Computer_Vision/Chapter03/Scaling_the_dataset.ipynb

from torchvision import datasets
from torch.utils.data import Dataset, DataLoader
import torch
import torch.nn as nn
device = "cuda" if torch.cuda.is_available() else "cpu"
import numpy as np
data_folder = '~/data/FMNIST' # This can be any directory you want 
# to download FMNIST to
fmnist = datasets.FashionMNIST(data_folder, download=True, train=True)
tr_images = fmnist.data
tr_targets = fmnist.targets

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to /root/data/FMNIST/FashionMNIST/raw/train-images-idx3-ubyte.gz

HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))

Extracting /root/data/FMNIST/FashionMNIST/raw/train-images-idx3-ubyte.gz to /root/data/FMNIST/FashionMNIST/raw
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to /root/data/FMNIST/FashionMNIST/raw/train-labels-idx1-ubyte.gz

HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))

Extracting /root/data/FMNIST/FashionMNIST/raw/train-labels-idx1-ubyte.gz to /root/data/FMNIST/FashionMNIST/raw
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to /root/data/FMNIST/FashionMNIST/raw/t10k-images-idx3-ubyte.gz

HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))

Extracting /root/data/FMNIST/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to /root/data/FMNIST/FashionMNIST/raw
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to /root/data/FMNIST/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz

HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))

Extracting /root/data/FMNIST/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to /root/data/FMNIST/FashionMNIST/raw
Processing...
Done!

/usr/local/lib/python3.6/dist-packages/torchvision/datasets/mnist.py:469: 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. (Triggered internally at  /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)
  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)

class FMNISTDataset(Dataset):
    def __init__(self, x, y):
        x = x.float()/255
        x = x.view(-1,28*28)
        self.x, self.y = x, y 
    def __getitem__(self, ix):
        x, y = self.x[ix], self.y[ix] 
        return x.to(device), y.to(device)
    def __len__(self): 
        return len(self.x)

def get_data(): 
    train = FMNISTDataset(tr_images, tr_targets) 
    trn_dl = DataLoader(train, batch_size=32, shuffle=True)
    return trn_dl
from torch.optim import SGD
def get_model():
    model = nn.Sequential(
        nn.Linear(28 * 28, 1000),
        nn.ReLU(),
        nn.Linear(1000, 10)
    ).to(device)
    loss_fn = nn.CrossEntropyLoss()
    optimizer = SGD(model.parameters(), lr=1e-2)
    return model, loss_fn, optimizer
def train_batch(x, y, model, opt, loss_fn):
    model.train()
    # call your model like any python function on your batch of inputs
    prediction = model(x)
    # compute loss
    batch_loss = loss_fn(prediction, y)
    # based on the forward pass in `model(x)` compute all the gradients of 
    # 'model.parameters()'
    batch_loss.backward()
    # apply new-weights = f(old-weights, old-weight-gradients) 
    # where "f" is the optimizer
    optimizer.step()
    # Flush memory for next batch of calculations
    optimizer.zero_grad()
    return batch_loss.item()
def accuracy(x, y, model):
    model.eval()
    # since there's no need for updating weights, we might 
    # as well not compute the gradients
    with torch.no_grad():
        # get the prediction matrix for a tensor of `x` images
        prediction = model(x)
    # compute if the location of maximum in each row coincides 
    # with ground truth
    max_values, argmaxes = prediction.max(-1)
    is_correct = argmaxes == y
    return is_correct.cpu().numpy().tolist()
trn_dl = get_data()
model, loss_fn, optimizer = get_model()
losses, accuracies = [], []
for epoch in range(5):
    print(epoch)
    epoch_losses, epoch_accuracies = [], []
    for ix, batch in enumerate(iter(trn_dl)):
        x, y = batch
        batch_loss = train_batch(x, y, model, optimizer, loss_fn)
        epoch_losses.append(batch_loss)
    epoch_loss = np.array(epoch_losses).mean()
    for ix, batch in enumerate(iter(trn_dl)):
        x, y = batch
        is_correct = accuracy(x, y, model)
        epoch_accuracies.extend(is_correct)
    epoch_accuracy = np.mean(epoch_accuracies)
    losses.append(epoch_loss)
    accuracies.append(epoch_accuracy)

0
1
2
3
4

epochs = np.arange(5)+1
import matplotlib.pyplot as plt
%matplotlib inline
plt.figure(figsize=(20,5))
plt.subplot(121)
plt.title('Loss value over increasing epochs')
plt.plot(epochs, losses, label='Training Loss')
plt.legend()
plt.subplot(122)
plt.title('Accuracy value over increasing epochs')
plt.plot(epochs, accuracies, label='Training Accuracy')
plt.gca().set_yticklabels(['{:.0f}%'.format(x*100) for x in plt.gca().get_yticks()]) 
plt.legend()

<matplotlib.legend.Legend at 0x7facd08c46d8>