Part3 - Training Neural Networks.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Apr  9 15:49:28 2020

@author: lachaji
"""

import torch
from torch import nn
import torch.nn.functional as F
from torchvision import datasets, transforms

# Define a transform to normalize the data
transform = transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.5,), (0.5,)),
                              ])
# Download and load the training data
trainset = datasets.MNIST('~/.pytorch/MNIST_data/', download=True, train=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)

# Build a feed-forward network
model = nn.Sequential(nn.Linear(784, 128),
                      nn.ReLU(),
                      nn.Linear(128, 64),
                      nn.ReLU(),
                      nn.Linear(64, 10))

# Define the loss
criterion = nn.CrossEntropyLoss()

# Get our data
images, labels = next(iter(trainloader))
# Flatten images
images = images.view(images.shape[0], -1)

# Forward pass, get our logits
logits = model(images)
# Calculate the loss with the logits and the labels
loss = criterion(logits, labels)

print(loss)


# TODO: Build a feed-forward network
model = nn.Sequential(nn.Linear(784, 128),
                      nn.ReLU(),
                      nn.Linear(128, 64),
                      nn.ReLU(),
                      nn.Linear(64, 10),
                      nn.LogSoftmax(dim=1))

# TODO: Define the loss
criterion = nn.NLLLoss()

### Run this to check your work
# Get our data
images, labels = next(iter(trainloader))
# Flatten images
images = images.view(images.shape[0], -1)

# Forward pass, get our logits
logits = model(images)
# Calculate the loss with the logits and the labels
loss = criterion(logits, labels)

print(loss)


#EX AutoGrad
x = torch.zeros(1, requires_grad=True)
y = x * 2
with torch.no_grad():
    z = x * 2
z.requires_grad

x = torch.randn(2,2, requires_grad=True)
y = x**2
print(y.grad_fn)
z = y.mean()

print(x.grad)
z.backward()
print(x.grad)
print(x/2)



# Build a feed-forward network
model = nn.Sequential(nn.Linear(784, 128),
                      nn.ReLU(),
                      nn.Linear(128, 64),
                      nn.ReLU(),
                      nn.Linear(64, 10),
                      nn.LogSoftmax(dim=1))

criterion = nn.NLLLoss()
images, labels = next(iter(trainloader))
images = images.view(images.shape[0], -1)

logps = model(images)
loss = criterion(logps, labels)

from torch import optim

# Optimizers require the parameters to optimize and a learning rate
optimizer = optim.SGD(model.parameters(), lr=0.01)

print('Initial weights - ', model[0].weight)

images, labels = next(iter(trainloader))
images.resize_(64, 784)

# Clear the gradients, do this because gradients are accumulated
optimizer.zero_grad()

# Forward pass, then backward pass, then update weights
output = model(images)
loss = criterion(output, labels)
loss.backward()
print('Gradient -', model[0].weight.grad)

# Take an update step and few the new weights
optimizer.step()
print('Updated weights - ', model[0].weight)



######
model = nn.Sequential(nn.Linear(784, 128),
                      nn.ReLU(),
                      nn.Linear(128, 64),
                      nn.ReLU(),
                      nn.Linear(64, 10),
                      nn.LogSoftmax(dim=1))

criterion = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.003)

epochs = 5
for e in range(epochs):
    running_loss = 0
    for images, labels in trainloader:
        # Flatten MNIST images into a 784 long vector
        images = images.view(images.shape[0], -1)
    
        # TODO: Training pass
        optimizer.zero_grad()
        
        output = model(images)
        loss = criterion(output, labels)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item()
    else:
        print(f"Training loss: {running_loss/len(trainloader)}")
        
        
import helper

images, labels = next(iter(trainloader))

img = images[1].view(1, 784)
# Turn off gradients to speed up this part
with torch.no_grad():
    logps = model(img)

# Output of the network are log-probabilities, need to take exponential for probabilities
ps = torch.exp(logps)
helper.view_classify(img.view(1, 28, 28), ps)