View file src/colab/constant_input.py - Download
# -*- coding: utf-8 -*-
"""constant_input.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/14zCs-jhEipeKOxRTl7nfPDHzLve6gi-H
"""
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from torchvision.transforms import ToTensor
from torch.utils.data import TensorDataset
# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using {device} device")
torch.manual_seed(14)
transform = transforms.ToTensor()
training_data = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_data = datasets.MNIST(root='./data', train=False, download=True, transform=transform)
batch_size = 50
# Create data loaders.
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)
for X, y in test_dataloader:
print(f"Shape of X [N, C, H, W]: {X.shape}")
print(f"Shape of y: {y.shape} {y.dtype}")
break
"""Functions to train and test a model"""
loss_fn = torch.nn.CrossEntropyLoss()
def train(dataloader, model, loss_fn):
size = len(dataloader.dataset)
model.train()
for batch, (X, y) in enumerate(dataloader):
X, y = X.to(device), y.to(device)
X = torch.flatten(X, 1, 3) # transform X of shape 50, 1, 28, 28 into 50, 28*28
# Compute prediction error
pred = model(X)
# Compute loss
loss = loss_fn(pred, y)
# Backpropagation
model.zero_grad()
loss.backward()
# Optimize parameters
model.optimize()
if batch % 200 == 0:
loss, current = loss.item(), batch * len(X)
print(f"loss: {loss:>7f} [{current:>5d}/{size:>5d}]")
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset)
num_batches = len(dataloader)
model.eval()
test_loss, correct = 0, 0
with torch.no_grad():
for X, y in dataloader:
X, y = X.to(device), y.to(device)
X = torch.flatten(X, 1, 3) # transform X of shape 50, 1, 28, 28 into 50, 28*28
pred = model(X)
test_loss += loss_fn(pred, y)
correct += (pred.argmax(1) == y).type(torch.float32).sum().item()
test_loss /= num_batches
correct /= size
print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")
"""In the first model, there are weights W and biases B, and Y = sigmoid(X W + B)"""
# Define model
def sigmoid(x): return 1/(1+torch.exp(-x))
class NeuralNetwork1(nn.Module):
def __init__(self):
super().__init__()
self.lr = 10
self.W1 = torch.randn((784, 256), requires_grad=True, device=device)
self.B1 = torch.randn(256, requires_grad=True, device=device)
self.W2 = torch.randn((256, 256), requires_grad=True, device=device)
self.B2 = torch.randn(256, requires_grad=True, device=device)
self.W3 = torch.randn((256, 10), requires_grad=True, device=device)
self.B3 = torch.randn(10, requires_grad=True, device=device)
def forward(self, x):
y1 = sigmoid((x @ self.W1) + self.B1)
y2 = sigmoid((y1 @ self.W2) + self.B2)
y3 = sigmoid((y2 @ self.W3) + self.B3)
return y3
def zero_grad(self):
if self.W1.grad is not None: self.W1.grad.zero_()
if self.B1.grad is not None: self.B1.grad.zero_()
if self.W2.grad is not None: self.W2.grad.zero_()
if self.B2.grad is not None: self.B2.grad.zero_()
if self.W3.grad is not None: self.W3.grad.zero_()
if self.B3.grad is not None: self.B3.grad.zero_()
def optimize(self):
self.W1.data -= self.lr * self.W1.grad.data
self.B1.data -= self.lr * self.B1.grad.data
self.W2.data -= self.lr * self.W2.grad.data
self.B2.data -= self.lr * self.B2.grad.data
self.W3.data -= self.lr * self.W3.grad.data
self.B3.data -= self.lr * self.B3.grad.data
model1 = NeuralNetwork1().to(device)
epochs = 5
for t in range(epochs):
print(f"Epoch {t+1}\n-------------------------------")
train(train_dataloader, model1, loss_fn)
test(test_dataloader, model1, loss_fn)
print("Done!")
"""In the second model, biases are replaced with a constant input with value 1, and Y = sigmoid((1|X) W) where 1|X represents X with 1 inserted at the beginning. The first row of W replaces the biases B.
"""
# Define model
def sigmoid(x): return 1/(1+torch.exp(-x))
def input_with_ones(x):
n = x.shape[0] # batch size
u = torch.ones(n)[:, None].to(device)
x1 = torch.cat([u, x], axis=-1) # insert 1 at the beginning of each line of x
return x1
class NeuralNetwork2(nn.Module):
def __init__(self):
super().__init__()
self.lr = 1
self.W1 = torch.randn((785, 256), requires_grad=True, device=device)
self.W2 = torch.randn((257, 256), requires_grad=True, device=device)
self.W3 = torch.randn((257, 10), requires_grad=True, device=device)
def forward(self, x):
y1 = sigmoid(input_with_ones(x) @ self.W1)
y2 = sigmoid(input_with_ones(y1) @ self.W2)
y3 = sigmoid(input_with_ones(y2) @ self.W3)
return y3
def zero_grad(self):
if self.W1.grad is not None: self.W1.grad.zero_()
if self.W2.grad is not None: self.W2.grad.zero_()
if self.W3.grad is not None: self.W3.grad.zero_()
def optimize(self):
self.W1.data -= self.lr * self.W1.grad.data
self.W2.data -= self.lr * self.W2.grad.data
self.W3.data -= self.lr * self.W3.grad.data
model2 = NeuralNetwork2().to(device)
epochs = 5
for t in range(epochs):
print(f"Epoch {t+1}\n-------------------------------")
train(train_dataloader, model2, loss_fn)
test(test_dataloader, model2, loss_fn)
print("Done!")