方法一：
"""
多層感知機簡單實現Fashion-MNIST分類，從零開始實現
"""
import torch
import torchvision
from torch.utils import data
from torchvision import transforms
from d2l import torch as d2l
from IPython import display
import matplotlib.pyplot as plt
from torch import nn
def get_fashion_mnist_labels(labels):
"""返回Fashion-MNIST資料集的文字標籤"""
text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
return [text_labels[int(i)] for i in labels]
def show_images(imgs, num_rows, num_cols, titles=None, scale=1.5):
"""繪製影像列表"""
figsize = (num_cols * scale, num_rows * scale)
_, axes = d2l.plt.subplots(num_rows, num_cols, figsize=figsize)
axes = axes.flatten()
for i, (ax, img) in enumerate(zip(axes, imgs)):
if torch.is_tensor(img):
# 圖片張量
ax.imshow(img.numpy())
else:
# PIL圖片
ax.imshow(img)
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
if titles:
ax.set_title(titles[i])
return axes
def get_dataloader_workers():
"""使用4個程序來讀取資料"""
return 4
# 準備資料
def load_data_fashion_mnist(batch_size, resize=None):
"""下載Fashion-MNIST資料集，然後將其載入到記憶體中"""
trans = [transforms.ToTensor()]
if resize:
trans.insert(0, transforms.Resize(resize))
trans = transforms.Compose(trans)
mnist_train = torchvision.datasets.FashionMNIST(
root="../data", train=True, transform=trans, download=True)
mnist_test = torchvision.datasets.FashionMNIST(
root="../data", train=False, transform=trans, download=True)
return (data.DataLoader(mnist_train, batch_size, shuffle=True,
num_workers=get_dataloader_workers()),
data.DataLoader(mnist_test, batch_size, shuffle=False,
num_workers=get_dataloader_workers()))
class Accumulator:
"""在n個變數上累加"""
def __init__(self, n):
self.data = [0.0] * n
def add(self, *args):
self.data = [a + float(b) for a, b in zip(self.data, args)]
def reset(self):
self.data = [0.0] * len(self.data)
def __getitem__(self, idx):
return self.data[idx]
class Animator:
"""在動畫中繪製資料"""
def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
ylim=None, xscale='linear', yscale='linear',
fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
figsize=(3.5, 2.5), pic_name=None):
# 增量地繪製多條線
if legend is None:
legend = []
d2l.use_svg_display()
self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize)
if nrows * ncols == 1:
self.axes = [self.axes, ]
# 使用lambda函式捕獲引數
self.config_axes = lambda: d2l.set_axes(
self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
self.X, self.Y, self.fmts = None, None, fmts
self.pic_name = pic_name
def add(self, x, y):
# 向圖表中新增多個資料點
if not hasattr(y, "__len__"):
y = [y]
n = len(y)
if not hasattr(x, "__len__"):
x = [x] * n
if not self.X:
self.X = [[] for _ in range(n)]
if not self.Y:
self.Y = [[] for _ in range(n)]
for i, (a, b) in enumerate(zip(x, y)):
if a is not None and b is not None:
self.X[i].append(a)
self.Y[i].append(b)
self.axes[0].cla()
for x, y, fmt in zip(self.X, self.Y, self.fmts):
self.axes[0].plot(x, y, fmt)
self.config_axes()
plt.draw()
plt.pause(0.1)
plt.savefig(self.pic_name)
display.display(self.fig)
display.clear_output(wait=True)
def show(self):
display.display(self.fig)
# 訓練
def accuracy(y_hat, y):
"""計算預測正確的數量"""
if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
y_hat = y_hat.argmax(axis=1)
cmp = y_hat.type(y.dtype) == y
return float(cmp.type(y.dtype).sum())
def evaluate_accuracy(net, data_iter):
"""計算在指定資料集上模型的精度"""
if isinstance(net, torch.nn.Module):
net.eval() # 將模型設定為評估模式
metric = Accumulator(2) # 正確預測數、預測總數
with torch.no_grad():
for X, y in data_iter:
metric.add(accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
# 訓練
def train_epoch_ch3(net, train_iter, loss, updater):
"""訓練模型一個迭代週期（定義見第3章）"""
# 將模型設定為訓練模式
if isinstance(net, torch.nn.Module):
net.train()
# 訓練損失總和、訓練準確度總和、樣本數
metric = Accumulator(3)
for X, y in train_iter:
# 計算梯度並更新引數
y_hat = net(X)
l = loss(y_hat, y)
if isinstance(updater, torch.optim.Optimizer):
# 使用PyTorch內建的最佳化器和損失函式
updater.zero_grad()
l.mean().backward()
updater.step()
else:
# 使用定製的最佳化器和損失函式
l.sum().backward()
updater(X.shape[0])
metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
# 返回訓練損失和訓練精度
return metric[0] / metric[2], metric[1] / metric[2]
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
"""訓練模型（定義見第3章）"""
animator = Animator(xlabel='epoch',
xlim=[1, num_epochs], ylim=[0.3, 0.9],
legend=['train loss', 'train acc', 'test acc'],
pic_name="Simple_Multilayer_Fashion_mnist")
for epoch in range(num_epochs):
train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
test_acc = evaluate_accuracy(net, test_iter)
animator.add(epoch + 1, train_metrics + (test_acc,))
train_loss, train_acc = train_metrics
assert train_loss < 0.5, train_loss # train_loss大於0.5報錯
assert train_acc <= 1 and train_acc > 0.7, train_acc
assert test_acc <= 1 and test_acc > 0.7, test_acc
def predict_ch3(net, test_iter, n=6):
"""預測標籤（定義見第3章）"""
for X, y in test_iter:
break
trues = d2l.get_fashion_mnist_labels(y)
preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1))
titles = ["True:" + true +'\n' + "Pred:" + pred for true, pred in zip(trues, preds)]
d2l.show_images(
X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n])
d2l.plt.show()
batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size) # 不進行resize操作, resize=64
# 網路模型
net = nn.Sequential(nn.Flatten(),
nn.Linear(784, 256),
nn.ReLU(),
nn.Linear(256, 10))
# 初始化模型引數
def init_weights(m):
if type(m) == nn.Linear:
nn.init.normal_(m.weight, std=0.01)
net.apply(init_weights)
num_inputs, num_outputs, num_hiddens = 784, 10, 256
batch_size, lr, num_epochs = 256, 0.1, 10
# 損失函式
loss = nn.CrossEntropyLoss(reduction='none')
trainer = torch.optim.SGD(net.parameters(), lr=lr)
train_iter, test_iter = load_data_fashion_mnist(batch_size)
train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
predict_ch3(net, test_iter)
方法二：呼叫nn
"""
多層感知機實現Fashion-MNIST分類，從零開始實現
"""
import torch
import torchvision
from torch.utils import data
from torchvision import transforms
from d2l import torch as d2l
from IPython import display
import matplotlib.pyplot as plt
from torch import nn
def get_fashion_mnist_labels(labels):
"""返回Fashion-MNIST資料集的文字標籤"""
text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
return [text_labels[int(i)] for i in labels]
def show_images(imgs, num_rows, num_cols, titles=None, scale=1.5): #@save
"""繪製影像列表"""
figsize = (num_cols * scale, num_rows * scale)
_, axes = d2l.plt.subplots(num_rows, num_cols, figsize=figsize)
axes = axes.flatten()
for i, (ax, img) in enumerate(zip(axes, imgs)):
if torch.is_tensor(img):
# 圖片張量
ax.imshow(img.numpy())
else:
# PIL圖片
ax.imshow(img)
ax.axes.get_xaxis().set_visible(False)
ax.axes.get_yaxis().set_visible(False)
if titles:
ax.set_title(titles[i])
return axes
def get_dataloader_workers():
"""使用4個程序來讀取資料"""
return 4
# 準備資料
def load_data_fashion_mnist(batch_size, resize=None):
"""下載Fashion-MNIST資料集，然後將其載入到記憶體中"""
trans = [transforms.ToTensor()]
if resize:
trans.insert(0, transforms.Resize(resize))
trans = transforms.Compose(trans)
mnist_train = torchvision.datasets.FashionMNIST(
root="../data", train=True, transform=trans, download=True)
mnist_test = torchvision.datasets.FashionMNIST(
root="../data", train=False, transform=trans, download=True)
return (data.DataLoader(mnist_train, batch_size, shuffle=True,
num_workers=get_dataloader_workers()),
data.DataLoader(mnist_test, batch_size, shuffle=False,
num_workers=get_dataloader_workers()))
batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size) # 不進行resize操作, resize=64
# 初始化模型引數
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = nn.Parameter(torch.randn(num_inputs, num_hiddens, requires_grad=True) * 0.01)
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
W2 = nn.Parameter(torch.randn(num_hiddens, num_outputs, requires_grad=True) * 0.01)
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))
params = [W1, b1, W2, b2]
# 啟用函式
def relu(X):
a = torch.zeros_like(X)
return torch.max(X, a)
# 網路模型
def net(X):
X = X.reshape((-1, num_inputs))
H = relu(X@W1 + b1) # 這裡“@”代表矩陣乘法
return (H@W2 + b2)
# 損失函式
loss = nn.CrossEntropyLoss(reduction='none')
class Accumulator:
"""在n個變數上累加"""
def __init__(self, n):
self.data = [0.0] * n
def add(self, *args):
self.data = [a + float(b) for a, b in zip(self.data, args)]
def reset(self):
self.data = [0.0] * len(self.data)
def __getitem__(self, idx):
return self.data[idx]
class Animator:
"""在動畫中繪製資料"""
def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
ylim=None, xscale='linear', yscale='linear',
fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
figsize=(3.5, 2.5), pic_name=None):
# 增量地繪製多條線
if legend is None:
legend = []
d2l.use_svg_display()
self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize)
if nrows * ncols == 1:
self.axes = [self.axes, ]
# 使用lambda函式捕獲引數
self.config_axes = lambda: d2l.set_axes(
self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
self.X, self.Y, self.fmts = None, None, fmts
self.pic_name = pic_name
def add(self, x, y):
# 向圖表中新增多個資料點
if not hasattr(y, "__len__"):
y = [y]
n = len(y)
if not hasattr(x, "__len__"):
x = [x] * n
if not self.X:
self.X = [[] for _ in range(n)]
if not self.Y:
self.Y = [[] for _ in range(n)]
for i, (a, b) in enumerate(zip(x, y)):
if a is not None and b is not None:
self.X[i].append(a)
self.Y[i].append(b)
self.axes[0].cla()
for x, y, fmt in zip(self.X, self.Y, self.fmts):
self.axes[0].plot(x, y, fmt)
self.config_axes()
plt.draw()
plt.pause(0.1)
plt.savefig(self.pic_name)
display.display(self.fig)
display.clear_output(wait=True)
def show(self):
display.display(self.fig)
# 訓練
def accuracy(y_hat, y):
"""計算預測正確的數量"""
if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
y_hat = y_hat.argmax(axis=1)
cmp = y_hat.type(y.dtype) == y
return float(cmp.type(y.dtype).sum())
def evaluate_accuracy(net, data_iter):
"""計算在指定資料集上模型的精度"""
if isinstance(net, torch.nn.Module):
net.eval() # 將模型設定為評估模式
metric = Accumulator(2) # 正確預測數、預測總數
with torch.no_grad():
for X, y in data_iter:
metric.add(accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
# 訓練
def train_epoch_ch3(net, train_iter, loss, updater):
"""訓練模型一個迭代週期（定義見第3章）"""
# 將模型設定為訓練模式
if isinstance(net, torch.nn.Module):
net.train()
# 訓練損失總和、訓練準確度總和、樣本數
metric = Accumulator(3)
for X, y in train_iter:
# 計算梯度並更新引數
y_hat = net(X)
l = loss(y_hat, y)
if isinstance(updater, torch.optim.Optimizer):
# 使用PyTorch內建的最佳化器和損失函式
updater.zero_grad()
l.mean().backward()
updater.step()
else:
# 使用定製的最佳化器和損失函式
l.sum().backward()
updater(X.shape[0])
metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
# 返回訓練損失和訓練精度
return metric[0] / metric[2], metric[1] / metric[2]
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
"""訓練模型（定義見第3章）"""
animator = Animator(xlabel='epoch',
xlim=[1, num_epochs], ylim=[0.3, 0.9],
legend=['train loss', 'train acc', 'test acc'],
pic_name="Multilayer_Fashion_mnist")
for epoch in range(num_epochs):
train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
test_acc = evaluate_accuracy(net, test_iter)
animator.add(epoch + 1, train_metrics + (test_acc,))
train_loss, train_acc = train_metrics
assert train_loss < 0.5, train_loss
assert train_acc <= 1 and train_acc > 0.7, train_acc
assert test_acc <= 1 and test_acc > 0.7, test_acc
def predict_ch3(net, test_iter, n=6):
"""預測標籤（定義見第3章）"""
for X, y in test_iter:
break
trues = d2l.get_fashion_mnist_labels(y)
preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1))
titles = ["True:" + true +'\n' + "Pred:" + pred for true, pred in zip(trues, preds)]
d2l.show_images(
X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n])
d2l.plt.show()
num_epochs, lr = 10, 0.1
updater = torch.optim.SGD(params, lr=lr)
train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)
predict_ch3(net, test_iter)