# 动手学深度学习：softmax完整代码（pytorch + windows+ pycharm）

### 文章目录

• softmax从零开始实现
• softmax简洁实现
• 遇到的问题
• pycharm无法多进程读取数据导致的报错
• pycharm绘图不显示/卡顿
• 无法动态绘制图像
• PermissionError: [WinError 5] 拒绝访问。: '../data'
• 图片自动关闭

# softmax从零开始实现

``````import torch
from d2l import torch as d2l
import matplotlib.pyplot as plt
from torchvision import transforms
import torchvision # 计算机视觉相关库
from torch.utils import data
from IPython import display

"""使用4个进程来读取数据"""
return 4  # 并行

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))
#transforms.Resize：调整PILImage对象的尺寸。transforms.Resize([h, w])或transforms.Resize(x)等比例缩放
trans = transforms.Compose(trans) # 串联多个图片变换的操作
mnist_train = torchvision.datasets.FashionMNIST(
mnist_test = torchvision.datasets.FashionMNIST(
return (data.DataLoader(mnist_train, batch_size, shuffle=True,

# 定义softmax
def softmax(X):
X_exp = torch.exp(X)
return X_exp / X_exp.sum(axis=1, keepdim=True)

def net(X):
return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)

# 交叉熵损失函数
def cross_entropy(y_hat, y):
return -torch.log(y_hat[range(len(y_hat)), y])

# 精度
def accuracy(y_hat, y):
if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
y_hat = y_hat.argmax(axis= 1)
cmp = y_hat == y
return float(cmp.type(y.dtype).sum())

# 为什么不在accuracy中除以len(y)：accuracy函数是一个batch一个batch求的，
# 因为如果样本数不是batch整数倍，
# 最后的batch_size可能与前面不同，所以要求出数量后累计求精度

#
def evaluate_accuracy(net, data_iter):  #@save
if isinstance(net, torch.nn.Module):
net.eval()
metric = Accumulater(2)  # 累加
for X, y in data_iter:
return metric[0]/metric[1]

class Accumulater: #@save
def __init__(self, n):
self.data = [0.0] *n

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]

# 训练一轮
def train_epoch_ch3(net, train_iter, loss, updater):
if isinstance(net, torch.nn.Module):
net.train()
metric = Accumulater(3)
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y)
if isinstance(updater, torch.optim.Optimizer):  # 使用torch内置优化器
l.mean().backward()
updater.step()
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]

# 绘图
class Animator:  #@save
"""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)

plt.pause(0.001)

# 训练全部
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],  # 可视化
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
assert train_loss < 0.7, 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 updater(batch_size):
return d2l.sgd([W, b], lr, batch_size)

# 预测
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])

if __name__=='__main__':
# 初始化模型参数
batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size)

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)

lr = 0.1
num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)
plt.show()

predict_ch3(net, test_iter)
plt.show()

``````

# softmax简洁实现

``````import torch
from torch import nn
from d2l import torch as d2l
import matplotlib.pyplot as plt
from torchvision import transforms
import torchvision # 计算机视觉相关库
from torch.utils import data

"""使用4个进程来读取数据，可以不写"""
return 4  # 并行

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))
#transforms.Resize：调整PILImage对象的尺寸。transforms.Resize([h, w])或transforms.Resize(x)等比例缩放
trans = transforms.Compose(trans) # 串联多个图片变换的操作
mnist_train = torchvision.datasets.FashionMNIST(
mnist_test = torchvision.datasets.FashionMNIST(
return (data.DataLoader(mnist_train, batch_size, shuffle=True,

if __name__=='__main__':
batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size)

# 初始化模型参数
net = nn.Sequential(nn.Flatten(), nn.Linear(784, 10))  # 线性层之前使用展平层调整输入的形状

def init_weights(m):
if type(m) == nn.Linear:
nn.init.normal_(m.weight, std=0.1)
net.apply(init_weights)

# 损失
loss = nn.CrossEntropyLoss(reduction='none')

# 优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.1)

# 训练
num_epoch = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epoch, trainer)
plt.show()

# 预测
d2l.predict_ch3(net, test_iter)
plt.show()

``````

# 遇到的问题

## pycharm无法多进程读取数据导致的报错

1. 使用cmd / Anaconda Prompt运行python文件
2. 将进程数更改为0
``````def get_dataloader_workers():
return 0
``````
1. 将需要运行的内容放入`if __name__=='__main__':`（除定义函数/类之外的内容）

## pycharm绘图不显示/卡顿

``````error: failed to send plot to http://127.0.0.1:63342
``````

1. 解决failed to send plot to http://127.0.0.1:63342
设置 => Python Scientific => 取消勾选在工具窗口中显示绘图
2. [解决未响应]
编辑配置 => 取消勾选使用python控制台运行

## 图片自动关闭

``````plt.show()
``````