View file src/colab/mnistds_pretenders.py - Download
# -*- coding: utf-8 -*-
"""mnistds_pretenders.ipynb
Automatically generated by Colab.
Original file is located at
https://colab.research.google.com/drive/1DSTRSA4LUtGaXz8cVqOpKyICLis1sCRp
"""
!python --version
!for p in torch numpy; do pip list | grep "^$p[ \t]"; done
"""Python 3.10.12
torch 2.5.1+cu121
numpy 1.26.4
"""
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
import numpy
# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using {device} device")
print("Loading labels ...")
# from labels import labels
# labels = torch.Tensor(labels)
# labels = labels.to(torch.long)
# train_labels = labels[0:8000]
# test_labels = labels[8000:9000]
print("Loading images ...")
# from images import images
# train_images = images[0:8000]
# test_images = images[8000:9000]
# train_images = numpy.array(train_images).astype('float32') / 255
# train_images = torch.Tensor(train_images)
# test_images = [test_images]
# test_images = numpy.array(test_images).astype('float32') / 255
# test_images = torch.Tensor(test_images)
# training_data = TensorDataset(torch.tensor(train_images,dtype=torch.float32), torch.tensor(train_labels,dtype=torch.long))
# test_data = TensorDataset(torch.tensor(test_images,dtype=torch.float32), torch.tensor(test_labels,dtype=torch.long))
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
# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using {device} device")
# Define model
class NeuralNetwork(nn.Module):
def __init__(self):
super().__init__()
self.flatten = nn.Flatten()
self.linear_relu_stack = nn.Sequential(
nn.Linear(28*28, 512),
nn.ReLU(),
nn.Linear(512, 512),
nn.ReLU(),
nn.Linear(512, 10)
)
def forward(self, x):
x = self.flatten(x)
logits = self.linear_relu_stack(x)
return logits
model1 = NeuralNetwork().to(device)
print(model1)
model2 = NeuralNetwork().to(device)
loss_fn = nn.CrossEntropyLoss()
optimizer1 = torch.optim.SGD(model1.parameters(), lr=1e-3)
optimizer2 = torch.optim.SGD(model2.parameters(), lr=1e-3)
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset)
model.train()
for batch, (X, y) in enumerate(dataloader):
X, y = X.to(device), y.to(device)
# Compute prediction error
pred = model(X)
loss = loss_fn(pred, y)
# Backpropagation
optimizer.zero_grad()
loss.backward()
optimizer.step()
if batch % 100 == 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)
pred = model(X)
test_loss += loss_fn(pred, y).item()
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")
return correct
import time
t1 = time.perf_counter()
epochs = 10
for t in range(epochs):
print(f"Epoch {t+1}\n-------------------------------")
print("Model 1")
train(train_dataloader, model1, loss_fn, optimizer1)
correct1 = test(test_dataloader, model1, loss_fn)
print(f"correct = {correct1}")
print("Model 2")
train(train_dataloader, model2, loss_fn, optimizer2)
correct2 = test(test_dataloader, model2, loss_fn)
print(f"correct = {correct2}")
if correct1 >= correct2:
print("Best model is 1")
model2 = NeuralNetwork().to(device)
optimizer2 = torch.optim.SGD(model2.parameters(), lr=1e-3)
else:
print("Best model is 2")
model1 = NeuralNetwork().to(device)
optimizer1 = torch.optim.SGD(model1.parameters(), lr=1e-3)
print("Done!")
t2 = time.perf_counter()
print('time taken to run:',t2-t1)
torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")
model = NeuralNetwork()
model.load_state_dict(torch.load("model.pth"))
classes = [
"Zero ",
"One ",
"Two ",
"Three",
"Four ",
"Five ",
"Six ",
"Seven",
"Eight",
"Nine ",
]
model.eval()
ngood = 0
nbad = 0
for i in range(100):
x, y = test_data[i][0], test_data[i][1]
with torch.no_grad():
pred = model(x)
predicted, actual = classes[pred[0].argmax(0)], classes[y]
if predicted == actual:
result = "Good"
ngood = ngood + 1
else:
result = "Bad"
nbad = nbad + 1
print(f'Predicted: "{predicted}", Actual: "{actual}", Result: {result}')
print(f'{ngood} good, {nbad} bad')