def main():
# 3.6.1 获取和读取数据
batch_size = 256
train_iter, test_iter = d2l.load_data_from_fashion_mnist(batch_size)
# 3.6.2 初始化模型参数
num_inputs = 784
num_outputs = 10
W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)),
dtype=torch.float32)
b = torch.zeros(num_outputs, dtype=torch.float32)
W.requires_grad_(True)
b.requires_grad_(True)
# 3.6.3 实现 softmax 运算
def softmax(X):
X_exp = X.exp()
partition = X_exp.sum(dim=1, keepdim=True)
return X_exp / partition
# 3.6.4 定义模型
def net(X):
return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)
# 3.6.5 定义损失函数
def cross_entropy(y_hat, y):
return -torch.log(y_hat.gather(1, y.view(-1, 1)))
# 3.6.6 计算分类准确率（已在 d2lzh 包中实现）
def accuracy(y_hat, y):
return (y_hat.argmax(dim=1) == y).float().mean().item()
# 3.6.7 训练模型
num_epochs, lr = 5, 0.1
d2l.train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs,
batch_size, [W, b], lr)
# 3.6.8 预测
X, y = iter(test_iter).next()
true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [
true + '\n' + pred for true, pred in zip(true_labels, pred_labels)
]
d2l.show_fashion_mnist(X[0:9], titles[0:9])
def main():
# 3.5.1 获取数据集
mnist_train = torchvision.datasets.FashionMNIST(
root="./data/FashionMNIST",
train=True,
download=True,
transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(
root="./data/FashionMNIST",
train=False,
download=True,
transform=transforms.ToTensor())
feature, label = mnist_train[0]
print(feature.shape, label)
X, y = [], []
for i in range(10):
X.append(mnist_train[i][0])
y.append(mnist_train[i][1])
d2l.show_fashion_mnist(X, d2l.get_fashion_mnist_labels(y))
# 3.5.2 读取小批量
batch_size = 256
train_iter = Data.DataLoader(mnist_train,
batch_size=batch_size,
shuffle=True,
num_workers=0)
test_iter = Data.DataLoader(mnist_test,
batch_size=batch_size,
shuffle=True,
num_workers=0)
# 查看读取一遍数据需要的时间
start = time.time()
for X, y in train_iter:
continue
for X, y in test_iter:
continue
print("%.2f secs" % (time.time() - start))
if optimizer is not None:
optimizer.zero_grad()
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
if optimizer is None:
d2l.sgd(params, lr, batch_size)
else:
optimizer.step() # “softmax回归的简洁实现”一节将用到
train_l_sum += l.item()
train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
n += y.shape[0]
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f' %
(epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size,
[W, b], lr)
X, y = iter(test_iter).next()
true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
d2l.show_fashion_mnist(X[0:9], titles[0:9])
l = loss(y_hat, y).sum()
if optimizer is not None:
optimizer.zero_grad()
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
if optimizer is None:
d2l.sgd(params, lr, batch_size)
else:
optimizer.step()
train_l_sum += l.item()
train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
n += y.shape[0]
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f' %
(epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size,
[W, b], lr)
'''X, y = iter(test_iter).next()
true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
d2l.show_fashion_mnist(X[0:9], titles[0:9])'''
num_workers=num_workers)
print('train len is ', len(mnist_train), 'test len is ', len(mnist_test))
# 可以使用下标访问任意一个样本
feature, label = mnist_train[0]
print(feature.shape, label)
# 将数值标签转换成对应的类别文本标签
def get_fashion_mnist_labels(labels):
text_labels = [
't-shirt', 'trouser', 'pullover', 'dress', 'coat', 'sandal', 'shirt',
'sneaker', 'bag', 'ankle boot'
]
return [text_labels[int(i)] for i in labels]
x, y = [], []
for i in range(10):
x.append(mnist_train[i][0])
y.append(mnist_test[i][1])
d2l.show_fashion_mnist(x, get_fashion_mnist_labels(y))
start = time.time()
for x, y in train_iter:
continue
print('load train data spend %.2f sec' % (time.time() - start))
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import time
import sys
sys.path.append("..") # 为了导⼊上层⽬录的d2lzh_pytorch
import d2lzh_pytorch as d2l
# %%
mnist_train = torchvision.datasets.FashionMNIST(
root='Datasets',
train=True,
download=True,
transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='Datasets',
train=False,
download=True,
transform=transforms.ToTensor())
print(type(mnist_train))
print(len(mnist_train), len(mnist_test))
# %%
feature, label = mnist_train[0]
print(feature.shape, label)
# %%
X, y = [], []
for i in range(10):
X.append(mnist_train[i][0])
y.append(mnist_train[i][1])
d2l.show_fashion_mnist(X, d2l.get_fashion_mnist_labels(y))
# %%
# 定义交叉熵损失函数
def cross_entropy(y_hat, y):
# -1 表示该维度大小由其他维度决定
# gather(dim, index) 可以理解为映射, index（即y）是一个tensor，它的dim和必须和y_hat一样
# 以y的值为下标，从y_hat中抽取对应的值
# 比如 torch.gather(t, 1, torch.tensor([[0,0],[1,0]])) 的结果为 tensor([[1, 1], [4, 3]])
return -torch.log(y_hat.gather(1, y.view(-1, 1))).sum() / y_hat.shape[0]
# 设置参数
batch_size, num_epochs, lr = 256, 3, 0.1
# 获取数据
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
# 训练模型
d2l.train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs,
batch_size, [W, b], lr)
# 预测
X, y = iter(test_iter).next()
true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
# 绘制
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
for i in range(2):
# test[:] 记住冒号右边的下标的元素不会包含在目标列表中！
d2l.show_fashion_mnist(X[(5 * i):(5 * (i + 1))],
titles[(5 * i):(5 * (i + 1))])
X_train_tensor = torch.from_numpy(X_train).to(torch.float32).view(
-1, 1, 28, 28) * (1 / 255.0)
X_test_tensor = torch.from_numpy(X_test).to(torch.float32).view(
-1, 1, 28, 28) * (1 / 255.0)
y_train_tensor = torch.from_numpy(y_train).to(torch.int64).view(-1, 1)
y_test_tensor = torch.from_numpy(y_test).to(torch.int64).view(-1, 1)
import torch.utils.data as Data
mnist_train = Data.TensorDataset(X_train_tensor, y_train_tensor)
mnist_test = Data.TensorDataset(X_test_tensor, y_test_tensor)
feature, label = mnist_train[0]
X, y = [], []
for i in range(10):
X.append(mnist_train[i][0])
y.append(mnist_test[i][1])
d2l.show_fashion_mnist(X, d2l.get_fashion_mnist_labels(y))
#%%
batch_size = 256
if sys.platform.startswith('win'):
num_workers = 0 #表示不用额外的进程来加速读取数据
else:
num_workers = 4
train_iter = torch.utils.data.DataLoader(mnist_train,
batch_size=batch_size,
shuffle=True,
num_workers=num_workers)
test_iter = torch.utils.data.DataLoader(mnist_test,
batch_size=batch_size,
shuffle=False,
num_workers=num_workers)
#%%
## Define model.
def net(X):
## -1 stands for single dimension
return softmax(torch.mm(X.view((-1, num_inputs)), W))
## Define loss function.
def cross_entropy(y_hat, y):
return -torch.log(y_hat.gather(1, y.view(-1, 1)))
def accuracy(y_hat, y):
return (y_hat.argmax(dim=1) == y).float().mean().item()
num_epoches, lr = 5, 0.1
## Train model.
d2l.train_ch3(net, train_iter, test_iter, cross_entropy, num_epoches,
batch_size, [W, b], lr)
## Eval model.
X, y = iter(test_iter).next()
true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
title = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
d2l.show_fashion_mnist(X[:9], title[:9], 10)
