一、数据集

在群中直接下载

二、构建模型

class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 9, 3)self.maxpool = nn.MaxPool2d(2, 2)self.conv2 = nn.Conv2d(9, 5, 3)self.relu = nn.ReLU()self.fc1 = nn.Linear(27 * 27 * 5, 1200)self.fc2 = nn.Linear(1200, 64)self.fc3 = nn.Linear(64, 2)def forward(self, x):x = self.maxpool(self.relu(self.conv1(x)))x = self.maxpool(self.relu(self.conv2(x)))x = x.view(-1, 27 * 27 * 5)x = self.relu(self.fc1(x))x = self.relu(self.fc2(x))x = self.fc3(x)return x

三、训练模型

model = Net()criterion = torch.nn.CrossEntropyLoss()  # 损失函数 交叉熵损失函数
optimizer = optim.SGD(model.parameters(), lr=0.1)  # 优化函数：随机梯度下降epochs = 10
for epoch in range(epochs):running_loss = 0.0for i, data in enumerate(data_loader):images, label = dataout = model(images)loss = criterion(out, label)optimizer.zero_grad()loss.backward()optimizer.step()running_loss += loss.item()if (i + 1) % 10 == 0:print('[%d  %5d]   loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))running_loss = 0.0print('finished train')# 保存模型
torch.save(model, 'model_name.pth')

四、测试训练好的模型

model_load = torch.load('model_name.pth')
# 读取一张图片 images[0]，测试
print("labels[0] truth:\t", labels[0])
x = images[0]
x = x.reshape([1, x.shape[0], x.shape[1], x.shape[2]])
predicted = torch.max(model_load(x), 1)
print("labels[0] predict:\t", predicted.indices)img = images[0].data.squeeze().numpy()  # 将输出转换为图片的格式
plt.imshow(img, cmap='gray')
plt.show()

五、计算模型准确率

# 读取模型
model_load = torch.load('model_name1.pth')correct = 0
total = 0
with torch.no_grad():  # 进行评测的时候网络不更新梯度for data in data_loader_test:  # 读取测试集images, labels = dataoutputs = model_load(images)_, predicted = torch.max(outputs.data, 1)  # 取出 最大值的索引 作为 分类结果total += labels.size(0)  # labels 的长度correct += (predicted == labels).sum().item()  # 预测正确的数目
print('Accuracy of the network on the  test images: %f %%' % (100. * correct / total))

六、查看训练好模型的特征图

import torch
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image
from torchvision import transforms, datasets
import torch.nn as nn
from torch.utils.data import DataLoaderplt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号 #有中文出现的情况，需要u'内容
#  定义图像预处理过程(要与网络模型训练过程中的预处理过程一致)
transforms = transforms.Compose([transforms.ToTensor(),  # 把图片进行归一化，并把数据转换成Tensor类型transforms.Grayscale(1)  # 把图片 转为灰度图
])
path = r'train_data'
data_train = datasets.ImageFolder(path, transform=transforms)
data_loader = DataLoader(data_train, batch_size=64, shuffle=True)
for i, data in enumerate(data_loader):images, labels = data# print(images.shape)# print(labels.shape)breakclass Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 9, 3)  # in_channel , out_channel , kennel_size , strideself.maxpool = nn.MaxPool2d(2, 2)self.conv2 = nn.Conv2d(9, 5, 3)  # in_channel , out_channel , kennel_size , strideself.relu = nn.ReLU()self.fc1 = nn.Linear(27 * 27 * 5, 1200)  # full connect 1self.fc2 = nn.Linear(1200, 64)  # full connect 2self.fc3 = nn.Linear(64, 2)  # full connect 3def forward(self, x):outputs = []x = self.maxpool(self.relu(self.conv1(x)))# outputs.append(x)x = self.maxpool(self.relu(self.conv2(x)))outputs.append(x)x = x.view(-1, 27 * 27 * 5)x = self.relu(self.fc1(x))x = self.relu(self.fc2(x))x = self.fc3(x)return outputs# create model
model1 = Net()# load model weights加载预训练权重
# model_weight_path ="./AlexNet.pth"
# model_weight_path = "model_name.pth"
# model1.load_state_dict(torch.load(model_weight_path))# 读取模型
model1 = torch.load('model_name.pth')x = images[0]# forward正向传播过程
out_put = model1(x)weights_keys = model1.state_dict().keys()
for key in weights_keys:print("key :", key)# 卷积核通道排列顺序 [kernel_number, kernel_channel, kernel_height, kernel_width]if key == "conv1.weight":weight_t = model1.state_dict()[key].numpy()print("weight_t.shape", weight_t.shape)k = weight_t[:, 0, :, :]  # 获取第一个卷积核的信息参数# show 9 kernel ,1 channelplt.figure()for i in range(9):ax = plt.subplot(3, 3, i + 1)  # 参数意义：3：图片绘制行数，5：绘制图片列数，i+1：图的索引plt.imshow(k[i, :, :], cmap='gray')title_name = 'kernel' + str(i) + ',channel1'plt.title(title_name)plt.show()if key == "conv2.weight":weight_t = model1.state_dict()[key].numpy()print("weight_t.shape", weight_t.shape)k = weight_t[:, :, :, :]  # 获取第一个卷积核的信息参数print(k.shape)print(k)plt.figure()for c in range(9):channel = k[:, c, :, :]for i in range(5):ax = plt.subplot(2, 3, i + 1)  # 参数意义：3：图片绘制行数，5：绘制图片列数，i+1：图的索引plt.imshow(channel[i, :, :], cmap='gray')title_name = 'kernel' + str(i) + ',channel' + str(c)plt.title(title_name)plt.show()

八、训练模型源代码

# https://blog.csdn.net/qq_53345829/article/details/124308515
import torch
from torchvision import transforms, datasets
import torch.nn as nn
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
import torch.optim as optimtransforms = transforms.Compose([transforms.ToTensor(),  # 把图片进行归一化，并把数据转换成Tensor类型transforms.Grayscale(1)  # 把图片 转为灰度图
])path = r'train_data'
path_test = r'test_data'data_train = datasets.ImageFolder(path, transform=transforms)
data_test = datasets.ImageFolder(path_test, transform=transforms)print("size of train_data:",len(data_train))
print("size of test_data:",len(data_test))data_loader = DataLoader(data_train, batch_size=64, shuffle=True)
data_loader_test = DataLoader(data_test, batch_size=64, shuffle=True)for i, data in enumerate(data_loader):images, labels = dataprint(images.shape)print(labels.shape)breakfor i, data in enumerate(data_loader_test):images, labels = dataprint(images.shape)print(labels.shape)breakclass Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 9, 3)  # in_channel , out_channel , kennel_size , strideself.maxpool = nn.MaxPool2d(2, 2)self.conv2 = nn.Conv2d(9, 5, 3)  # in_channel , out_channel , kennel_size , strideself.relu = nn.ReLU()self.fc1 = nn.Linear(27 * 27 * 5, 1200)  # full connect 1self.fc2 = nn.Linear(1200, 64)  # full connect 2self.fc3 = nn.Linear(64, 2)  # full connect 3def forward(self, x):x = self.maxpool(self.relu(self.conv1(x)))x = self.maxpool(self.relu(self.conv2(x)))x = x.view(-1, 27 * 27 * 5)x = self.relu(self.fc1(x))x = self.relu(self.fc2(x))x = self.fc3(x)return xmodel = Net()criterion = torch.nn.CrossEntropyLoss()  # 损失函数 交叉熵损失函数
optimizer = optim.SGD(model.parameters(), lr=0.1)  # 优化函数：随机梯度下降epochs = 10
for epoch in range(epochs):running_loss = 0.0for i, data in enumerate(data_loader):images, label = dataout = model(images)loss = criterion(out, label)optimizer.zero_grad()loss.backward()optimizer.step()running_loss += loss.item()if (i + 1) % 10 == 0:print('[%d  %5d]   loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))running_loss = 0.0print('finished train')# 保存模型 torch.save(model.state_dict(), model_path)
torch.save(model.state_dict(), 'model_name1.pth')  # 保存的是模型， 不止是w和b权重值# 读取模型
model = torch.load('model_name1.pth')

九、测试模型源代码

# https://blog.csdn.net/qq_53345829/article/details/124308515
import torch
from torchvision import transforms, datasets
import torch.nn as nn
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt
import torch.optim as optimtransforms = transforms.Compose([transforms.ToTensor(),  # 把图片进行归一化，并把数据转换成Tensor类型transforms.Grayscale(1)  # 把图片 转为灰度图
])path = r'train_data'
path_test = r'test_data'data_train = datasets.ImageFolder(path, transform=transforms)
data_test = datasets.ImageFolder(path_test, transform=transforms)print("size of train_data:", len(data_train))
print("size of test_data:", len(data_test))data_loader = DataLoader(data_train, batch_size=64, shuffle=True)
data_loader_test = DataLoader(data_test, batch_size=64, shuffle=True)
print(len(data_loader))
print(len(data_loader_test))class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 9, 3)  # in_channel , out_channel , kennel_size , strideself.maxpool = nn.MaxPool2d(2, 2)self.conv2 = nn.Conv2d(9, 5, 3)  # in_channel , out_channel , kennel_size , strideself.relu = nn.ReLU()self.fc1 = nn.Linear(27 * 27 * 5, 1200)  # full connect 1self.fc2 = nn.Linear(1200, 64)  # full connect 2self.fc3 = nn.Linear(64, 2)  # full connect 3def forward(self, x):x = self.maxpool(self.relu(self.conv1(x)))x = self.maxpool(self.relu(self.conv2(x)))x = x.view(-1, 27 * 27 * 5)x = self.relu(self.fc1(x))x = self.relu(self.fc2(x))x = self.fc3(x)return x# 读取模型
model = Net()
model.load_state_dict(torch.load('model_name1.pth', map_location='cpu')) # 导入网络的参数# model_load = torch.load('model_name1.pth')
# https://blog.csdn.net/qq_41360787/article/details/104332706correct = 0
total = 0
with torch.no_grad():  # 进行评测的时候网络不更新梯度for data in data_loader_test:  # 读取测试集images, labels = dataoutputs = model(images)_, predicted = torch.max(outputs.data, 1)  # 取出 最大值的索引 作为 分类结果total += labels.size(0)  # labels 的长度correct += (predicted == labels).sum().item()  # 预测正确的数目
print('Accuracy of the network on the  test images: %f %%' % (100. * correct / total))#  "_," 的解释 https://blog.csdn.net/weixin_48249563/article/details/111387501

人工智能-作业6：CNN实现XO识别相关推荐

NNDL 作业6：基于CNN的XO识别
实现卷积-池化-激活 Numpy版本:手工实现卷积-池化-激活自定义卷积算子.池化算子实现,源码如下: import numpy as npx = np.array([[-1, -1, -1, - ...
作业6：基于CNN的XO识别深度学习手搓卷积代码
目录一.实现卷积池化激活代码 1.numpy版本生成图像卷积核生成卷积操作池化操作最大池化平均池化激活操作 2.pytorch版本(利用pytorch框架) 2.1相关函数 2. ...
【2021-2022 春学期】人工智能-作业6：CNN实现XO识别
文章目录一.数据集二.构建模型三.训练模型四.测试训练好的模型五.计算模型准确率六.查看训练好模型的特征图七.查看卷积核八.源码 1.训练模型源码 2.测试模型源码一.数据集二.构 ...
【机器学习/人工智能】大作业：手写数字识别系统
写在前面参考的是https://zh.d2l.ai/index.html 一.大作业设计目的与要求 (1)利用所学习的聚类算法完成简单的图像分割系统. (2)编程并利用相关软件完成大作业测试,得到实 ...
Python仿真及应用结课大作业—基于CNN的手写数字识别与涂鸦识别
提示:文章写完后,目录可以自动生成,如何生成可参考右边的帮助文档文章目录前言一.结课文档目录二.涂鸦识别(篇幅问题只展示其一) 涂鸦识别引入必要的库函数导入数据为各个数据文件添加标签数 ...
2021年人工神经网络第四次作业 - 第二题MNIST手写体识别
简介: ※MNIST数据集合是深度学习基础训练数据集合.改数据集合可以使用稠密前馈神经网络训练,也可以使用CNN.本文采用了单隐层BP网络和LeNet网络对于MNIST数据集合进行测试.实验结果标明 ...
使用Python+Tensorflow的CNN技术快速识别验证码
北京上海巡回站 | NVIDIA DLI深度学习培训 2018年1月26/1月12日 NVIDIA 深度学习学院带你快速进入火热的DL领域阅读全文 ...
深度学习100例-卷积神经网络（CNN）花朵识别 | 第4天
文章目录一.前期工作 1. 设置GPU 2. 下载数据 3. 检查数据二.数据预处理 1. 加载数据 2. 可视化数据 3. 再次检查数据 4. 配置数据集三.构建CNN网络四.编译五.训练 ...
天池算法赛——广东电网智慧现场作业挑战赛赛道三：识别高空作业及安全带佩戴
记录下第一次正式参加线上算法比赛的解题流程.虽然错过了B榜时间,但收获匪浅! 相关数据集及下文代码可见识别高空作业及安全带_数据集及相关代码.txt 目录项目介绍数据处理标签数据提取标签数据 ...

人工智能-作业6：CNN实现XO识别

文章目录

一、数据集

二、构建模型

三、训练模型

四、测试训练好的模型

五、计算模型准确率

六、查看训练好模型的特征图

八、训练模型源代码

九、测试模型源代码

人工智能-作业6：CNN实现XO识别相关推荐

最新文章

热门文章

人工智能-作业6：CNN实现XO识别

文章目录

一、 数据集

二、构建模型

三、训练模型

四、测试训练好的模型

五、计算模型准确率

六、查看训练好模型的特征图

八、训练模型源代码

九、测试模型源代码

人工智能-作业6：CNN实现XO识别相关推荐

最新文章

热门文章

一、数据集