%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()
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)
输出
(60000, 10000)
mnist_train[0][0].shape
输出
torch.Size([1, 28, 28])
单通道,28 * 28
def get_fashion_mnist_labels(labels):
"""返回数据集的文本标签"""
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):
"""绘制图像列表"""
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):
ax.imshow(img.numpy())
else:
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
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));
将数据集放进一个DataLoader里,指定一个batch_size
batch_size = 256
def get_dataloader_workers(): #@save
"""使用4个进程来读取数据"""
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
f'{timer.stop():.2f} sec'
输出
'6.63 sec'
def load_data_fashion_mnist(batch_size, resize=None): #@save
"""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, 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()))
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)
每次读取256个图片,返回训练集和测试集迭代器
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)
像素 = 28 * 28,通道数 = 1,作为一个向量输入维度 = 784,这个拉伸过程会损失很多空间信息,卷积神经网络可以解决这个问题。
图片有10种分类,所以输出维度 = 10
W矩阵大小 784 * 10 ,计算梯度 requires_grad=True
b是长为10的列向量
X = torch.tensor([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
X.sum(0, keepdim=True), X.sum(1, keepdim=True)
输出
(tensor([[5., 7., 9.]]),
tensor([[ 6.],
[15.]]))
回顾一下:对矩阵某一行或列求和
0:列的求和(把所有行摞到一起)
1:行的求和(把所有列挤到一起)
keepdim = True 保持矩阵的维度
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
s o f t m a x ( X ) i j = e x p ( X i j ) ∑ k e x p ( X i k ) softmax(X)_{ij} = \frac{exp(X_{ij})}{\sum_{k}exp(X_{ik})} softmax(X)ij=∑kexp(Xik)exp(Xij)
对于输出矩阵,对每一行(每一个样本)做Softmax
验证一下
X = torch.normal(0, 1, (2, 5))
X_prob = softmax(X)
X_prob, X_prob.sum(1)
输出
(tensor([[0.2459, 0.0962, 0.1512, 0.4693, 0.0374],
[0.1013, 0.0931, 0.1746, 0.0606, 0.5704]]),
tensor([1., 1.]))
def net(X):
return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)
reshape((-1, W.shape[0])) -1:自己算一下,实际等于批量大小。
维度:
X = batchsize(256) * 样本的长度(784)
W = 784 * 10
b = 10 * 1
怎么把预测值拿出来?
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]
例子
对两个样本做三个类别的预测:
y:正确的分类,即第一个样本应该被预测为第一类,第二个样本应该被预测为第三类。
y_hat:我的输出
y_hat[[0, 1], y] : 二维矩阵中元素的位置:[0 , 0],[1 , 2]
即我预测出来的值 0.1和0.5
tensor([0.1000, 0.5000])
交叉熵损失函数
def cross_entropy(y_hat, y):
return - torch.log(y_hat[range(len(y_hat)), y])
cross_entropy(y_hat, y)
range(len(y_hat)):生成 [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
tensor([2.3026, 0.6931])
还是上面的那个两个样本的例子,分别求出了两个样本的损失
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:
"""axis=1:每一行的列的值进行比较,最大的作为这一行的y_hat"""
y_hat = y_hat.argmax(axis=1)
cmp = y_hat.type(y.dtype) == y
return float(cmp.type(y.dtype).sum())
accuracy(y_hat, y) / len(y)
cmp是bool值,该函数返回预测正确的样本数,然后计算预测正确率
0.5
评估任意模型net的正确率
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) # 累加器:正确预测数、预测总数
with torch.no_grad():
for X, y in data_iter:
#先预测一下net(X),再评估一下正确率accuracy(net(X), y),放入累加器
metric.add(accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
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)
测试一下
0.086
这时候还没反向传播梯度下降呢,就是一个随机的模型,准确率大概10%,正好10个类别
#训练一带
def train_epoch_ch3(net, train_iter, loss, updater):
"""训练模型一个迭代周期(定义见第3章)"""
# 如果我用的是nn,将模型设置为训练模式,告诉pytorch我要计算梯度
if isinstance(net, torch.nn.Module):
net.train()
# 训练损失总和、训练准确度总和、样本数
metric = Accumulator(3)
for X, y in train_iter:
# 计算梯度并更新参数
y_hat = net(X)
l = loss(y_hat, y)
if isinstance(updater, torch.optim.Optimizer):
# 使用PyTorch内置的优化器和损失函数
updater.zero_grad()
l.mean().backward()
updater.step()
else:
# 使用定制的优化器和损失函数
l.sum().backward()
updater(X.shape[0])
metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
# 返回训练损失和训练精度
return metric[0] / metric[2], metric[1] / metric[2]
#画图
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)
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater): #@save
"""训练模型(定义见第3章)"""
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):
#训练一代
train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
#在测试集上看看精度
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
lr = 0.1
def updater(batch_size):
return d2l.sgd([W, b], lr, batch_size)
num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)
def predict_ch3(net, test_iter, n=6): #@save
"""预测标签(定义见第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)
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)
# PyTorch不会隐式地调整输入的形状。因此,
# 我们在线性层前定义了展平层(flatten),来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);
因为softmax不会调整形状,所以nn.Flatten():将任意维度压缩成二维,保留第一个维度(样本数),将剩下的维度拉伸成一个变量。和reshape()差不多。
后面一个线性层,输入:784;输出:10
init_weights(m) : m是当前层,如果是线性层,把w初始化成均值为0,方差为1的正态分布随机值。
net.apply(init_weights):每一层都跑一下这个函数,完成模型参数初始化。
loss = nn.CrossEntropyLoss(reduction='none')
trainer = torch.optim.SGD(net.parameters(), lr=0.1)
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
之前在d2l中保存的 train_ch3