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 28\times28 28×28像素)。图5.12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,代码如下所示:
import matplotlib.pyplot as plt
import numpy as np
import PIL
from PIL import Image
image, label = train_set[0][0], train_set[1][0]
image, label = np.array(image).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
image = np.reshape(image, [28,28])
image = Image.fromarray(image.astype('uint8'), mode='L')
print("The number in the picture is {}".format(label))
plt.figure(figsize=(5, 5))
plt.imshow(image)
plt.savefig('conv-number5.pdf')
运行结果:
The number in the picture is 5
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:
在飞桨中,提供了部分视觉领域的高层API,可以直接调用API实现简单的图像处理操作。通过调用torchvision.transforms.Resize
调整大小;调用torchvision.transforms.Normalize
进行标准化处理;使用torchvision.transforms.Compose
将两个预处理操作进行拼接。
代码实现如下:
# 5.3.1.1
from torchvision.transforms import Compose, Resize, Normalize
# 数据预处理
transforms = Compose([Resize(32), Normalize(mean=[127.5], std=[127.5])])
将原始的数据集封装为Dataset类,以便DataLoader调用。
import random
from torch.utils.data import Dataset,DataLoader
import torchvision.transforms as transforms
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(image.astype('uint8'), mode='L')
image = self.transforms(image)
return image, label
def __len__(self):
return len(self.dataset[0])
random.seed(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的网络结构如图5.13所示。
我们使用上面定义的卷积层算子和汇聚层算子构建一个LeNet-5模型。
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 = 1 024 32\times 32=1\, 024 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:
# 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:
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([[[[-0.3585, -0.5452, 1.3631, ..., 1.2136, -0.1091, 2.4632],
[-0.1857, 0.4949, -0.8363, ..., -0.8915, -0.6937, 1.2373],
[ 0.0445, 1.9412, 2.5286, ..., -1.4750, -0.1582, -0.2900],
...,
[-0.8129, 0.9677, -0.7584, ..., -0.9465, -0.5650, 0.9721],
[-1.0167, -1.6895, 0.6300, ..., 2.8304, -0.5249, 0.1658],
[ 0.1880, -1.6031, -1.4927, ..., 1.9868, 0.4754, 0.1171]]]])
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。飞桨框架中,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paddle.nn.Conv2D
、paddle.nn.MaxPool2D
和paddle.nn.AvgPool2D
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: 0.0004978704452514648 s
Torch_LeNet speed: 0.000518350601196289 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([[ 0.026521, 0.122189, -0.049708, -0.073667, -0.013976, -0.019401,
0.041322, -0.131140, -0.007805, -0.044831]],
grad_fn=)
Torch_LeNet output: tensor([[ 0.026521, 0.122189, -0.049708, -0.073667, -0.013976, -0.019401,
0.041322, -0.131140, -0.007805, -0.044831]],
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 61706 61706 61706。
在飞桨中,还可以使用paddle.summary
API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,结果与公式推导一致。
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 423344 423344。
在飞桨中,还可以使用paddle.flops
API自动统计计算量。
可以看到,结果与公式推导一致。
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。
# -*- coding: utf-8 -*-
# @Time : 2022-10-28 17:36
# @Author : Mr.Liu
# @Email : [email protected]
# @File : 5.3.1.py
# @ProjectName: python
# 学习率大小
import torch
from torch import nn as nn
import torch.nn.functional as F
import numpy as np
from PIL import Image
import warnings
warnings.filterwarnings("ignore", category=UserWarning)
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)
y = torch.tensor(y, dtype=torch.int64)
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
self.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)
y = torch.tensor(y, dtype=torch.int64)
# 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):
model_state_dict = torch.load(model_path)
self.model.set_state_dict(model_state_dict)
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)
# F6:全连接层
output = F.relu(self.linear6(output))
# F7:全连接层
output = self.linear7(output)
return output
lr = 0.1
# 批次大小
batch_size = 64
class MNIST_dataset(torch.utils.data.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(image.astype('uint8'), mode='L')
image = self.transforms(image)
return image, label
def __len__(self):
return len(self.dataset[0])
from torchvision.transforms import Compose, Resize, Normalize,ToTensor
def accuracy(preds, labels):
# 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.tensor()'将preds的数据类型转换为float32类型
preds = torch.as_tensor((preds >= 0.5),dtype=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).int()
return torch.mean(torch.as_tensor((preds == labels),dtype=torch.float32))
import torch
class Accuracy():
def __init__(self, is_logist=True):
"""
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 = is_logist
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, dim=-1)
if self.is_logist:
# logist判断是否大于0
preds = torch.tensor((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.tensor((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)
preds = torch.tensor(preds, dtype=torch.int64)
# 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(torch.tensor(preds == labels, dtype=torch.float32)).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"
# 数据预处理
transforms = Compose([Resize(32),ToTensor(), Normalize(mean=[127.5], std=[127.5])])
# 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')
# 加载数据
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
dev_loader = torch.utils.data.DataLoader(dev_dataset, batch_size=batch_size)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size)
# 定义LeNet网络
# 自定义算子实现的LeNet-5
# model = Model_LeNet(in_channels=1, num_classes=10)
# 飞桨API实现的LeNet-5
model = torch_LeNet(in_channels=1, num_classes=10)
# 定义优化器
optimizer = torch.optim.SGD(lr=lr, params=model.parameters())
# 定义损失函数
loss_fn = F.cross_entropy
# 定义评价指标
metric = Accuracy(is_logist=True)
# 实例化 RunnerV3 类,并传入训练配置。
runner = RunnerV3(model=model, optimizer=optimizer,loss_fn = loss_fn, metric=metric)
# 启动训练
log_steps = 15
eval_steps = 15
runner.train(train_loader, dev_loader, num_epochs=5, log_steps=log_steps,
eval_steps=eval_steps, save_path="best_model.pdparams")
运行结果:
[Train] epoch: 0/5, step: 0/80, loss: 2.31964
[Train] epoch: 0/5, step: 15/80, loss: 1.96424
[Evaluate] dev score: 0.31000, dev loss: 1.94272
[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.31000
[Train] epoch: 1/5, step: 30/80, loss: 1.90126
[Evaluate] dev score: 0.58500, dev loss: 1.58386
[Evaluate] best accuracy performence has been updated: 0.31000 --> 0.58500
[Train] epoch: 2/5, step: 45/80, loss: 0.92311
[Evaluate] dev score: 0.63000, dev loss: 1.17126
[Evaluate] best accuracy performence has been updated: 0.58500 --> 0.63000
[Train] epoch: 3/5, step: 60/80, loss: 0.31175
[Evaluate] dev score: 0.80000, dev loss: 0.40704
[Evaluate] best accuracy performence has been updated: 0.63000 --> 0.80000
[Train] epoch: 4/5, step: 75/80, loss: 0.36434
[Evaluate] dev score: 0.83000, dev loss: 0.44397
[Evaluate] best accuracy performence has been updated: 0.80000 --> 0.83000
[Evaluate] dev score: 0.85000, dev loss: 0.50347
[Evaluate] best accuracy performence has been updated: 0.83000 --> 0.85000
[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:
[Evaluate] dev score: 0.50000, dev loss: 1.37084
[Evaluate] best accuracy performence has been updated: 0.30000 --> 0.50000
[Train] epoch: 4/10, step: 75/160, loss: 1.79037
[Evaluate] dev score: 0.39500, dev loss: 1.68836
[Train] epoch: 5/10, step: 90/160, loss: 0.97746
[Evaluate] dev score: 0.72000, dev loss: 0.99998
[Evaluate] best accuracy performence has been updated: 0.50000 --> 0.72000
[Train] epoch: 6/10, step: 105/160, loss: 0.65764
[Evaluate] dev score: 0.76000, dev loss: 0.60664
[Evaluate] best accuracy performence has been updated: 0.72000 --> 0.76000
[Train] epoch: 7/10, step: 120/160, loss: 0.36129
[Evaluate] dev score: 0.77000, dev loss: 0.60093
[Evaluate] best accuracy performence has been updated: 0.76000 --> 0.77000
[Train] epoch: 8/10, step: 135/160, loss: 0.28965
[Evaluate] dev score: 0.84000, dev loss: 0.39456
[Evaluate] best accuracy performence has been updated: 0.77000 --> 0.84000
[Train] epoch: 9/10, step: 150/160, loss: 0.15746
[Evaluate] dev score: 0.87500, dev loss: 0.31205
[Evaluate] best accuracy performence has been updated: 0.84000 --> 0.87500
[Evaluate] dev score: 0.89500, dev loss: 0.28777
[Evaluate] best accuracy performence has been updated: 0.87500 --> 0.89500
[Train] Training done!
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: 0.9050/0.2857
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,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[1]).numpy()
print(pred_class)
label = label[1].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][1], test_set[1][1]
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-number2.pdf')
运行结果:
The true category is 1 and the predicted category is 1
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: 0.522 , acc: 54.70 %
[1, 200]: loss: 0.143 , acc: 87.17 %
[1, 300]: loss: 0.098 , acc: 91.45 %
[1, 400]: loss: 0.083 , acc: 92.45 %
[1, 500]: loss: 0.074 , acc: 93.41 %
[1, 600]: loss: 0.067 , acc: 94.22 %
[1, 700]: loss: 0.054 , acc: 95.34 %
[1, 800]: loss: 0.055 , acc: 95.23 %
[1, 900]: loss: 0.048 , acc: 95.58 %
[1]: Accuracy on test set: 96.2 %
[2, 100]: loss: 0.042 , acc: 96.56 %
[2, 200]: loss: 0.042 , acc: 96.03 %
[2, 300]: loss: 0.036 , acc: 96.61 %
[2, 400]: loss: 0.037 , acc: 96.73 %
[2, 500]: loss: 0.037 , acc: 96.88 %
[2, 600]: loss: 0.032 , acc: 97.30 %
[2, 700]: loss: 0.029 , acc: 97.12 %
[2, 800]: loss: 0.034 , acc: 97.06 %
[2, 900]: loss: 0.029 , acc: 97.36 %
[2]: Accuracy on test set: 97.1 %
[3, 100]: loss: 0.028 , acc: 97.52 %
[3, 200]: loss: 0.024 , acc: 98.03 %
[3, 300]: loss: 0.025 , acc: 97.92 %
[3, 400]: loss: 0.028 , acc: 97.62 %
[3, 500]: loss: 0.026 , acc: 97.64 %
[3, 600]: loss: 0.027 , acc: 97.61 %
[3, 700]: loss: 0.027 , acc: 97.62 %
[3, 800]: loss: 0.027 , acc: 97.47 %
[3, 900]: loss: 0.026 , acc: 97.53 %
[3]: Accuracy on test set: 98.4 %
[4, 100]: loss: 0.022 , acc: 98.02 %
[4, 200]: loss: 0.023 , acc: 97.91 %
[4, 300]: loss: 0.024 , acc: 97.78 %
[4, 400]: loss: 0.019 , acc: 98.38 %
[4, 500]: loss: 0.023 , acc: 97.72 %
[4, 600]: loss: 0.019 , acc: 98.23 %
[4, 700]: loss: 0.024 , acc: 97.86 %
[4, 800]: loss: 0.021 , acc: 97.94 %
[4, 900]: loss: 0.023 , acc: 97.83 %
[4]: Accuracy on test set: 98.5 %
[5, 100]: loss: 0.020 , acc: 98.19 %
[5, 200]: loss: 0.020 , acc: 98.23 %
[5, 300]: loss: 0.020 , acc: 98.14 %
[5, 400]: loss: 0.018 , acc: 98.14 %
[5, 500]: loss: 0.015 , acc: 98.67 %
[5, 600]: loss: 0.020 , acc: 98.33 %
[5, 700]: loss: 0.016 , acc: 98.47 %
[5, 800]: loss: 0.022 , acc: 98.05 %
[5, 900]: loss: 0.020 , acc: 98.19 %
[5]: Accuracy on test set: 98.5 %
from keras.models import Sequential
from keras.layers import Dense,Flatten
from keras.layers.convolutional import Conv2D,MaxPooling2D
from keras.utils.np_utils import to_categorical
from keras.datasets import mnist
from keras import backend as K
from keras.models import load_model
import numpy as np
import matplotlib.pyplot as plt
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape((-1,28,28,1))
y_train = to_categorical(y_train,10)
x_test = x_test.reshape((-1,28,28,1))
y_test = to_categorical(y_test,10)
model = Sequential()
model.add(Conv2D(6,(5,5),strides=(1,1),input_shape=(28,28,1),padding='valid',activation='relu',kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(16,(5,5),strides=(1,1),padding='valid',activation='relu',kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(120,activation='relu'))
model.add(Dense(84,activation='relu'))
model.add(Dense(10,activation='softmax'))
model.compile(optimizer='sgd',loss='categorical_crossentropy',metrics=['accuracy'])
model.summary()
model.fit(x_train,y_train,batch_size=100,epochs=50,shuffle=True)
model.save('D:/LeNet/LeNet-5_model.h5')
loss, accuracy=model.evaluate(x_test, y_test,batch_size=100)
print(loss, accuracy)
#----------------------------------各个层特征可视化-------------------------------
(x_train, y_train), (x_test, y_test) = mnist.load_data()
#加载前面保存的模型
model=load_model('D:/LeNet/LeNet-5_model.h5')
#查看输入图片
fig1,ax1 = plt.subplots(figsize=(4,4))
ax1.imshow(np.reshape(x_test[12], (28, 28)))
plt.show()
image_arr=np.reshape(x_test[12], (-1,28, 28,1))
#可视化第一个MaxPooling2D
layer_1 = K.function([model.layers[0].input], [model.layers[1].output])
# 只修改inpu_image
f1 = layer_1([image_arr])[0]
# 第一层卷积后的特征图展示,输出是(1,12,12,6),(样本个数,特征图尺寸长,特征图尺寸宽,特征图个数)
re = np.transpose(f1, (0,3,1,2))
for i in range(6):
plt.subplot(2,4,i+1)
plt.imshow(re[0][i]) #,cmap='gray'
plt.show()
#可视化第二个MaxPooling2D
layer_2 = K.function([model.layers[0].input], [model.layers[3].output])
f2 = layer_2([image_arr])[0]
# 第一层卷积后的特征图展示,输出是(1,4,4,16),(样本个数,特征图尺寸长,特征图尺寸宽,特征图个数)
re = np.transpose(f2, (0,3,1,2))
for i in range(16):
plt.subplot(4,4,i+1)
plt.imshow(re[0][i]) #, cmap='gray'
plt.show()
#----------------------------------可视化滤波器-------------------------------
model=load_model('D:/LeNet/LeNet-5_model.h5')
#将张量转换成有效图像
def deprocess_image(x):
# 对张量进行规范化
x -= x.mean()
x /= (x.std() + 1e-5)
x *= 0.1
x += 0.5
x = np.clip(x, 0, 1)
# 转化到RGB数组
x *= 255
x = np.clip(x, 0, 255).astype('uint8')
return x
for i_kernal in range(10):
input_img=model.input
## 构建一个损耗函数,使所考虑的层的第n个滤波器的激活最大化,-1层softmax层
loss = K.mean(model.layers[-1].output[:,i_kernal])
# loss = K.mean(model.output[:, :,:, i_kernal])
# 计算输入图像的梯度与这个损失
grads = K.gradients(loss, input_img)[0]
# 效用函数通过其L2范数标准化张量
grads /= (K.sqrt(K.mean(K.square(grads))) + 1e-5)
# 此函数返回给定输入图像的损耗和梯度
iterate = K.function([input_img, K.learning_phase()], [loss, grads])
# 从带有一些随机噪声的灰色图像开始
np.random.seed(0)
#图像通道
num_channels=1
#输入图像尺寸
img_height=img_width=28
#归一化图像
input_img_data = (255- np.random.randint(0,255,(1, img_height, img_width, num_channels))) / 255.
failed = False
# run gradient ascent
print('####################################',i_kernal+1)
loss_value_pre=0
# 运行梯度上升500步
for i in range(500):
loss_value, grads_value = iterate([input_img_data,1])
if i%10 == 0:
# print(' predictions: ' , np.shape(predictions), np.argmax(predictions))
print('Iteration %d/%d, loss: %f' % (i, 500, loss_value))
print('Mean grad: %f' % np.mean(grads_value))
if all(np.abs(grads_val) < 0.000001 for grads_val in grads_value.flatten()):
failed = True
print('Failed')
break
# print('Image:\n%s' % str(input_img_data[0,0,:,:]))
if loss_value_pre != 0 and loss_value_pre > loss_value:
break
if loss_value_pre == 0:
loss_value_pre = loss_value
# if loss_value > 0.99:
# break
input_img_data += grads_value * 1 #e-3
plt.subplot(2,5, i_kernal+1)
# plt.imshow((process(input_img_data[0,:,:,0])*255).astype('uint8'), cmap='Greys') #cmap='Greys'
img_re = deprocess_image(input_img_data[0])
img_re = np.reshape(img_re, (28,28))
plt.imshow(img_re) #cmap='Greys'
plt.show()
刚开始的训练,实验的结果一直很低,连10%都到不了,最后换了一个数据集才走上正轨。作业一直交不上就是数据集不好。没事还是要多问问吧。