id,label
0,0
1,4
2,4
3,2
jal x1, T_N # call T(n')=T(n//2)
slli x8, x8, 2 # 4T(n//2)
add x8, x8, x7
add x8, x8, x7
addi sp, sp, 24
lw x1, 0(sp)
lw x10, 8(sp)
lw x7, 16(sp)
jalr x0, 0(x1)
################################################################################
__start:
# Prints msg0
addi a0, x0, 4
la a1, msg0
ecall
# Prints msg1
addi a0, x0, 4
23,4
24,6
25,1
26,8
27,2
jal x1, T_N # call T(n')=T(n//2)
slli x8, x8, 2 # 4T(n//2)
add x8, x8, x7
add x8, x8, x7
addi sp, sp, 24
lw x1, 0(sp)
lw x10, 8(sp)
lw x7, 16(sp)
jalr x0, 0(x1)
################################################################################
__start:
# Prints msg0
addi a0, x0, 4
la a1, msg0
ecall
# Prints msg1
addi a0, x0, 4
46,3
47,5
48,3
49,3
50,5
51,1
52,6
53,6
54,9
55,9
56,3
57,7
58,3
59,4
60,6
jal x1, T_N # call T(n')=T(n//2)
slli x8, x8, 2 # 4T(n//2)
add x8, x8, x7
add x8, x8, x7
addi sp, sp, 24
lw x1, 0(sp)
lw x10, 8(sp)
lw x7, 16(sp)
jalr x0, 0(x1)
################################################################################
__start:
# Prints msg0
addi a0, x0, 4
la a1, msg0
ecall
# Prints msg1
addi a0, x0, 4
78,5
79,3
80,3
81,9
82,2
83,9
84,0
85,7
86,9
87,7
88,9
89,6
90,3
91,2
92,9
93,8
94,1
95,9
213202302230..153615156
123
123
02
30
.
0.
0
.
0.
jal x1, T_N # call T(n')=T(n//2)
slli x8, x8, 2 # 4T(n//2)
add x8, x8, x7
add x8, x8, x7
addi sp, sp, 24
lw x1, TRAINING A CLASSIFIER
This is it. You have seen how to define neural networks, compute loss and make
updates to the weights of the network.
Now you might be thinking,
What about data?
Generally, when you have to deal with image, text, audio or video data, you can use
standard python packages that load data into a numpy array. Then you can convert
this array into a torch.*Tensor.
For images, packages such as Pillow, OpenCV are useful
For audio, packages such as scipy and librosa
For text, either raw Python or Cython based loading, or NLTK and SpaCy are useful
Specifically for vision, we have created a package called torchvision, that has
data loaders for common datasets such as Imagenet, CIFAR10, MNIST, etc. and data
transformers for images, viz., torchvision.datasets and
torch.utils.data.DataLoader.
This provides a huge convenience and avoids writing boilerplate code.
For this tutorial, we will use the CIFAR10 dataset. It has the classes: ‘airplane’,
‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The
images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels
in size.
cifar10
cifar10
Training an image classifier
We will do the following steps in order:
Load and normalizing the CIFAR10 training and test datasets using torchvision
Define a Convolutional Neural Network
Define a loss function
Train the network on the training data
Test the network on the test data
1. Loading and normalizing CIFAR10
Using torchvision, it’s extremely easy to load CIFAR10.
import torch
import torchvision
import torchvision.transforms as transforms
The output of torchvision datasets are PILImage images of range [0, 1]. We
transform them to Tensors of normalized range [-1, 1]. .. note:
If running on Windows and you get a BrokenPipeError, try setting
the num_worker of torch.utils.data.DataLoader() to 0.
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')
Out:
Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to
./data/cifar-10-python.tar.gz
Extracting ./data/cifar-10-python.tar.gz to ./data
Files already downloaded and verified
Let us show some of the training images, for fun.
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
lw x1, 0(sp)
lw x10, 8(sp)
lw x7, 16(sp)
jalr x0, 0(x1)
################################################################################
__start:TRAINING A CLASSIFIER
This is it. You have seen how to define neural networks, compute loss and make
updates to the weights of the network.
Now you might be thinking,
What about data?
Generally, when you have to deal with image, text, audio or video data, you can use
standard python packages that load data into a numpy array. Then you can convert
this array into a torch.*Tensor.
For images, packages such as Pillow, OpenCV are useful
For audio, packages such as scipy and librosa
For text, either raw Python or Cython based loading, or NLTK and SpaCy are useful
Specifically for vision, we have created a package called torchvision, that has
data loaders for common datasets such as Imagenet, CIFAR10, MNIST, etc. and data
transformers for images, viz., torchvision.datasets and
torch.utils.data.DataLoader.
This provides a huge convenience and avoids writing boilerplate code.
For this tutorial, we will use the CIFAR10 dataset. It has the classes: ‘airplane’,
‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The
images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels
in size.
cifar10
cifar10
Training an image classifier
We will do the following steps in order:
Load and normalizing the CIFAR10 training and test datasets using torchvision
Define a Convolutional Neural Network
Define a loss function
Train the network on the training data
Test the network on the test data
1. Loading and normalizing CIFAR10
Using torchvision, it’s extremely easy to load CIFAR10.
import torch
import torchvision
import torchvision.transforms as transforms
The output of torchvision datasets are PILImage images of range [0, 1]. We
transform them to Tensors of normalized range [-1, 1]. .. note:
If running on Windows and you get a BrokenPipeError, try setting
the num_worker of torch.utils.data.DataLoader() to 0.
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')
Out:
Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to
./data/cifar-10-python.tar.gz
Extracting ./data/cifar-10-python.tar.gz to ./data
Files already downloaded and verified
Let us show some of the training images, for fun.
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
