Computer_Vision/Chapter03/Learning_rate_annealing.ipynb

from torchvision import datasets
import torch
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)

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()
        x = x.view(-1,28*28)/255
        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):
    model.train()
    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):
    model.eval()
    # this is the same as @torch.no_grad 
    # at the top of function, only difference
    # being, grad is not computed in the with scope
    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=False)
    return trn_dl, val_dl

@torch.no_grad()
def val_loss(x, y, model):
    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()

from torch import optim
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, factor=0.5, patience=0, threshold = 0.001, verbose=True, min_lr = 1e-5, threshold_mode = 'abs')
train_losses, train_accuracies = [], []
val_losses, val_accuracies = [], []
for epoch in range(30):
    #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)
        scheduler.step(validation_loss)
    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)

Epoch     2: reducing learning rate of group 0 to 5.0000e-04.
Epoch     8: reducing learning rate of group 0 to 2.5000e-04.
Epoch    11: reducing learning rate of group 0 to 1.2500e-04.
Epoch    14: reducing learning rate of group 0 to 6.2500e-05.
Epoch    15: reducing learning rate of group 0 to 3.1250e-05.
Epoch    16: reducing learning rate of group 0 to 1.5625e-05.
Epoch    17: reducing learning rate of group 0 to 1.0000e-05.

epochs = np.arange(30)+1
import matplotlib.ticker as mtick
import matplotlib.pyplot as plt
import matplotlib.ticker as mticker
%matplotlib inline
plt.subplot(211)
plt.plot(epochs, train_losses, 'bo', label='Training loss')
plt.plot(epochs, val_losses, 'r', label='Validation loss')
plt.gca().xaxis.set_major_locator(mticker.MultipleLocator(1))
plt.title('Training and validation loss with learning rate scheduler')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.grid('off')
plt.show()
plt.subplot(212)
plt.plot(epochs, train_accuracies, 'bo', label='Training accuracy')
plt.plot(epochs, val_accuracies, 'r', label='Validation accuracy')
plt.gca().xaxis.set_major_locator(mticker.MultipleLocator(1))
plt.title('Training and validation accuracy with learning rate scheduler')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.gca().set_yticklabels(['{:.0f}%'.format(x*100) for x in plt.gca().get_yticks()]) 
plt.legend()
plt.grid('off')
plt.show()