Pytorch -- Fashion MNIST using feedforward neural networks

Classifying images from Fashion MNIST using feedforward neural networks

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 import DataLoader
from 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())
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, labels 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])


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, 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': 2.324085235595703, 'val_acc': 0.09970702975988388}]
history += fit(5, 0.5, model, train_loader, val_loader)
Epoch [0], val_loss: 1.2256, val_acc: 0.5346
Epoch [1], val_loss: 0.6470, val_acc: 0.7549
Epoch [2], val_loss: 0.5319, val_acc: 0.7907
Epoch [3], val_loss: 0.5584, val_acc: 0.7864
Epoch [4], val_loss: 0.5184, val_acc: 0.8092
history += fit(5, 0.1, model, train_loader, val_loader)
Epoch [0], val_loss: 0.4486, val_acc: 0.8343
Epoch [1], val_loss: 0.4457, val_acc: 0.8428
Epoch [2], val_loss: 0.4234, val_acc: 0.8475
Epoch [3], val_loss: 0.4249, val_acc: 0.8430
Epoch [4], val_loss: 0.4109, val_acc: 0.8491
losses = [x['val_loss'] for x in history]
plt.plot(losses, '-x')
plt.title('Loss vs. No. of epochs');
accuracies = [x['val_acc'] for x in history]
plt.plot(accuracies, '-x')
plt.title('Accuracy vs. No. of epochs');

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
evaluate(model, test_loader)
{'val_loss': 0.4459717273712158, 'val_acc': 0.8360351324081421}

Save and upload

saved_weights_fname='fashion-feedforward.pth', saved_weights_fname)
!pip install jovian --upgrade --quiet

import jovian

jovian.commit(project=project_name, environment=None, outputs=[saved_weights_fname])
已标记关键词 清除标记
©️2020 CSDN 皮肤主题: 点我我会动 设计师:上身试试 返回首页