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')