本节代码文件在chapter_linear-networks/image-classification-dataset.ipynb中
1.图像分类数据集
2.softmax回归的从0实现pycharm版
import torch
# import numpy
# import random
from IPython import display
from d2l import torch as d2l
# from d2l.torch import Accumulator
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
num_inputs = 784
num_outputs = 10 # 数据集有十个类别，所以输出为10
W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True) # （均值，方差，（行数，列数），是否计算梯度）
b = torch.zeros(num_outputs, requires_grad=True)
# 给定一个矩阵x，对所有元素求和
# 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)
# print(X.sum(0, keepdim=True), X.sum(1, keepdim=True))
# 实现softmax
def softmax(X):
X_exp = torch.exp(X)
partition = X_exp.sum(1, keepdim=True) # 按行求和
return X_exp / partition # 应用广播机制
X = torch.normal(0, 1, (2,5))
X_prob = softmax(X)
# X_prob,X_prob.sum(1)
print(X_prob, X_prob.sum(1))
# 实现softmax回归模型
def net(X):
return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b) # 让X的列数等于W的行数，然后矩阵相乘加上b再用softmax转化
# -1是占位符，根据后面的额维度推算-1这位的具体数值
X = torch.normal(0, 1, (2,5))
print(X)
print(X+1)
# 交叉熵
y = torch.tensor([0, 2]) # 两个真实标号， 两个样本
y_hat = torch.tensor([[0.1, 0.3, 0.6],
[0.3, 0.2, 0.5]]) # 预测值，分别对应三类
# y_hat[[0, 1], y]
print(y_hat[[0, 1], y])
def cross_entropy(y_hat, y):
return -torch.log(y_hat[range(len(y_hat)), y])
# cross_entropy(y_hat, y)
# print(cross_entropy(y_hat, y))
# 将预测类别与真实y元素比较
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
return float(cmp.type(y.dtype).sum())
# accuracy(y_hat, y) / len(y)
print(accuracy(y_hat, y) / len(y))
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() # 将模式设置为评估模式
metric = Accumulator(2)
for X, y in data_iter:
metric.add(accuracy(net(X), y), y.numel())
return metric[0] / metric[1] # 正确样本数/总样本数
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]
# if __name__=='__main__':
# print(evaluate_accuracy(net, test_iter))
def train_epoch_ch3(net, train_iter, loss, updater):
if isinstance(net, torch.nn.Module):
net.train() # 训练模式
metric = Accumulator(3) # 长度为3的迭代器
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(l) * 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]
# 在动画中绘制数据
class Animator:
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)):
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, ]
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):
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)
# 训练函数
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,))
d2l.plt.show()
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):
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])
d2l.plt.show()
predict_ch3(net, test_iter)3.softmax回归的简洁实现
# softmax回归的简洁实现
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)
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)
loss = nn.CrossEntropyLoss()
trainer = torch.optim.SGD(net.parameters(), lr=0.1) # 学习率为0.1的小批量随机梯度下降作为优化算法
num_epochs = 10
# d2l.train_ch3(net, train_iter,test_iter, loss, num_epochs, trainer)
d2l.train_ch3(net, train_iter,test_iter,loss,num_epochs,trainer)
d2l.plt.show() # 只调用在pycharm里不能显示曲线，所以加一句用来显示曲线
注：比较新的版本可能不能调用train_ch3()函数，一开始用的1.17.0版本，不能调用，换成了0.15.1版本后就可以调用了
2540
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
