李沐视频课笔记其他文章目录链接(不定时更新)
Code:
%matplotlib inline
import torch
import torchvision
from torch.utils import data
from torchvision import transforms
from d2l import torch as d2l
d2l.use_svg_display()
Code:
# 通过ToTensor实例将图像数据从PIL类型变换为32位浮点数格式
# 并除以255使得所有像素的数据均在0到1之间
trans = transforms.ToTensor()
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
)
len(mnist_train), len(mnist_test), mnist_train[0][0].shape
Result:
Code:
def get_fashion_mnist_labels(labels):
'''返回Fashion-MNIST数据集的文本标签'''
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):
"""Plot is a list of images."""
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):
# 图片张量
ax.imshow(img.numpy())
ax.axis('off')
ax.set_title(titles[i])
else:
# PIL图片
ax.imshow(img)
Code:
X, y = next(iter(data.DataLoader(mnist_train, batch_size=18)))
show_images(X.reshape(18, 28, 28), 2, 9, titles=get_fashion_mnist_labels(y))
Result:
Code:
batch_size = 256
def get_dataloader_workers():
"""使用4个进程来读取的数据"""
return 4
train_iter = data.DataLoader(mnist_train, batch_size, shuffle=True,
num_workers=get_dataloader_workers())
timer = d2l.Timer()
for X, y in train_iter:
continue
print(f'{timer.stop():.2f} sec')
Result:
Code:
def load_data_fashion_mnist(batch_size, resize=None):
"""下载Fashion-MNIST数据集, 然后将其加载到内存中。"""
trans = [transforms.ToTensor()]
if resize:
trans.insert(0, transfoems.Resize(resize))
trans = transforms.Compose(trans)
mnist_train = torchvision.datasets.FashionMNIST(root="../data",
train=True,transform=trans,
download=False)
mnist_test = torchvision.datasets.FashionMNIST(root="../data",
train=False,transform=trans,
download=False)
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()))
Code:
import torch
from IPython import display
from d2l import torch as d2l
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
Code:
num_inputs = 784
num_outputs = 10
W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)
s o f t m a x ( X i j ) = e x p ( X i j ) ∑ k X i k softmax(X_{ij})=\frac{exp(X_{ij})}{\sum_{k}X_{ik}} softmax(Xij)=∑kXikexp(Xij)
Code:
def softmax(X):
X_exp = torch.exp(X)
partition = X_exp.sum(1, keepdim=True)
return X_exp / partition # 这里应用了广播机制
Code:
def net(X):
return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)
Code:
y = torch.tensor([0, 2])
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y_hat[[0, 1], y]
Result:
Code:
def cross_entropy(y_hat, y):
return -torch.log(y_hat[range(len(y_hat)), y])
cross_entropy(y_hat, y)
Result:
Code:
def accuracy(y_hat, y):
"""计算预测正确的数量"""
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 # 从右至左,y_hat.type(y.dtype)返回y数据类型的张量,之后返回bool类型给cmp
return float(cmp.type(y.dtype).sum())
accuracy(y_hat, y) / len(y)
Result:
Code:
def evaluate_accuracy(net, data_iter):
"""计算在指定数据集上模型的精度"""
if isinstance(net, torch.nn.Module):
net.eval() # 将模型设置为评估模式
metric = Accumulator(2) # 正确预测数、预测总数
for X, y in data_iter:
metric.add(accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
Code:
class Accumulator:
"""在'n'个变量上累加。"""
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]
evaluate_accuracy(net, test_iter)
Result:
Code:
def train_epoch_ch3(net, train_iter, loss, updater):
if isinstance(net, torch.nn.Module):
net.train()
metric = Accumulator(3)
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y)
if isinstance(updater, torch.optim.Optimizer):
updater.zero_grad()
l.backward()
updater.step()
metric.add(
float(1) * len(y), accuracy(y_hat, y),
y.size.numel()
)
else:
l.sum().backward()
updater(X.shape[0])
metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
return metric[0] / metric[2], metric[1] / metric[2]
Code:
class Animator:
"""在动画中绘制数据"""
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)):
#增量地绘制多条线
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函数捕获参数
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
def add(self, x, y):
# 向图表中添加多个数据点
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()
display.display(self.fig)
display.clear_output(wait=True)
Code:
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9],
legend=['train loss', 'train acc', 'test acc'])
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
Code:
lr = 0.1
def updater(batch_size):
return d2l.sgd([W, b], lr, batch_size)
Code:
num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)
Result:
Code:
def predict_ch3(net, test_iter, n=6): #@save
"""预测标签(定义⻅第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 +'\n' + pred for true, pred in zip(trues, preds)]
d2l.show_images(
X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n])
predict_ch3(net, test_iter)
Result:
Code:
import torch
from torch import nn
from d2l import torch as d2l
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
Code:
# PyTorch不会隐式地调整输入的形状
# 因此,我们定义了展平层(flatten)在线性层前调整网络输入的形状
net = nn.Sequential(nn.Flatten(), nn.Linear(784, 10))
def init_weights(m):
if type(m) == nn.Linear:
nn.init.normal_(m.weight, std=0.01)
net.apply(init_weights)
Result:
Code:
loss = nn.CrossEntropyLoss()
Code:
trainer = torch.optim.SGD(net.parameters(), lr=0.1)
Code:
# d2l包中的train_epoch_ch3函数和视频课上实现的train_epoch_ch3函数不同,
# 视频课使用l.mean().backward(),d2l包使用l.sum().backward(),
# 求和导致损失过大,图像上不显示loss曲线
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
Result: