log_probs = model(bow_vec)
    print(log_probs)

# Index corresponding to Spanish goes up, English goes down!
print(next(model.parameters())[:, word_to_ix["creo"]])


    

In [ ]:

    

import torch
import torch.autograd as autograd
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

torch.manual_seed(1)


    

In [ ]:

    

word_to_ix = {"hello": 0, "world": 1}
embeds = nn.Embedding(2, 5)  # 2 words in vocab, 5 dimensional embeddings
lookup_tensor = torch.LongTensor([word_to_ix["hello"]])
hello_embed = embeds(autograd.Variable(lookup_tensor))
print(hello_embed)


    

In [ ]:

    

CONTEXT_SIZE = 2
EMBEDDING_DIM = 10
# We will use Shakespeare Sonnet 2
test_sentence = """When forty winters shall besiege thy brow,
And dig deep trenches in thy beauty's field,
Thy youth's proud livery so gazed on now,
Will be a totter'd weed of small worth held:
Then being asked, where all thy beauty lies,
Where all the treasure of thy lusty days;
To say, within thine own deep sunken eyes,
Were an all-eating shame, and thriftless praise.
How much more praise deserv'd thy beauty's use,
If thou couldst answer 'This fair child of mine
Shall sum my count, and make my old excuse,'
Proving his beauty by succession thine!
This were to be new made when thou art old,
And see thy blood warm when thou feel'st it cold.""".split()
# we should tokenize the input, but we will ignore that for now
# build a list of tuples.  Each tuple is ([ word_i-2, word_i-1 ], target word)
trigrams = [([test_sentence[i], test_sentence[i + 1]], test_sentence[i + 2])
            for i in range(len(test_sentence) - 2)]
# print the first 3, just so you can see what they look like
print(trigrams[:3])

vocab = set(test_sentence)
word_to_ix = {word: i for i, word in enumerate(vocab)}


class NGramLanguageModeler(nn.Module):

    def __init__(self, vocab_size, embedding_dim, context_size):
        super(NGramLanguageModeler, self).__init__()
        self.embeddings = nn.Embedding(vocab_size, embedding_dim)
        self.linear1 = nn.Linear(context_size * embedding_dim, 128)
        self.linear2 = nn.Linear(128, vocab_size)

    def forward(self, inputs):
        embeds = self.embeddings(inputs).view((1, -1))
        out = F.relu(self.linear1(embeds))
        out = self.linear2(out)
        log_probs = F.log_softmax(out)
        return log_probs


losses = []
loss_function = nn.NLLLoss()
model = NGramLanguageModeler(len(vocab), EMBEDDING_DIM, CONTEXT_SIZE)
optimizer = optim.SGD(model.parameters(), lr=0.001)

for epoch in range(10):
    total_loss = torch.Tensor([0])
    for context, target in trigrams:

        # Step 1. Prepare the inputs to be passed to the model (i.e, turn the words
        # into integer indices and wrap them in variables)
        context_idxs = [word_to_ix[w] for w in context]
        context_var = autograd.Variable(torch.LongTensor(context_idxs))

        # Step 2. Recall that torch *accumulates* gradients. Before passing in a
        # new instance, you need to zero out the gradients from the old
        # instance
        model.zero_grad()

        # Step 3. Run the forward pass, getting log probabilities over next
        # words
        log_probs = model(context_var)

        # Step 4. Compute your loss function. (Again, Torch wants the target
        # word wrapped in a variable)
        loss = loss_function(log_probs, autograd.Variable(
            torch.LongTensor([word_to_ix[target]])))

        # Step 5. Do the backward pass and update the gradient
        loss.backward()
        optimizer.step()

        total_loss += loss.data
    losses.append(total_loss)
print(losses)  # The loss decreased every iteration over the training data!