第三章 3.10 构建更深的神经网络 比较有0、1、2隐含层的神经网络

 

比较有0、1、2隐含层的神经网络，发现层多时，过拟合

# https://github.com/PacktPublishing/Modern-Computer-Vision-with-PyTorch
# https://github.com/PacktPublishing/Modern-Computer-Vision-with-PyTorch

###################  Chapter Three #######################################

# 第三章  读取数据集并显示
from torch.utils.data import Dataset, DataLoader
import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt
########################################################################
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

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
#Model with 0 hidden layers
# def get_model():
#     model = nn.Sequential(
#         nn.Linear(28 * 28, 10)
#     ).to(device)
#
#     loss_fn = nn.CrossEntropyLoss()
#     optimizer = Adam(model.parameters(), lr=1e-3)
#     return model, loss_fn, optimizer
#Model with 1 hidden layers
# def get_model():
#     model = nn.Sequential(
#         #nn.Linear(28 * 28, 10)
#         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

# Model with 2 hidden layers
def get_model():
    model = nn.Sequential(
        nn.Linear(28 * 28, 1000),
        nn.ReLU(),
        nn.Linear(1000, 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, optimizer, 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)#批大小
    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):
    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(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)
    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)

########################################################################
epochs = np.arange(30)+1#轮数 30
import matplotlib.ticker as mtick
import matplotlib.pyplot as plt
import matplotlib.ticker as mticker
#%matplotlib inline
plt.figure(figsize=(20,5))
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 no hidden layer')
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 no hidden layer')
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()