Pytorch and Machine Learning for the Math Impaired
Download as PPTX, PDF0 likes157 views
The document provides a tutorial on implementing deep learning using PyTorch, detailing key concepts like tensors, neural networks, and data handling. It includes code examples for training a convolutional neural network on the CIFAR-10 dataset, along with evaluation metrics. The author addresses common challenges for those less confident in their mathematical skills while learning machine learning.
![WHAT'S A TENSOR
from __future__ import print_function
import torch
x = torch.Tensor(5, 3)
print(x)
>>0.0000 0.0000 0.0001
0.0000 0.0001 0.0000
3.3717 0.0000 3.3717
0.0000 3.8859 0.0000
3.8001 0.0000 27.0173
[torch.FloatTensor of size 5x3]
print(x.size())
>>torch.Size([5, 3])](https://image.slidesharecdn.com/pytorch-180119143823/85/Pytorch-and-Machine-Learning-for-the-Math-Impaired-10-320.jpg)
![NEURAL NETWORK IN PYTORCH
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, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
input = Variable(torch.randn(1, 1, 32, 32))
out = net(input)
print(out)
>>Variable containing:
0.0490 0.0798 0.0189 -0.0231 0.0577 -0.0843 -0.0357 -0.0950 0.0220 -0.1126
[torch.FloatTensor of size 1x10]](https://image.slidesharecdn.com/pytorch-180119143823/85/Pytorch-and-Machine-Learning-for-the-Math-Impaired-12-320.jpg)
![CIFAR10 TRAINING DATA
import torch
import torchvision
import torchvision.transforms as transforms
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')](https://image.slidesharecdn.com/pytorch-180119143823/85/Pytorch-and-Machine-Learning-for-the-Math-Impaired-13-320.jpg)
![TRAINING THE NETWORK
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
for epoch in range(2): # 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), Variable(labels)
# 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')](https://image.slidesharecdn.com/pytorch-180119143823/85/Pytorch-and-Machine-Learning-for-the-Math-Impaired-14-320.jpg)
![TESTING THE NETWORK
correct = 0
total = 0
for data in testloader:
images, labels = data
outputs = net(Variable(images))
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))
>>Accuracy of the network on the 10000 test images: 53 %
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
outputs = net(Variable(images))
_, predicted = torch.max(outputs.data, 1)
c = (predicted == labels).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]))
>>Accuracy of plane : 43 %
Accuracy of car : 67 %
Accuracy of bird : 27 %
Accuracy of cat : 60 %
Accuracy of deer : 44 %
Accuracy of dog : 36 %
Accuracy of frog : 64 %
Accuracy of horse : 56 %
Accuracy of ship : 55 %](https://image.slidesharecdn.com/pytorch-180119143823/85/Pytorch-and-Machine-Learning-for-the-Math-Impaired-15-320.jpg)
Pytorch and Machine Learning for the Math Impaired
- 1. PYTORCH AND MACHINE LEARNING FOR THE MATH
- 2. WHO AM I ▸Tyrel Denison ▸Senior Developer at Field Agent ▸@tyreldenison
- 3. DEEP LEARNING, WHAT IS IT?
- 4. BUT I SUCK AT MATH!!
- 5. LOOK AT THIS NETWORK
- 6. CONVOLUTION
- 7. MAX POOLING
- 8. NETWORK FLOW
- 9. WHY PYTORCH ▸Imperative vs Symbolic ▸Dynamic vs Static Computation Graph ▸GPU Access (Cuda) ▸Pythonic ▸In and out of Numpy (Super similar apis) ▸Autograd and History
- 10. WHAT'S A TENSOR from __future__ import print_function import torch x = torch.Tensor(5, 3) print(x) >>0.0000 0.0000 0.0001 0.0000 0.0001 0.0000 3.3717 0.0000 3.3717 0.0000 3.8859 0.0000 3.8001 0.0000 27.0173 [torch.FloatTensor of size 5x3] print(x.size()) >>torch.Size([5, 3])
- 11. MEDIA TO DATA ▸Pillow and OpenCV for images ▸scipy and librosa for audio ▸Python and Cython for text
- 12. NEURAL NETWORK IN PYTORCH 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, 6, 5) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(6, 16, 5) self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = x.view(-1, 16 * 5 * 5) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x net = Net() input = Variable(torch.randn(1, 1, 32, 32)) out = net(input) print(out) >>Variable containing: 0.0490 0.0798 0.0189 -0.0231 0.0577 -0.0843 -0.0357 -0.0950 0.0220 -0.1126 [torch.FloatTensor of size 1x10]
- 13. CIFAR10 TRAINING DATA import torch import torchvision import torchvision.transforms as transforms 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')
- 14. TRAINING THE NETWORK import torch.optim as optim criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) for epoch in range(2): # 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), Variable(labels) # 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')
- 15. TESTING THE NETWORK correct = 0 total = 0 for data in testloader: images, labels = data outputs = net(Variable(images)) _, predicted = torch.max(outputs.data, 1) total += labels.size(0) correct += (predicted == labels).sum() print('Accuracy of the network on the 10000 test images: %d %%' % ( 100 * correct / total)) >>Accuracy of the network on the 10000 test images: 53 % 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 outputs = net(Variable(images)) _, predicted = torch.max(outputs.data, 1) c = (predicted == labels).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])) >>Accuracy of plane : 43 % Accuracy of car : 67 % Accuracy of bird : 27 % Accuracy of cat : 60 % Accuracy of deer : 44 % Accuracy of dog : 36 % Accuracy of frog : 64 % Accuracy of horse : 56 % Accuracy of ship : 55 %