目录
5.3 基于LeNet实现手写体数字识别实验
5.3.1 MNIST数据集
5.3.1.1 数据预处理
5.3.2 模型构建
5.3.5 模型预测
5.3.4 模型评价
5.3.5 模型预测
选做
使用前馈神经网络实现MNIST识别,与LeNet效果对比。
总结
参考:
在本节中,我们实现经典卷积网络LeNet-5,并进行手写体数字识别任务。
手写体数字识别是计算机视觉中最常用的图像分类任务,让计算机识别出给定图片中的手写体数字(0-9共10个数字)。由于手写体风格差异很大,因此手写体数字识别是具有一定难度的任务。
我们采用常用的手写数字识别数据集:MNIST数据集。MNIST数据集是计算机视觉领域的经典入门数据集,包含了60,000个训练样本和10,000个测试样本。这些数字已经过尺寸标准化并位于图像中心,图像是固定大小(28 × 28 像素)。下图给出了部分样本的示例。
为了节省训练时间,本节选取MNIST数据集的一个子集进行后续实验,数据集的划分为:
MNIST数据集分为train_set、dev_set和test_set三个数据集,每个数据集含两个列表分别存放了图片数据以及标签数据。比如train_set包含:
观察数据集分布情况,代码实现如下:
import json
import gzip
# 打印并观察数据集分布情况
train_set, dev_set, test_set = json.load(gzip.open('./mnist.json.gz'))
train_images, train_labels = train_set[0][:1000], train_set[1][:1000]
dev_images, dev_labels = dev_set[0][:200], dev_set[1][:200]
test_images, test_labels = test_set[0][:200], test_set[1][:200]
train_set, dev_set, test_set = [train_images, train_labels], [dev_images, dev_labels], [test_images, test_labels]
print('Length of train/dev/test set:{}/{}/{}'.format(len(train_set[0]), len(dev_set[0]), len(test_set[0])))
运行结果:
Length of train/dev/test set:1000/200/200
可视化观察其中的一张样本以及对应的标签,这里我选的是索引值为9的照片,真实值为4,代码如下所示:
import numpy as np
import matplotlib.pyplot as plt
import PIL.Image as Image
img, label = train_set[0][9], train_set[1][9]
img, label = np.array(img).astype('float32'), int(label)
# 原始图像数据为长度784的行向量,需要调整为[28,28]大小的图像
img = np.reshape(img, [28, 28])
img = Image.fromarray(img.astype('uint8'), mode='L')
print("The number in the picture is {}".format(label))
plt.figure(figsize=(5, 5))
plt.imshow(img)
plt.show()
plt.savefig('conv-number4.pdf')
运行结果:
图像分类网络对输入图片的格式、大小有一定的要求,数据输入模型前,需要对数据进行预处理操作,使图片满足网络训练以及预测的需要。本实验主要应用了如下方法:
调整图片大小:LeNet网络对输入图片大小的要求为 32 × 32 ,而MNIST数据集中的原始图片大小却是 28 × 28 ,这里为了符合网络的结构设计,将其调整为32 × 32;
规范化: 通过规范化手段,把输入图像的分布改变成均值为0,标准差为1的标准正态分布,使得最优解的寻优过程明显会变得平缓,训练过程更容易收敛。
代码实现如下:
import torchvision.transforms as transforms
# 数据预处理
transforms = transforms.Compose(
[transforms.Resize(32), transforms.ToTensor(), transforms.Normalize(mean=[0.5], std=[0.5])])
from torch.utils.data import Dataset
class MNIST_dataset(Dataset):
def __init__(self, dataset, transforms, mode='train'):
self.mode = mode
self.transforms = transforms
self.dataset = dataset
def __getitem__(self, idx):
# 获取图像和标签
image, label = self.dataset[0][idx], self.dataset[1][idx]
image, label = np.array(image).astype('float32'), int(label)
image = np.reshape(image, [28, 28])
image = Image.fromarray(np.unit8(image), mode='L')
image = self.transforms(image)
return image, label
def __len__(self):
return len(self.dataset[0])
# 加载 mnist 数据集
train_dataset = MNIST_dataset(dataset=train_set, transforms=transforms, mode='train')
test_dataset = MNIST_dataset(dataset=test_set, transforms=transforms, mode='test')
dev_dataset = MNIST_dataset(dataset=dev_set, transforms=transforms, mode='dev')
LeNet-5虽然提出的时间比较早,但它是一个非常成功的神经网络模型。基于LeNet-5的手写数字识别系统在20世纪90年代被美国很多银行使用,用来识别支票上面的手写数字。LeNet-5的网络结构如下图所示。
这里的LeNet-5和原始版本有4点不同:
网络共有7层,包含3个卷积层、2个汇聚层以及2个全连接层的简单卷积神经网络接,受输入图像大小为32 × 32 = 1024,输出对应10个类别的得分。具体实现如下:
import torch.nn.functional as F
import torch.nn as nn
class Model_LeNet(nn.Module):
def __init__(self, in_channels, num_classes=10):
super(Model_LeNet, self).__init__()
# 卷积层:输出通道数为6,卷积核大小为5×5
self.conv1 = nn.Conv2d(in_channels=in_channels, out_channels=6, kernel_size=5)
# 汇聚层:汇聚窗口为2×2,步长为2
self.pool2 = nn.MaxPool2d(kernel_size=(2, 2), stride=2)
# 卷积层:输入通道数为6,输出通道数为16,卷积核大小为5×5,步长为1
self.conv3 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5, stride=1)
# 汇聚层:汇聚窗口为2×2,步长为2
self.pool4 = nn.AvgPool2d(kernel_size=(2, 2), stride=2)
# 卷积层:输入通道数为16,输出通道数为120,卷积核大小为5×5
self.conv5 = nn.Conv2d(in_channels=16, out_channels=120, kernel_size=5, stride=1)
# 全连接层:输入神经元为120,输出神经元为84
self.linear6 = nn.Linear(120, 84)
# 全连接层:输入神经元为84,输出神经元为类别数
self.linear7 = nn.Linear(84, num_classes)
def forward(self, x):
# C1:卷积层+激活函数
output = F.relu(self.conv1(x))
# S2:汇聚层
output = self.pool2(output)
# C3:卷积层+激活函数
output = F.relu(self.conv3(output))
# S4:汇聚层
output = self.pool4(output)
# C5:卷积层+激活函数
output = F.relu(self.conv5(output))
# 输入层将数据拉平[B,C,H,W] -> [B,CxHxW]
output = torch.squeeze(output, dim=3)
output = torch.squeeze(output, dim=2)
# F6:全连接层
output = F.relu(self.linear6(output))
# F7:全连接层
output = self.linear7(output)
return output
下面测试一下上面的LeNet-5模型,构造一个形状为 [1,1,32,32]的输入数据送入网络,观察每一层特征图的形状变化。代码实现如下:
class Torch_LeNet(nn.Module):
def __init__(self, in_channels, num_classes=10):
super(Torch_LeNet, self).__init__()
# 卷积层:输出通道数为6,卷积核大小为5*5
self.conv1 = nn.Conv2d(in_channels=in_channels, out_channels=6, kernel_size=5)
# 汇聚层:汇聚窗口为2*2,步长为2
self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
# 卷积层:输入通道数为6,输出通道数为16,卷积核大小为5*5
self.conv3 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5)
# 汇聚层:汇聚窗口为2*2,步长为2
self.pool4 = nn.AvgPool2d(kernel_size=2, stride=2)
# 卷积层:输入通道数为16,输出通道数为120,卷积核大小为5*5
self.conv5 = nn.Conv2d(in_channels=16, out_channels=120, kernel_size=5)
# 全连接层:输入神经元为120,输出神经元为84
self.linear6 = nn.Linear(in_features=120, out_features=84)
# 全连接层:输入神经元为84,输出神经元为类别数
self.linear7 = nn.Linear(in_features=84, out_features=num_classes)
def forward(self, x):
# C1:卷积层+激活函数
output = F.relu(self.conv1(x))
# S2:汇聚层
output = self.pool2(output)
# C3:卷积层+激活函数
output = F.relu(self.conv3(output))
# S4:汇聚层
output = self.pool4(output)
# C5:卷积层+激活函数
output = F.relu(self.conv5(output))
# 输入层将数据拉平[B,C,H,W] -> [B,CxHxW]
output = torch.squeeze(output, dim=3)
output = torch.squeeze(output, dim=2)
# F6:全连接层
output = F.relu(self.linear6(output))
# F7:全连接层
output = self.linear7(output)
return output
下面测试一下上面的LeNet-5模型,构造一个形状为 [1,1,32,32]的输入数据送入网络,观察每一层特征图的形状变化。代码实现如下:
# 这里用np.random创建一个随机数组作为输入数据
inputs = np.random.randn(*[1, 1, 32, 32])
inputs = inputs.astype('float32')
# 创建Model_LeNet类的实例,指定模型名称和分类的类别数目
model = Model_LeNet(in_channels=1, num_classes=10)
print(model)
# 通过调用LeNet从基类继承的sublayers()函数,查看LeNet中所包含的子层
print(model.named_parameters())
x = torch.tensor(inputs)
print(x)
for item in model.children():
# item是LeNet类中的一个子层
# 查看经过子层之后的输出数据形状
item_shapex = 0
names = []
parameter = []
for name in item.named_parameters():
names.append(name[0])
parameter.append(name[1])
item_shapex += 1
try:
x = item(x)
except:
# 如果是最后一个卷积层输出,需要展平后才可以送入全连接层
x = x.reshape([x.shape[0], -1])
x = item(x)
if item_shapex == 2:
# 查看卷积和全连接层的数据和参数的形状,
# 其中item.parameters()[0]是权重参数w,item.parameters()[1]是偏置参数b
print(item, x.shape, parameter[0].shape, parameter[1].shape)
else:
# 汇聚层没有参数
print(item, x.shape)
运行结果:
Length of train/dev/test set:1000/200/200
The number in the picture is 3
Model_LeNet(
(conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))
(pool2): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
(conv3): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
(pool4): AvgPool2d(kernel_size=(2, 2), stride=2, padding=0)
(conv5): Conv2d(16, 120, kernel_size=(5, 5), stride=(1, 1))
(linear6): Linear(in_features=120, out_features=84, bias=True)
(linear7): Linear(in_features=84, out_features=10, bias=True)
)
tensor([[[[ 2.2872e+00, 2.5909e-01, -7.3315e-01, ..., 9.8182e-01,
-5.6555e-01, -1.3480e+00],
[-1.0333e+00, -4.0936e-01, 2.1097e-01, ..., 6.3379e-01,
1.2221e+00, 1.2943e+00],
[-1.9701e-01, 5.3759e-01, 9.5780e-02, ..., -3.2455e-01,
-1.4870e+00, 6.3696e-01],
...,
[-9.7722e-01, 1.2465e+00, 3.1143e-02, ..., 9.2502e-01,
-1.0147e+00, 1.3323e+00],
[-1.5388e+00, -3.0364e+00, 1.1936e+00, ..., 4.0109e-01,
-4.0882e-01, 8.4390e-01],
[-2.3155e-01, -6.5325e-01, -4.3401e-01, ..., 1.7663e+00,
2.6898e+00, -2.6486e-03]]]])
Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1)) torch.Size([1, 6, 28, 28]) torch.Size([6, 1, 5, 5]) torch.Size([6])
MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False) torch.Size([1, 6, 14, 14])
Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1)) torch.Size([1, 16, 10, 10]) torch.Size([16, 6, 5, 5]) torch.Size([16])
AvgPool2d(kernel_size=(2, 2), stride=2, padding=0) torch.Size([1, 16, 5, 5])
Conv2d(16, 120, kernel_size=(5, 5), stride=(1, 1)) torch.Size([1, 120, 1, 1]) torch.Size([120, 16, 5, 5]) torch.Size([120])
Linear(in_features=120, out_features=84, bias=True) torch.Size([1, 84]) torch.Size([84, 120]) torch.Size([84])
Linear(in_features=84, out_features=10, bias=True) torch.Size([1, 10]) torch.Size([10, 84]) torch.Size([10])
从输出结果看,
考虑到自定义的Conv2D和Pool2D算子中包含多个for循环,所以运算速度比较慢。pytorch中,针对卷积层算子和汇聚层算子进行了速度上的优化,这里基于torch.nn.Conv2d();torch.nn.MaxPool2d();torch.nn.avg_pool2d()构建LeNet-5模型,对比与上边实现的模型的运算速度。代码实现如下:
class Torch_LeNet(nn.Module):
def __init__(self, in_channels, num_classes=10):
super(Torch_LeNet, self).__init__()
# 卷积层:输出通道数为6,卷积核大小为5*5
self.conv1 = nn.Conv2d(in_channels=in_channels, out_channels=6, kernel_size=5)
# 汇聚层:汇聚窗口为2*2,步长为2
self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
# 卷积层:输入通道数为6,输出通道数为16,卷积核大小为5*5
self.conv3 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5)
# 汇聚层:汇聚窗口为2*2,步长为2
self.pool4 = nn.AvgPool2d(kernel_size=2, stride=2)
# 卷积层:输入通道数为16,输出通道数为120,卷积核大小为5*5
self.conv5 = nn.Conv2d(in_channels=16, out_channels=120, kernel_size=5)
# 全连接层:输入神经元为120,输出神经元为84
self.linear6 = nn.Linear(in_features=120, out_features=84)
# 全连接层:输入神经元为84,输出神经元为类别数
self.linear7 = nn.Linear(in_features=84, out_features=num_classes)
def forward(self, x):
# C1:卷积层+激活函数
output = F.relu(self.conv1(x))
# S2:汇聚层
output = self.pool2(output)
# C3:卷积层+激活函数
output = F.relu(self.conv3(output))
# S4:汇聚层
output = self.pool4(output)
# C5:卷积层+激活函数
output = F.relu(self.conv5(output))
# 输入层将数据拉平[B,C,H,W] -> [B,CxHxW]
output = torch.squeeze(output, dim=3)
output = torch.squeeze(output, dim=2)
# F6:全连接层
output = F.relu(self.linear6(output))
# F7:全连接层
output = self.linear7(output)
return output
测试两个网络的运算速度。
import time
# 这里用np.random创建一个随机数组作为测试数据
inputs = np.random.randn(*[1,1,32,32])
inputs = inputs.astype('float32')
x = torch.tensor(inputs)
# 创建Model_LeNet类的实例,指定模型名称和分类的类别数目
model = Model_LeNet(in_channels=1, num_classes=10)
# 创建Torch_LeNet类的实例,指定模型名称和分类的类别数目
torch_model = Torch_LeNet(in_channels=1, num_classes=10)
# 计算Model_LeNet类的运算速度
model_time = 0
for i in range(60):
strat_time = time.time()
out = model(x)
end_time = time.time()
# 预热10次运算,不计入最终速度统计
if i < 10:
continue
model_time += (end_time - strat_time)
avg_model_time = model_time / 50
print('Model_LeNet speed:', avg_model_time, 's')
# 计算Torch_LeNet类的运算速度
torch_model_time = 0
for i in range(60):
strat_time = time.time()
torch_out = torch_model(x)
end_time = time.time()
# 预热10次运算,不计入最终速度统计
if i < 10:
continue
torch_model_time += (end_time - strat_time)
avg_torch_model_time = torch_model_time / 50
print('Torch_LeNet speed:', avg_torch_model_time, 's')
运行结果
Model_LeNet speed: 0.0003124380111694336 s
Torch_LeNet speed: 0.0003123950958251953 s
这里还可以令两个网络加载同样的权重,测试一下两个网络的输出结果是否一致。
# 这里用np.random创建一个随机数组作为测试数据
inputs = np.random.randn(*[1,1,32,32])
inputs = inputs.astype('float32')
x = torch.tensor(inputs)
# 创建Model_LeNet类的实例,指定模型名称和分类的类别数目
model = Model_LeNet(in_channels=1, num_classes=10)
# 获取网络的权重
params = model.state_dict()
# 自定义Conv2D算子的bias参数形状为[out_channels, 1]
# torch API中Conv2D算子的bias参数形状为[out_channels]
# 需要进行调整后才可以赋值
for key in params:
if 'bias' in key:
params[key] = params[key].squeeze()
# 创建Torch_LeNet类的实例,指定模型名称和分类的类别数目
torch_model = Torch_LeNet(in_channels=1, num_classes=10)
# 将Model_LeNet的权重参数赋予给Torch_LeNet模型,保持两者一致
torch_model.load_state_dict(params)
# 打印结果保留小数点后6位
torch.set_printoptions(6)
# 计算Model_LeNet的结果
output = model(x)
print('Model_LeNet output: ', output)
# 计算Torch_LeNet的结果
torch_output = torch_model(x)
print('Torch_LeNet output: ', torch_output)
运行结果
Model_LeNet output: tensor([[-0.026712, 0.084623, 0.079348, -0.104063, 0.099383, 0.110550,0.055438, -0.022714, 0.066782, -0.001770]],grad_fn=
) Torch_LeNet output: tensor([[-0.026712, 0.084623, 0.079348, -0.104063, 0.099383, 0.110550,0.055438, -0.022714, 0.066782, -0.001770]],grad_fn=
)
可以看到,输出结果是一致的。
这里还可以统计一下LeNet-5模型的参数量和计算量。
参数量
按照公式(5.18)进行计算,可以得到:
所以,LeNet-5总的参数量为6170661706。
在pytorch中,还可以使用torchsummaryAPI自动计算参数量。
from torchsummary import summary
model = Torch_LeNet(in_channels=1, num_classes=10)
params_info = summary(model, (1, 32, 32))
print(params_info)
运行结果
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 6, 28, 28] 156
MaxPool2d-2 [-1, 6, 14, 14] 0
Conv2d-3 [-1, 16, 10, 10] 2,416
AvgPool2d-4 [-1, 16, 5, 5] 0
Conv2d-5 [-1, 120, 1, 1] 48,120
Linear-6 [-1, 84] 10,164
Linear-7 [-1, 10] 850
================================================================
Total params: 61,706
Trainable params: 61,706
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.00
Forward/backward pass size (MB): 0.06
Params size (MB): 0.24
Estimated Total Size (MB): 0.30
----------------------------------------------------------------
None
可以看到,结果与公推导一致。
计算量
按照公式(5.19)进行计算,可以得到:
所以,LeNet-5总的计算量为423344。
在torch中,还可以使用torchstatAPI自动统计计算量。
使用交叉熵损失函数,并用随机梯度下降法作为优化器来训练LeNet-5网络。
用RunnerV3在训练集上训练5个epoch,并保存准确率最高的模型作为最佳模型。
class RunnerV3(object):
def __init__(self, model, optimizer, loss_fn, metric, **kwargs):
self.model = model
self.optimizer = optimizer
self.loss_fn = loss_fn
self.metric = metric # 只用于计算评价指标
# 记录训练过程中的评价指标变化情况
self.dev_scores = []
# 记录训练过程中的损失函数变化情况
self.train_epoch_losses = [] # 一个epoch记录一次loss
self.train_step_losses = [] # 一个step记录一次loss
self.dev_losses = []
# 记录全局最优指标
self.best_score = 0
def train(self, train_loader, dev_loader=None, **kwargs):
# 将模型切换为训练模式
self.model.train()
# 传入训练轮数,如果没有传入值则默认为0
num_epochs = kwargs.get("num_epochs", 0)
# 传入log打印频率,如果没有传入值则默认为100
log_steps = kwargs.get("log_steps", 100)
# 评价频率
eval_steps = kwargs.get("eval_steps", 0)
# 传入模型保存路径,如果没有传入值则默认为"best_model.pdparams"
save_path = kwargs.get("save_path", "best_model.pdparams")
custom_print_log = kwargs.get("custom_print_log", None)
# 训练总的步数
num_training_steps = num_epochs * len(train_loader)
if eval_steps:
if self.metric is None:
raise RuntimeError('Error: Metric can not be None!')
if dev_loader is None:
raise RuntimeError('Error: dev_loader can not be None!')
# 运行的step数目
global_step = 0
# 进行num_epochs轮训练
for epoch in range(num_epochs):
# 用于统计训练集的损失
total_loss = 0
for step, data in enumerate(train_loader):
X, y = data
# 获取模型预测
logits = self.model(X)
loss = self.loss_fn(logits, y) # 默认求mean
total_loss += loss
# 训练过程中,每个step的loss进行保存
self.train_step_losses.append((global_step, loss.item()))
if log_steps and global_step % log_steps == 0:
print(
f"[Train] epoch: {epoch}/{num_epochs}, step: {global_step}/{num_training_steps}, loss: {loss.item():.5f}")
# 梯度反向传播,计算每个参数的梯度值
loss.backward()
if custom_print_log:
custom_print_log(self)
# 小批量梯度下降进行参数更新
self.optimizer.step()
# 梯度归零
optimizer.zero_grad()
# 判断是否需要评价
if eval_steps > 0 and global_step > 0 and \
(global_step % eval_steps == 0 or global_step == (num_training_steps - 1)):
dev_score, dev_loss = self.evaluate(dev_loader, global_step=global_step)
print(f"[Evaluate] dev score: {dev_score:.5f}, dev loss: {dev_loss:.5f}")
# 将模型切换为训练模式
self.model.train()
# 如果当前指标为最优指标,保存该模型
if dev_score > self.best_score:
self.save_model(save_path)
print(
f"[Evaluate] best accuracy performence has been updated: {self.best_score:.5f} --> {dev_score:.5f}")
self.best_score = dev_score
global_step += 1
# 当前epoch 训练loss累计值
trn_loss = (total_loss / len(train_loader)).item()
# epoch粒度的训练loss保存
self.train_epoch_losses.append(trn_loss)
print("[Train] Training done!")
# 模型评估阶段,使用'paddle.no_grad()'控制不计算和存储梯度
@torch.no_grad()
def evaluate(self, dev_loader, **kwargs):
assert self.metric is not None
# 将模型设置为评估模式
self.model.eval()
global_step = kwargs.get("global_step", -1)
# 用于统计训练集的损失
total_loss = 0
# 重置评价
self.metric.reset()
# 遍历验证集每个批次
for batch_id, data in enumerate(dev_loader):
X, y = data
# 计算模型输出
logits = self.model(X)
# 计算损失函数
loss = self.loss_fn(logits, y).item()
# 累积损失
total_loss += loss
# 累积评价
self.metric.update(logits, y)
dev_loss = (total_loss / len(dev_loader))
dev_score = self.metric.accumulate()
# 记录验证集loss
if global_step != -1:
self.dev_losses.append((global_step, dev_loss))
self.dev_scores.append(dev_score)
return dev_score, dev_loss
# 模型评估阶段,使用'paddle.no_grad()'控制不计算和存储梯度
@torch.no_grad()
def predict(self, x, **kwargs):
# 将模型设置为评估模式
self.model.eval()
# 运行模型前向计算,得到预测值
logits = self.model(x)
return logits
def save_model(self, save_path):
torch.save(self.model.state_dict(), save_path)
def load_model(self, model_path):
state_dict = torch.load(model_path)
self.model.load_state_dict(state_dict)
import torch
#新增准确率计算函数
def accuracy(preds, labels):
"""
输入:
- preds:预测值,二分类时,shape=[N, 1],N为样本数量,多分类时,shape=[N, C],C为类别数量
- labels:真实标签,shape=[N, 1]
输出:
- 准确率:shape=[1]
"""
print(preds)
# 判断是二分类任务还是多分类任务,preds.shape[1]=1时为二分类任务,preds.shape[1]>1时为多分类任务
if preds.shape[1] == 1:
# 二分类时,判断每个概率值是否大于0.5,当大于0.5时,类别为1,否则类别为0
# 使用'torch.can_cast'将preds的数据类型转换为float32类型
preds = torch.can_cast((preds>=0.5).dtype,to=torch.float32)
else:
# 多分类时,使用'torch.argmax'计算最大元素索引作为类别
preds = torch.argmax(preds,dim=1)
torch.can_cast(preds.dtype,torch.int32)
return torch.mean(torch.tensor((preds == labels), dtype=torch.float32))
class Accuracy():
def __init__(self):
"""
输入:
- is_logist: outputs是logist还是激活后的值
"""
# 用于统计正确的样本个数
self.num_correct = 0
# 用于统计样本的总数
self.num_count = 0
self.is_logist = True
def update(self, outputs, labels):
"""
输入:
- outputs: 预测值, shape=[N,class_num]
- labels: 标签值, shape=[N,1]
"""
# 判断是二分类任务还是多分类任务,shape[1]=1时为二分类任务,shape[1]>1时为多分类任务
if outputs.shape[1] == 1: # 二分类
outputs = torch.squeeze(outputs, axis=-1)
if self.is_logist:
# logist判断是否大于0
preds = torch.can_cast((outputs>=0), dtype=torch.float32)
else:
# 如果不是logist,判断每个概率值是否大于0.5,当大于0.5时,类别为1,否则类别为0
preds = torch.can_cast((outputs>=0.5), dtype=torch.float32)
else:
# 多分类时,使用'paddle.argmax'计算最大元素索引作为类别
preds = torch.argmax(outputs, dim=1).int()
# 获取本批数据中预测正确的样本个数
labels = torch.squeeze(labels, dim=-1)
batch_correct = torch.sum((preds == labels).clone().detach()).numpy()
batch_count = len(labels)
# 更新num_correct 和 num_count
self.num_correct += batch_correct
self.num_count += batch_count
def accumulate(self):
# 使用累计的数据,计算总的指标
if self.num_count == 0:
return 0
return self.num_correct / self.num_count
def reset(self):
# 重置正确的数目和总数
self.num_correct = 0
self.num_count = 0
def name(self):
return "Accuracy"
import torch.optim as opti
from torch.utils.data import DataLoader
torch.manual_seed(100)
# 学习率大小
lr = 0.1
# 批次大小
batch_size = 64
# 加载数据
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
dev_loader = DataLoader(dev_dataset, batch_size=batch_size)
test_loader = DataLoader(test_dataset, batch_size=batch_size)
model = Model_LeNet(in_channels=1, num_classes=10)
optimizer = opti.SGD(model.parameters(), 0.2)
# 定义损失函数
loss_fn = F.cross_entropy
# 定义评价指标
metric = Accuracy()
# 实例化 RunnerV3 类,并传入训练配置。
runner = RunnerV3(model, optimizer, loss_fn, metric)
# 启动训练
log_steps = 15
eval_steps = 15
runner.train(train_loader, dev_loader, num_epochs=6, log_steps=log_steps,
eval_steps=eval_steps, save_path="best_model.pdparams")
运行结果
[Train] epoch: 0/6, step: 0/96, loss: 2.31005
[Train] epoch: 0/6, step: 15/96, loss: 2.30053
[Evaluate] dev score: 0.10000, dev loss: 2.29804
[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.10000
[Train] epoch: 1/6, step: 30/96, loss: 2.19406
[Evaluate] dev score: 0.20000, dev loss: 2.22632
[Evaluate] best accuracy performence has been updated: 0.10000 --> 0.20000
[Train] epoch: 2/6, step: 45/96, loss: 1.90754
[Evaluate] dev score: 0.20500, dev loss: 2.09735
[Evaluate] best accuracy performence has been updated: 0.20000 --> 0.20500
[Train] epoch: 3/6, step: 60/96, loss: 1.39710
[Evaluate] dev score: 0.54500, dev loss: 1.20112
[Evaluate] best accuracy performence has been updated: 0.20500 --> 0.54500
[Train] epoch: 4/6, step: 75/96, loss: 1.01853
[Evaluate] dev score: 0.66000, dev loss: 0.91668
[Evaluate] best accuracy performence has been updated: 0.54500 --> 0.66000
[Train] epoch: 5/6, step: 90/96, loss: 0.72001
[Evaluate] dev score: 0.69000, dev loss: 0.89194
[Evaluate] best accuracy performence has been updated: 0.66000 --> 0.69000
[Evaluate] dev score: 0.55500, dev loss: 1.11665
[Train] Training done!
可视化观察训练集与验证集的损失变化情况。
# 可视化误差
def plot(runner, fig_name):
plt.figure(figsize=(10, 5))
plt.subplot(1, 2, 1)
train_items = runner.train_step_losses[::30]
train_steps = [x[0] for x in train_items]
train_losses = [x[1] for x in train_items]
plt.plot(train_steps, train_losses, color='#8E004D', label="Train loss")
if runner.dev_losses[0][0] != -1:
dev_steps = [x[0] for x in runner.dev_losses]
dev_losses = [x[1] for x in runner.dev_losses]
plt.plot(dev_steps, dev_losses, color='#E20079', linestyle='--', label="Dev loss")
# 绘制坐标轴和图例
plt.ylabel("loss", fontsize='x-large')
plt.xlabel("step", fontsize='x-large')
plt.legend(loc='upper right', fontsize='x-large')
plt.subplot(1, 2, 2)
# 绘制评价准确率变化曲线
if runner.dev_losses[0][0] != -1:
plt.plot(dev_steps, runner.dev_scores,
color='#E20079', linestyle="--", label="Dev accuracy")
else:
plt.plot(list(range(len(runner.dev_scores))), runner.dev_scores,
color='#E20079', linestyle="--", label="Dev accuracy")
# 绘制坐标轴和图例
plt.ylabel("score", fontsize='x-large')
plt.xlabel("step", fontsize='x-large')
plt.legend(loc='lower right', fontsize='x-large')
plt.savefig(fig_name)
plt.show()
runner.load_model('best_model.pdparams')
plot(runner, 'cnn-loss1.pdf')
运行结果
使用测试数据对在训练过程中保存的最佳模型进行评价,观察模型在测试集上的准确率以及损失变化情况。
# 加载最优模型
runner.load_model('best_model.pdparams')
# 模型评价
score, loss = runner.evaluate(test_loader)
print("[Test] accuracy/loss: {:.4f}/{:.4f}".format(score, loss))
运行结果
[Test] accuracy/loss: 0.8000/0.5851
同样地,我们也可以使用保存好的模型,对测试集中的某一个数据进行模型预测,我选择的是数据集中索引为10的数字1,观察模型效果。
# 获取测试集中第一条数
X, label = next(iter(test_loader))
logits = runner.predict(X)
# 多分类,使用softmax计算预测概率
pred = F.softmax(logits,dim=1)
print(pred.shape)
# 获取概率最大的类别
pred_class = torch.argmax(pred[2]).numpy()
print(pred_class)
label = label[2].numpy()
# 输出真实类别与预测类别
print("The true category is {} and the predicted category is {}".format(label, pred_class))
# 可视化图片
plt.figure(figsize=(2, 2))
image, label = test_set[0][10], test_set[1][10]
image= np.array(image).astype('float32')
image = np.reshape(image, [28, 28])
image = Image.fromarray(image.astype('uint8'), mode='L')
plt.imshow(image)
plt.savefig('cnn-number1.pdf')
运行结果
torch.Size([64, 10])
1
The true category is 1 and the predicted category is 1
代码
import torch
import torch.nn as nn
from matplotlib import pyplot as plt
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets
batch_size = 64
lr = 0.01
momentum = 0.5
epoch = 5
# 归一化
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
# train=True训练集,=False测试集
train_dataset = datasets.MNIST(root='./pythonProject/mnist', train=True, transform=transform, download=True)
test_dataset = datasets.MNIST(root='./pythonProject/mnist', train=False, transform=transform, download=True)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
fig = plt.figure()
for i in range(12):
plt.subplot(3, 4, i + 1)
plt.tight_layout()
plt.imshow(train_dataset.train_data[i], cmap='gray', interpolation='none')
plt.title("Labels: {}".format(train_dataset.train_labels[i]))
plt.xticks([])
plt.yticks([])
plt.show()
# 定义前馈神经网络
class Model_MLP_L2_V3(nn.Module):
def __init__(self):
super(Model_MLP_L2_V3, self).__init__()
self.conv1 = torch.nn.Sequential(torch.nn.Conv2d(1, 10, kernel_size=(5, 5)), torch.nn.ReLU(),
torch.nn.MaxPool2d(kernel_size=2))
self.conv2 = torch.nn.Sequential(torch.nn.Conv2d(10, 20, kernel_size=(5, 5)), torch.nn.ReLU(),
torch.nn.MaxPool2d(kernel_size=2))
self.fc = torch.nn.Sequential(torch.nn.Linear(320, 50), torch.nn.Linear(50, 10))
def forward(self, x):
batch_size = x.size(0)
x = self.conv1(x) # 一层卷积层,一层池化层,一层激活层
x = self.conv2(x)
x = x.view(batch_size, -1) # flatten变成全连接网络需要的输入(batch, 20,4,4)==>(batch,320),-1此处自动算出的是320
x = self.fc(x)
return x
model = Model_MLP_L2_V3()
# 设置损失函数和优化器
criterion = torch.nn.CrossEntropyLoss() # 交叉熵损失
optimizer = torch.optim.SGD(model.parameters(), lr=lr, momentum=momentum)
def train(epoch):
running_loss = 0.0 # 这整个epoch的loss清零
running_total = 0
running_correct = 0
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data
optimizer.zero_grad()
# forward + backward + update
outputs = model(inputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
# 把运行中的loss累加起来,为了下面300次一除
running_loss += loss.item()
# 把运行中的准确率acc算出来
_, predicted = torch.max(outputs.data, dim=1)
running_total += inputs.shape[0]
running_correct += (predicted == target).sum().item()
if batch_idx % 100 == 99:
print('[%d, %5d]: loss: %.3f , acc: %.2f %%' % (
epoch + 1, batch_idx + 1, running_loss / 300, 100 * running_correct / running_total))
running_loss = 0.0 # 该批次loss清零
running_total = 0
running_correct = 0 # 该批次acc清零
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images, labels = data
outputs = model(images)
_, predicted = torch.max(outputs.data, dim=1) # dim=1 列是第0个维度,行是第1个维度,沿着行(第1个维度)去找1.最大值和2.最大值的下标
total += labels.size(0) # 张量之间的比较运算
correct += (predicted == labels).sum().item()
accuracy = correct / total # 测试准确率=正确数/总数
print('[%d]: Accuracy on test set: %.1f %% ' % (epoch + 1, 100 * accuracy))
return accuracy
# 主函数
if __name__ == '__main__':
acc_list_test = []
for epoch in range(epoch):
train(epoch)
acc_test = test()
acc_list_test.append(acc_test)
plt.plot(acc_list_test)
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.show()
运行结果
[1, 100]: loss: 0.528 , acc: 52.45 %
[1, 200]: loss: 0.154 , acc: 86.17 %
[1, 300]: loss: 0.111 , acc: 90.19 %
[1, 400]: loss: 0.090 , acc: 91.98 %
[1, 500]: loss: 0.076 , acc: 93.41 %
[1, 600]: loss: 0.066 , acc: 93.95 %
[1, 700]: loss: 0.054 , acc: 95.09 %
[1, 800]: loss: 0.049 , acc: 95.27 %
[1, 900]: loss: 0.047 , acc: 95.75 %
[1]: Accuracy on test set: 96.7 %
[2, 100]: loss: 0.045 , acc: 96.16 %
[2, 200]: loss: 0.040 , acc: 96.17 %
[2, 300]: loss: 0.039 , acc: 96.44 %
[2, 400]: loss: 0.036 , acc: 96.53 %
[2, 500]: loss: 0.034 , acc: 96.81 %
[2, 600]: loss: 0.033 , acc: 96.98 %
[2, 700]: loss: 0.034 , acc: 96.92 %
[2, 800]: loss: 0.031 , acc: 97.30 %
[2, 900]: loss: 0.032 , acc: 97.09 %
[2]: Accuracy on test set: 97.7 %
[3, 100]: loss: 0.028 , acc: 97.52 %
[3, 200]: loss: 0.028 , acc: 97.48 %
[3, 300]: loss: 0.027 , acc: 97.47 %
[3, 400]: loss: 0.031 , acc: 97.02 %
[3, 500]: loss: 0.025 , acc: 97.44 %
[3, 600]: loss: 0.028 , acc: 97.61 %
[3, 700]: loss: 0.027 , acc: 97.80 %
[3, 800]: loss: 0.026 , acc: 97.58 %
[3, 900]: loss: 0.021 , acc: 98.02 %
[3]: Accuracy on test set: 98.1 %
[4, 100]: loss: 0.024 , acc: 97.86 %
[4, 200]: loss: 0.027 , acc: 97.70 %
[4, 300]: loss: 0.021 , acc: 97.97 %
[4, 400]: loss: 0.021 , acc: 98.03 %
[4, 500]: loss: 0.025 , acc: 97.92 %
[4, 600]: loss: 0.020 , acc: 98.12 %
[4, 700]: loss: 0.021 , acc: 97.91 %
[4, 800]: loss: 0.023 , acc: 97.84 %
[4, 900]: loss: 0.020 , acc: 98.22 %
[4]: Accuracy on test set: 98.4 %
[5, 100]: loss: 0.020 , acc: 98.19 %
[5, 200]: loss: 0.022 , acc: 98.05 %
[5, 300]: loss: 0.020 , acc: 98.06 %
[5, 400]: loss: 0.018 , acc: 98.20 %
[5, 500]: loss: 0.023 , acc: 97.98 %
[5, 600]: loss: 0.019 , acc: 98.16 %
[5, 700]: loss: 0.018 , acc: 98.42 %
[5, 800]: loss: 0.020 , acc: 98.05 %
[5, 900]: loss: 0.018 , acc: 98.27 %
[5]: Accuracy on test set: 98.5 %
前馈神经网络和LeNet相比前者开始准确率高而后者开始准确率低,但与LeNet相比前馈神经网络的不足之处在于:前馈神经网络虽然在训练之初就能获得较高的准确率,但在后续的训练过程中,准确率却很难再有显著提升,且训练时间要比LeNet长。
他这次实验主要是基于LeNet实现手写数字识别,通过这次试验,对LeNet的理解又加深了一些,同时也对上课所学的知识做了个巩固。
NNDL 实验5(上) - HBU_DAVID - 博客园邱锡鹏,神经网络与深度学习,机械工业出版社,https://nndl.github.io/, 2020. https://github.com/nndl/practice-in-paddle/ 第5章https://www.cnblogs.com/hbuwyg/p/16617671.htmlNNDL 实验六 卷积神经网络(3)LeNet实现MNIST_HBU_David的博客-CSDN博客_lenet实现mnistLeNet vs. FNNhttps://blog.csdn.net/qq_38975453/article/details/126799661?spm=1001.2014.3001.5502