177 KiB
177 KiB
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>