In this lab, you will use a single layer neural network to classify handwritten digits from the MNIST database.
Import the following libraries:
In [ ]:
!conda install -y torchvision
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision.datasets as dsets
import torch.nn.functional as F
import matplotlib.pylab as plt
import numpy as np
Use the following helper functions for plotting the loss:
In [ ]:
def plot_accuracy_loss(training_results):
plt.subplot(2, 1, 1)
plt.plot(training_results['training_loss'],'r')
plt.ylabel('loss')
plt.title('training loss iterations')
plt.subplot(2,1,2)
plt.plot( training_results['validation_accuracy'])
plt.ylabel('accuracy')
plt.xlabel('epochs ')
plt.show()
Use the following function for printing the model parameters:
In [ ]:
def pint_model_parameters(model):
for i in range(len(list(model.parameters()))):
if (i+1)%2==0:
print("the number of bias parameters for layer",i)
else:
print("the number of parameters for layer",i+1)
print( list(model.parameters())[i].size() )
Define the neural network module or class:
In [ ]:
def show_data(data_sample):
plt.imshow(data_sample.numpy().reshape(28,28),cmap='gray')
plt.show()
Define the neural network module or class:
In [ ]:
class Net(nn.Module):
def __init__(self,D_in,H,D_out):
super(Net,self).__init__()
self.linear1=nn.Linear(D_in,H)
self.linear2=nn.Linear(H,D_out)
def forward(self,x):
x=torch.sigmoid(self.linear1(x))
x=self.linear2(x)
return x
Define a function to train the model. In this case, the function returns a Python dictionary to store the training loss and accuracy on the validation data.
In [ ]:
def train(model,criterion, train_loader,validation_loader, optimizer, epochs=100):
i=0
useful_stuff={'training_loss':[],'validation_accuracy':[]}
#n_epochs
for epoch in range(epochs):
for i,(x, y) in enumerate(train_loader):
#clear gradient
optimizer.zero_grad()
#make a prediction logits
z=model(x.view(-1,28*28))
# calculate loss
loss=criterion(z,y)
# calculate gradients of parameters
loss.backward()
# update parameters
optimizer.step()
useful_stuff['training_loss'].append(loss.data.item())
correct=0
for x, y in validation_loader:
#perform a prediction on the validation data
yhat=model(x.view(-1,28*28))
_,lable=torch.max(yhat,1)
correct+=(lable==y).sum().item()
accuracy=100*(correct/len(validation_dataset))
useful_stuff['validation_accuracy'].append(accuracy)
return useful_stuff
Load the training dataset by setting the parameters train to True and convert it to a tensor by placing a transform object in the argument transform.
In [ ]:
train_dataset=dsets.MNIST(root='./data', train=True, download=True, transform=transforms.ToTensor())
Load the testing dataset by setting the parameters train to False and convert it to a tensor by placing a transform object in the argument transform:
In [ ]:
validation_dataset=dsets.MNIST(root='./data', train=False, download=True, transform=transforms.ToTensor())
Create the criterion function:
In [ ]:
criterion=nn.CrossEntropyLoss()
Create the training-data loader and the validation-data loader objects:
In [ ]:
train_loader=torch.utils.data.DataLoader(dataset=train_dataset,batch_size=2000,shuffle=True)
validation_loader=torch.utils.data.DataLoader(dataset=validation_dataset,batch_size=5000,shuffle=False)
Create the criterion function:
In [ ]:
criterion=nn.CrossEntropyLoss()
Create the model with 100 hidden layers:
In [ ]:
input_dim=28*28
hidden_dim=100
output_dim=10
model=Net(input_dim,hidden_dim,output_dim)
Print the model parameters:
In [ ]:
pint_model_parameters(model)
Define the optimizer object with a learning rate of 0.01:
In [ ]:
learning_rate=0.01
optimizer=torch.optim.SGD(model.parameters(),lr=learning_rate)
Train the model by using 100 epochs (this process takes time):
In [ ]:
training_results=train(model,criterion, train_loader,validation_loader, optimizer, epochs=30)
Plot the training total loss or cost for every iteration and plot the training accuracy for every epoch:
In [ ]:
plot_accuracy_loss(training_results)
Plot the first five misclassified samples:
In [ ]:
count=0
for x,y in validation_dataset:
z=model(x.reshape(-1,28*28))
_,yhat=torch.max(z,1)
if yhat!=y:
show_data(x)
count+=1
if count>=5:
break
Use nn.Sequential to build exactly the same model as you just built. Use the function plot_accuracy_loss to see the metrics. Also, try different epoch numbers.
In [ ]:
Double-click here for the solution.
Joseph Santarcangelo has a PhD in Electrical Engineering. His research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition.
Other contributors: Michelle Carey ,Mavis Zhou