基于LeNet实现手写体数字识别实验
数据集下载网站
手写数字识别数据集：MNIST数据集
1.模型构建：
分布
import json
import gzip
# 打印并观察数据集分布情况
#使用json.load()和gzip.open()函数，以gzip压缩格式从指定路径读取MNIST数据集文件
train_set, dev_set, test_set = json.load(gzip.open(r'C:\Users\320\PycharmProjects\pythonProject\mnist.json.gz'))
#通过切片操作，提取出训练集、验证集和测试集的前3000个样本作为训练数据，前200个样本作为验证数据和测试数据
train_images, train_labels = train_set[0][:3000], train_set[1][:3000]
dev_images, dev_labels = dev_set[0][:200], dev_set[1][:200]
test_images, test_labels = test_set[0][:200], test_set[1][:200]
#重新组织成train_set、dev_set和test_set
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])))
查看
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
image, label = train_set[0][0], train_set[1][0]#从训练集中获取第一个样本的图像和标签
image, label = np.array(image).astype('float32'), int(label)#标签转化
# 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') #将numpy数组转化成图片形式
print("The number in the picture is {}".format(label))
plt.figure(figsize=(5, 5))
plt.imshow(image, cmap='gray') #cmap='gray'灰度图片
plt.show()
数据预处理
调用torch包中自带的方法
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])])import random
import torch.utils.data as io
class MNIST_dataset(io.Dataset):#继承自torch.utils.data.Dataset类，用于处理数据集
def __init__(self, dataset, transforms, mode='train'):#接受dataset（数据集）、transforms（转换函数）和mode（模式）
self.mode = mode
self.transforms = transforms
self.dataset = dataset
def __getitem__(self, idx):#定义了数据集类的索引方法，用于获取数据集中特定索引的样本
# 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):#获取数据集大小
return len(self.dataset[0])
# 固定随机种子
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')模型构建
LeNet-5模型
自定义卷积算子和池化层
- C3层没有使用连接表来减少卷积数量。
- 汇聚层使用了简单的平均汇聚，没有引入权重和偏置参数以及非线性激活函数。
- 卷积层的激活函数使用ReLU函数。
- 最后的输出层为一个全连接线性层。
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
class Conv2D(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0):
super(Conv2D, self).__init__()
# 创建卷积核
self.weight = torch.nn.Parameter(torch.ones(out_channels, in_channels, kernel_size, kernel_size))
# 创建偏置
self.bias = torch.nn.Parameter(torch.zeros(out_channels, 1))
self.stride = stride
self.padding = padding
# 输入通道数
self.in_channels = in_channels
# 输出通道数
self.out_channels = out_channels
# 基础卷积运算
def single_forward(self, X, weight):
# 零填充
new_X = torch.zeros([X.shape[0], X.shape[1] + 2 * self.padding, X.shape[2] + 2 * self.padding])
new_X[:, self.padding:X.shape[1] + self.padding, self.padding:X.shape[2] + self.padding] = X
u, v = weight.shape
output_w = (new_X.shape[1] - u) // self.stride + 1
output_h = (new_X.shape[2] - v) // self.stride + 1
output = torch.zeros([X.shape[0], output_w, output_h])
for i in range(0, output.shape[1]):
for j in range(0, output.shape[2]):
output[:, i, j] = torch.sum(
new_X[:, self.stride * i:self.stride * i + u, self.stride * j:self.stride * j + v] * weight,
dim=[1, 2])
return output
def forward(self, inputs):
"""
输入：
- inputs：输入矩阵，shape=[B, D, M, N]
- weights：P组二维卷积核，shape=[P, D, U, V]
- bias：P个偏置，shape=[P, 1]
"""
feature_maps = []
# 进行多次多输入通道卷积运算
p = 0
for w, b in zip(self.weight, self.bias): # P个(w,b),每次计算一个特征图Zp
multi_outs = []
# 循环计算每个输入特征图对应的卷积结果
for i in range(self.in_channels):
single = self.single_forward(inputs[:, i, :, :], w[i])
multi_outs.append(single)
# print("Conv2D in_channels:",self.in_channels,"i:",i,"single:",single.shape)
# 将所有卷积结果相加
feature_map = torch.sum(torch.stack(multi_outs), dim=0) + b # Zp
feature_maps.append(feature_map)
# print("Conv2D out_channels:",self.out_channels, "p:",p,"feature_map:",feature_map.shape)
p += 1
# 将所有Zp进行堆叠
out = torch.stack(feature_maps, 1)
return out
class Pool2D(nn.Module):
def __init__(self, size=(2, 2), mode='max', stride=1):
super(Pool2D, self).__init__()
# 汇聚方式
self.mode = mode
self.h, self.w = size
self.stride = stride
def forward(self, x):
output_w = (x.shape[2] - self.w) // self.stride + 1
output_h = (x.shape[3] - self.h) // self.stride + 1
output = torch.zeros([x.shape[0], x.shape[1], output_w, output_h])
# 汇聚
for i in range(output.shape[2]):
for j in range(output.shape[3]):
# 最大汇聚
if self.mode == 'max':
output[:, :, i, j] = torch.max(
x[:, :, self.stride * i:self.stride * i + self.w, self.stride * j:self.stride * j + self.h])
# 平均汇聚
elif self.mode == 'avg':
output[:, :, i, j] = torch.mean(
x[:, :, self.stride * i:self.stride * i + self.w, self.stride * j:self.stride * j + self.h],
dim=[2, 3])
return output
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 = 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 = Pool2D(size=(2, 2), mode='max', 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 = 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 = Pool2D(size=(2, 2), mode='avg', 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 = 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
# 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)
# 通过调用LeNet从基类继承的modules()函数，查看LeNet中所包含的子层
print(model.modules())
x = torch.tensor(inputs)
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)
测试两个网络的运算速度
import numpy as np
import time
import torch
# 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PyTorch_LeNet类的实例，指定模型名称和分类的类别数目
torch_model = PyTorch_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')
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。
import numpy as np
import torch
# 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 = PyTorch_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)
统计LeNet-5模型的参数量和计算量
import torchsummary
model = PyTorch_LeNet(in_channels=1, num_classes=10)
model = model.cuda()
params_info = torchsummary.summary(model, (1, 32, 32))
print(params_info)2.模型训练
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
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'torch.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'torch.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)
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, dim=-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'torch.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(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"训练
import torch.optim as opti
from torch.utils.data import DataLoader
# 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)
# 定义LeNet网络
# 飞桨API实现的LeNet-5
model = PyTorch_LeNet(in_channels=1, num_classes=10)
# 定义优化器
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")
可视化
import matplotlib.pyplot as plt
# 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')
3.模型评价
# 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))
4.模型预测
# 获取测试集中第一条数据
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)
# 获取概率最大的类别
pred_class = torch.argmax(pred[2]).numpy()
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][2], test_set[1][2]
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')
1937
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
