Learn data science and machine learning by building real-world projects on Jovian
Join the Zero to Data Science Bootcamp by Jovian. 20 weeks part-time, 7 courses, 12 assignments, 4 projects, and 6 months of career support.

Classifying images from Fashion MNIST using feedforward neural networks

Dataset source: https://github.com/zalandoresearch/fashion-mnist Detailed tutorial: https://jovian.ml/aakashns/04-feedforward-nn

# Uncomment and run the commands below if imports fail
# !conda install numpy pandas pytorch torchvision cpuonly -c pytorch -y
# !pip install matplotlib --upgrade --quiet
import torch
import torchvision
import numpy as np
import matplotlib.pyplot as plt
import torch.nn as nn
import torch.nn.functional as F
from torchvision.datasets import FashionMNIST
from torchvision.transforms import ToTensor
from torchvision.utils import make_grid
from torch.utils.data.dataloader import DataLoader
from torch.utils.data import random_split
%matplotlib inline

Preparing the Data

dataset = FashionMNIST(root='data/', download=True, transform=ToTensor())
test_dataset = FashionMNIST(root='data/', train=False, transform=ToTensor())
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to data/FashionMNIST/raw/train-images-idx3-ubyte.gz
HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))
Extracting data/FashionMNIST/raw/train-images-idx3-ubyte.gz to data/FashionMNIST/raw Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw/train-labels-idx1-ubyte.gz
HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))
Extracting data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))
Extracting data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))
Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw Processing... Done!
/opt/conda/conda-bld/pytorch_1587428398394/work/torch/csrc/utils/tensor_numpy.cpp:141: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program.
val_size = 10000
train_size = len(dataset) - val_size
train_ds, val_ds = random_split(dataset, [train_size, val_size])
len(train_ds), len(val_ds)
(50000, 10000)
train_loader = DataLoader(train_ds, batch_size, shuffle=True, num_workers=4, pin_memory=True)
val_loader = DataLoader(val_ds, batch_size*2, num_workers=4, pin_memory=True)
test_loader = DataLoader(test_dataset, batch_size*2, num_workers=4, pin_memory=True)
for images, _ in train_loader:
    print('images.shape:', images.shape)
    plt.imshow(make_grid(images, nrow=16).permute((1, 2, 0)))
images.shape: torch.Size([128, 1, 28, 28])
Notebook Image


def accuracy(outputs, labels):
    _, preds = torch.max(outputs, dim=1)
    return torch.tensor(torch.sum(preds == labels).item() / len(preds))
class MnistModel(nn.Module):
    """Feedfoward neural network with 1 hidden layer"""
    def __init__(self, in_size, out_size):
        # hidden layer
        self.linear1 = nn.Linear(in_size, 16)
        # hidden layer 2
        self.linear2 = nn.Linear(16, 32)
        # output layer
        self.linear3 = nn.Linear(32, out_size)
    def forward(self, xb):
        # Flatten the image tensors
        out = xb.view(xb.size(0), -1)
        # Get intermediate outputs using hidden layer 1
        out = self.linear1(out)
        # Apply activation function
        out = F.relu(out)
        # Get intermediate outputs using hidden layer 2
        out = self.linear2(out)
        # Apply activation function
        out = F.relu(out)
        # Get predictions using output layer
        out = self.linear3(out)
        return out
    def training_step(self, batch):
        images, labels = batch 
        out = self(images)                  # Generate predictions
        loss = F.cross_entropy(out, labels) # Calculate loss
        return loss
    def validation_step(self, batch):
        images, labels = batch 
        out = self(images)                    # Generate predictions
        loss = F.cross_entropy(out, labels)   # Calculate loss
        acc = accuracy(out, labels)           # Calculate accuracy
        return {'val_loss': loss, 'val_acc': acc}
    def validation_epoch_end(self, outputs):
        batch_losses = [x['val_loss'] for x in outputs]
        epoch_loss = torch.stack(batch_losses).mean()   # Combine losses
        batch_accs = [x['val_acc'] for x in outputs]
        epoch_acc = torch.stack(batch_accs).mean()      # Combine accuracies
        return {'val_loss': epoch_loss.item(), 'val_acc': epoch_acc.item()}
    def epoch_end(self, epoch, result):
        print("Epoch [{}], val_loss: {:.4f}, val_acc: {:.4f}".format(epoch, result['val_loss'], result['val_acc']))

Using a GPU

def get_default_device():
    """Pick GPU if available, else CPU"""
    if torch.cuda.is_available():
        return torch.device('cuda')
        return torch.device('cpu')
device = get_default_device()
def to_device(data, device):
    """Move tensor(s) to chosen device"""
    if isinstance(data, (list,tuple)):
        return [to_device(x, device) for x in data]
    return data.to(device, non_blocking=True)
class DeviceDataLoader():
    """Wrap a dataloader to move data to a device"""
    def __init__(self, dl, device):
        self.dl = dl
        self.device = device
    def __iter__(self):
        """Yield a batch of data after moving it to device"""
        for b in self.dl: 
            yield to_device(b, self.device)

    def __len__(self):
        """Number of batches"""
        return len(self.dl)
train_loader = DeviceDataLoader(train_loader, device)
val_loader = DeviceDataLoader(val_loader, device)
test_loader = DeviceDataLoader(test_loader, device)

Training the model

def evaluate(model, val_loader):
    outputs = [model.validation_step(batch) for batch in val_loader]
    return model.validation_epoch_end(outputs)

def fit(epochs, lr, model, train_loader, val_loader, opt_func=torch.optim.SGD):
    history = []
    optimizer = opt_func(model.parameters(), lr)
    for epoch in range(epochs):
        # Training Phase 
        for batch in train_loader:
            loss = model.training_step(batch)
        # Validation phase
        result = evaluate(model, val_loader)
        model.epoch_end(epoch, result)
    return history
input_size = 784
num_classes = 10
model = MnistModel(input_size, out_size=num_classes)
to_device(model, device)
  (linear1): Linear(in_features=784, out_features=16, bias=True)
  (linear2): Linear(in_features=16, out_features=32, bias=True)
  (linear3): Linear(in_features=32, out_features=10, bias=True)
history = [evaluate(model, val_loader)]
[{'val_loss': 2.304597854614258, 'val_acc': 0.10898437350988388}]
history += fit(5, 0.5, model, train_loader, val_loader)
Epoch [0], val_loss: 0.8635, val_acc: 0.6880 Epoch [1], val_loss: 0.5844, val_acc: 0.7808 Epoch [2], val_loss: 0.5300, val_acc: 0.8067 Epoch [3], val_loss: 0.5175, val_acc: 0.8035 Epoch [4], val_loss: 0.5453, val_acc: 0.7750
history += fit(5, 0.1, model, train_loader, val_loader)
Epoch [0], val_loss: 0.4513, val_acc: 0.8349 Epoch [1], val_loss: 0.4393, val_acc: 0.8380 Epoch [2], val_loss: 0.4361, val_acc: 0.8407 Epoch [3], val_loss: 0.4337, val_acc: 0.8404 Epoch [4], val_loss: 0.4299, val_acc: 0.8428
losses = [x['val_loss'] for x in history]
plt.plot(losses, '-x')
plt.title('Loss vs. No. of epochs');
Notebook Image
accuracies = [x['val_acc'] for x in history]
plt.plot(accuracies, '-x')
plt.title('Accuracy vs. No. of epochs');
Notebook Image

Prediction on Samples

def predict_image(img, model):
    xb = to_device(img.unsqueeze(0), device)
    yb = model(xb)
    _, preds  = torch.max(yb, dim=1)
    return preds[0].item()
img, label = test_dataset[0]
plt.imshow(img[0], cmap='gray')
print('Label:', dataset.classes[label], ', Predicted:', dataset.classes[predict_image(img, model)])
Label: Ankle boot , Predicted: Ankle boot
Notebook Image
evaluate(model, test_loader)
{'val_loss': 0.44173064827919006, 'val_acc': 0.838574230670929}

Save and upload

torch.save(model.state_dict(), saved_weights_fname)
!pip install jovian --upgrade --quiet
WARNING: You are using pip version 20.1; however, version 20.1.1 is available. You should consider upgrading via the '/opt/conda/bin/python3.7 -m pip install --upgrade pip' command.
import jovian
jovian.commit(project=project_name, environment=None, outputs=[saved_weights_fname])
[jovian] Attempting to save notebook..