Softmax与分类模型
softmax从零开始的实现
import torch
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
print(torchvision.__version__)
获取训练集数据和测试集数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, root='/home/kesci/input/FashionMNIST2065')
模型参数初始化
num_inputs = 784
print(28*28)
num_outputs = 10
W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)), dtype=torch.float)
b = torch.zeros(num_outputs, dtype=torch.float)
784
W.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)
tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], requires_grad=True)
对多维Tensor按维度操作
X = torch.tensor([[1, 2, 3], [4, 5, 6]])
print(X.sum(dim=0, keepdim=True)) # dim为0，按照相同的列求和，并在结果中保留列特征
print(X.sum(dim=1, keepdim=True)) # dim为1，按照相同的行求和，并在结果中保留行特征
print(X.sum(dim=0, keepdim=False)) # dim为0，按照相同的列求和，不在结果中保留列特征
print(X.sum(dim=1, keepdim=False)) # dim为1，按照相同的行求和，不在结果中保留行特征
tensor([[5, 7, 9]])
tensor([[ 6],
[15]])
tensor([5, 7, 9])
tensor([ 6, 15])
定义softmax操作
def softmax(X):
X_exp = X.exp()
partition = X_exp.sum(dim=1, keepdim=True)
# print("X size is ", X_exp.size())
# print("partition size is ", partition, partition.size())
return X_exp / partition # 这里应用了广播机制
X = torch.rand((2, 5))
X_prob = softmax(X)
print(X_prob, '\n', X_prob.sum(dim=1))
tensor([[0.2253, 0.1823, 0.1943, 0.2275, 0.1706],
[0.1588, 0.2409, 0.2310, 0.1670, 0.2024]])
tensor([1.0000, 1.0000])
softmax回归模型
def net(X):
return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)
定义损失函数
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y = torch.LongTensor([0, 2])
y_hat.gather(1, y.view(-1, 1))
tensor([[0.1000],
[0.5000]])
def cross_entropy(y_hat, y):
return - torch.log(y_hat.gather(1, y.view(-1, 1)))
定义准确率
我们模型训练完了进行模型预测的时候，会用到我们这里定义的准确率。
def accuracy(y_hat, y):
return (y_hat.argmax(dim=1) == y).float().mean().item()
print(accuracy(y_hat, y))#0.5
# 本函数已保存在d2lzh_pytorch包中方便以后使用。该函数将被逐步改进：它的完整实现将在“图像增广”一节中描述
def evaluate_accuracy(data_iter, net):
acc_sum, n = 0.0, 0
for X, y in data_iter:
acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
n += y.shape[0]
return acc_sum / n
print(evaluate_accuracy(test_iter, net))#0.1445
训练模型
num_epochs, lr = 5, 0.1
# 本函数已保存在d2lzh_pytorch包中方便以后使用
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params=None, lr=None, optimizer=None):
for epoch in range(num_epochs):
train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y).sum()
# 梯度清零
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)
epoch 1, loss 0.7851, train acc 0.750, test acc 0.791
epoch 2, loss 0.5704, train acc 0.814, test acc 0.810
epoch 3, loss 0.5258, train acc 0.825, test acc 0.819
epoch 4, loss 0.5014, train acc 0.832, test acc 0.824
epoch 5, loss 0.4865, train acc 0.836, test acc 0.827
模型预测
现在我们的模型训练完了，可以进行一下预测，我们的这个模型训练的到底准确不准确。 现在就可以演示如何对图像进行分类了。给定一系列图像（第三行图像输出），我们比较一下它们的真实标签（第一行文本输出）和模型预测结果（第二行文本输出）。
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])
softmax的简洁实现
# 加载各种包或者模块
import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
初始化参数和获取数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, root='/home/kesci/input/FashionMNIST2065')
定义网络模型
num_inputs = 784
num_outputs = 10
class LinearNet(nn.Module):
def __init__(self, num_inputs, num_outputs):
super(LinearNet, self).__init__()
self.linear = nn.Linear(num_inputs, num_outputs)
def forward(self, x): # x 的形状: (batch, 1, 28, 28)
y = self.linear(x.view(x.shape[0], -1))
return y
# net = LinearNet(num_inputs, num_outputs)
class FlattenLayer(nn.Module):
def __init__(self):
super(FlattenLayer, self).__init__()
def forward(self, x): # x 的形状: (batch, *, *, ...)
return x.view(x.shape[0], -1)
from collections import OrderedDict
net = nn.Sequential(
# FlattenLayer(),
# LinearNet(num_inputs, num_outputs)
OrderedDict([
('flatten', FlattenLayer()),
('linear', nn.Linear(num_inputs, num_outputs))]) # 或者写成我们自己定义的 LinearNet(num_inputs, num_outputs) 也可以
)
初始化模型参数
init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)
Parameter containing:
tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], requires_grad=True)
定义损失函数
loss = nn.CrossEntropyLoss() # 下面是他的函数原型
# class torch.nn.CrossEntropyLoss(weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean')
定义优化函数
optimizer = torch.optim.SGD(net.parameters(), lr=0.1) # 下面是函数原型
# class torch.optim.SGD(params, lr=, momentum=0, dampening=0, weight_decay=0, nesterov=False)
训练
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)
epoch 1, loss 0.0031, train acc 0.751, test acc 0.795
epoch 2, loss 0.0022, train acc 0.813, test acc 0.809
epoch 3, loss 0.0021, train acc 0.825, test acc 0.806
epoch 4, loss 0.0020, train acc 0.833, test acc 0.813
epoch 5, loss 0.0019, train acc 0.837, test acc 0.822
