Computer_Vision/Chapter04/Issues_with_image_translation.ipynb

from torchvision import datasets
import torch
data_folder = '/content/' # This can be any directory you want to download FMNIST to
fmnist = datasets.FashionMNIST(data_folder, download=True, train=True)

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

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

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

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

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

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

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

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

Extracting /content/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to /content/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)

tr_images = fmnist.data
tr_targets = fmnist.targets

val_fmnist = datasets.FashionMNIST(data_folder, download=True, train=False)
val_images = val_fmnist.data
val_targets = val_fmnist.targets

import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
from torch.utils.data import Dataset, DataLoader
import torch
import torch.nn as nn
device = 'cuda' if torch.cuda.is_available() else 'cpu'

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)

from torch.optim import SGD, Adam
def get_model():
    model = nn.Sequential(
        nn.Linear(28 * 28, 1000),
        nn.ReLU(),
        nn.Linear(1000, 10)
    ).to(device)

    loss_fn = nn.CrossEntropyLoss()
    optimizer = Adam(model.parameters(), lr=1e-3)
    return model, loss_fn, optimizer

def train_batch(x, y, model, opt, loss_fn):
    prediction = model(x)
    batch_loss = loss_fn(prediction, y)
    batch_loss.backward()
    optimizer.step()
    optimizer.zero_grad()
    return batch_loss.item()

def accuracy(x, y, model):
    with torch.no_grad():
        prediction = model(x)
    max_values, argmaxes = prediction.max(-1)
    is_correct = argmaxes == y
    return is_correct.cpu().numpy().tolist()

def get_data():     
    train = FMNISTDataset(tr_images, tr_targets)     
    trn_dl = DataLoader(train, batch_size=32, shuffle=True)
    val = FMNISTDataset(val_images, val_targets)     
    val_dl = DataLoader(val, batch_size=len(val_images), shuffle=True)
    return trn_dl, val_dl

def val_loss(x, y, model):
    with torch.no_grad():
        prediction = model(x)
    val_loss = loss_fn(prediction, y)
    return val_loss.item()

trn_dl, val_dl = get_data()
model, loss_fn, optimizer = get_model()

train_losses, train_accuracies = [], []
val_losses, val_accuracies = [], []
for epoch in range(5):
    print(epoch)
    train_epoch_losses, train_epoch_accuracies = [], []
    for ix, batch in enumerate(iter(trn_dl)):
        x, y = batch
        batch_loss = train_batch(x, y, model, optimizer, loss_fn)
        train_epoch_losses.append(batch_loss)        
    train_epoch_loss = np.array(train_epoch_losses).mean()

    for ix, batch in enumerate(iter(trn_dl)):
        x, y = batch
        is_correct = accuracy(x, y, model)
        train_epoch_accuracies.extend(is_correct)
    train_epoch_accuracy = np.mean(train_epoch_accuracies)

    for ix, batch in enumerate(iter(val_dl)):
        x, y = batch
        val_is_correct = accuracy(x, y, model)
        validation_loss = val_loss(x, y, model)
    val_epoch_accuracy = np.mean(val_is_correct)

    train_losses.append(train_epoch_loss)
    train_accuracies.append(train_epoch_accuracy)
    val_losses.append(validation_loss)
    val_accuracies.append(val_epoch_accuracy)

0
1
2
3
4

#ix = np.random.randint(len(tr_images))
ix = 24300
plt.imshow(tr_images[ix], cmap='gray')
plt.title(fmnist.classes[tr_targets[ix]])

Text(0.5, 1.0, 'Trouser')

img = tr_images[ix]/255.
img = img.view(28*28)
img = img.to(device)

np_output = model(img).cpu().detach().numpy()
np.exp(np_output)/np.sum(np.exp(np_output))

array([2.4361714e-06, 9.9999738e-01, 8.3687448e-09, 2.2200647e-08,
       5.7493144e-10, 8.5185324e-14, 1.6882856e-07, 7.0115940e-21,
       3.0295655e-12, 1.3271068e-13], dtype=float32)

Translation

tr_targets[ix]

tensor(1)

preds = []
for px in range(-5,6):
  img = tr_images[ix]/255.
  img = img.view(28, 28)
  #img2 = np.zeros((28,28))
  img2 = np.roll(img, px, axis=1)
  plt.imshow(img2)
  plt.show()
  img3 = torch.Tensor(img2).view(28*28).to(device)
  np_output = model(img3).cpu().detach().numpy()
  preds.append(np.exp(np_output)/np.sum(np.exp(np_output)))

import seaborn as sns
fig, ax = plt.subplots(1,1, figsize=(12,10))
plt.title('Probability of each class for various translations')
sns.heatmap(np.array(preds), annot=True, ax=ax, fmt='.2f', xticklabels=fmnist.classes, yticklabels=[str(i)+str(' pixels') for i in range(-5,6)], cmap='gray')

<matplotlib.axes._subplots.AxesSubplot at 0x7fe8819940f0>