PyTorch
From Kaggle: "MNIST ("Modified National Institute of Standards and Technology") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike."
This code is adopted from the pytorch examples repository. It is licensed under BSD 3-Clause "New" or "Revised" License. Source: https://github.com/pytorch/examples/ LICENSE: https://github.com/pytorch/examples/blob/master/LICENSE
Table from Wikipedia
!pip install torch torchvision
#Import Libraries
from future import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable
args={}
kwargs={}
args['batch_size']=1000
args['test_batch_size']=1000
args['epochs']=10 #The number of Epochs is the number of times you go through the full dataset.
args['lr']=0.01 #Learning rate is how fast it will decend.
args['momentum']=0.5 #SGD momentum (default: 0.5) Momentum is a moving average of our gradients (helps to keep direction).
args['seed']=1 #random seed
args['log_interval']=10
args['cuda']=False
#load the data
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args['batch_size'], shuffle=True, kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args['test_batch_size'], shuffle=True, kwargs)
class Net(nn.Module):
#This defines the structure of the NN.
def init(self):
super(Net, self).init()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d() #Dropout
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="c1">#Convolutional Layer/Pooling Layer/Activation</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">max_pool2d</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv1</span><span class="p">(</span><span class="n">x</span><span class="p">),</span> <span class="mi">2</span><span class="p">))</span>
<span class="c1">#Convolutional Layer/Dropout/Pooling Layer/Activation</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">max_pool2d</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv2_drop</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv2</span><span class="p">(</span><span class="n">x</span><span class="p">)),</span> <span class="mi">2</span><span class="p">))</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">320</span><span class="p">)</span>
<span class="c1">#Fully Connected Layer/Activation</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fc1</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">dropout</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">training</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">training</span><span class="p">)</span>
<span class="c1">#Fully Connected Layer/Activation</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="c1">#Softmax gets probabilities. </span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">log_softmax</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
def train(epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
if args['cuda']:
data, target = data.cuda(), target.cuda()
#Variables in Pytorch are differenciable.
data, target = Variable(data), Variable(target)
#This will zero out the gradients for this batch.
optimizer.zero_grad()
output = model(data)
# Calculate the loss The negative log likelihood loss. It is useful to train a classification problem with C classes.
loss = F.nll_loss(output, target)
#dloss/dx for every Variable
loss.backward()
#to do a one-step update on our parameter.
optimizer.step()
#Print out the loss periodically.
if batch_idx % args['log_interval'] == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx len(data), len(train_loader.dataset),
100. batch_idx / len(train_loader), loss.data[0]))
def test():
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
if args['cuda']:
data, target = data.cuda(), target.cuda()
data, target = Variable(data, volatile=True), Variable(target)
output = model(data)
test_loss += F.nll_loss(output, target, size_average=False).data[0] # sum up batch loss
pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
correct += pred.eq(target.data.view_as(pred)).long().cpu().sum()
<span class="n">test_loss</span> <span class="o">/=</span> <span class="nb">len</span><span class="p">(</span><span class="n">test_loader</span><span class="o">.</span><span class="n">dataset</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">'</span><span class="se">\n</span><span class="s1">Test set: Average loss: </span><span class="si">{:.4f}</span><span class="s1">, Accuracy: </span><span class="si">{}</span><span class="s1">/</span><span class="si">{}</span><span class="s1"> (</span><span class="si">{:.0f}</span><span class="s1">%)</span><span class="se">\n</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">test_loss</span><span class="p">,</span> <span class="n">correct</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">test_loader</span><span class="o">.</span><span class="n">dataset</span><span class="p">),</span>
<span class="mf">100.</span> <span class="o">*</span> <span class="n">correct</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">test_loader</span><span class="o">.</span><span class="n">dataset</span><span class="p">)))</span>
model = Net()
if args['cuda']:
model.cuda()
optimizer = optim.SGD(model.parameters(), lr=args['lr'], momentum=args['momentum'])
for epoch in range(1, args['epochs'] + 1):
train(epoch)
test()
