猫狗识别—静态图像识别

Sun.HY2024-06-25 10:22

猫狗识别---静态图像识别

1. 导入必要的库:

python 复制代码 
import torch
import numpy as np
import torchvision
from os import path
from torchvision import datasets, models
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
import os
import tkinter as tk
from PIL import Image, ImageTk
from tkinter import filedialog
import cv2
import subprocess
from tkinter import messagebox

2. 设置数据目录和模型路径:

  • data_dir变量设置了数据目录的路径，model_path变量设置了预训练模型的路径。
python 复制代码 
#设置数据目录和模型路径
data_dir = r'data'
model_path = 'cat_dog_classifier.pth'

3. 定义图像转换

python 复制代码 
data_transforms = {
    'test': transforms.Compose([
        transforms.Resize(size=224),
        transforms.CenterCrop(size=224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

4. 使用GPU

python 复制代码 
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

5. 加载没有预训练权重的ResNet模型

python 复制代码 
model = models.resnet50(pretrained=False)  # 使用pretrained=False
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, 2)
model.load_state_dict(torch.load(model_path))
model = model.to(device)
model.eval()

6. 创建Tkinter窗口:

python 复制代码 
#创建Tkinter窗口
root = tk.Tk()
root.title('图像识别猫狗')
root.geometry('800x650')

image = Image.open("图像识别背景.gif")
image = image.resize((800, 650))  # 调整背景图片大小
photo1 = ImageTk.PhotoImage(image)
canvas = tk.Label(root, image=photo1)
canvas.pack()


#添加文本标签来显示识别结果
result_label = tk.Label(root, text="", font=('Helvetica', 18))
result_label.place(x=280, y=450)

#原始图像标签
image_label = tk.Label(root, text="", image="")
image_label.place(x=210, y=55)

#保存用户选择的图片路径
selected_image_path = None

#加载测试数据集
image_datasets = {x: datasets.ImageFolder(root=os.path.join(data_dir, x),
                                          transform=data_transforms[x])
                  for x in ['test']}
dataloaders = {x: DataLoader(image_datasets[x], batch_size=1, shuffle=False)
               for x in ['test']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['test']}
class_names = image_datasets['test'].classes  # 定义class_names


#加载Haar特征级联分类器
cat_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalcatface.xml')
dog_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_alt2.xml')

7.定义选择图片的函数:

python 复制代码 
#定义一个函数来打开文件选择对话框并显示图片
def choose_image():
    global selected_image_path
    file_path = filedialog.askopenfilename(initialdir=data_dir, title="选择图片",
                                           filetypes=(("图片文件", "*.png *.jpg *.jpeg *.gif *.bmp"), ("所有文件", "*.*")))
    if file_path:
        selected_image_path = file_path
        img = Image.open(file_path)
        img = img.resize((400, 350), Image.LANCZOS)
        imgTk = ImageTk.PhotoImage(img)
        image_label.config(image=imgTk)
        image_label.image = imgTk

8.定义预测图片的函数:

python 复制代码 
#定义一个函数来使用模型进行预测
def predict_image():
    global selected_image_path
    if selected_image_path:
        img = Image.open(selected_image_path)
        transform = data_transforms['test']
        img_tensor = transform(img).unsqueeze(0).to(device)

        with torch.no_grad():
            outputs = model(img_tensor)
            _, preds = torch.max(outputs, 1)

        prediction = class_names[preds.item()]  # 使用str()来将整数转换为字符串
        result_label.config(text=f"检测到的结果为: {prediction}")

        # 使用OpenCV在原始图像上绘制矩形框
        img_cv2 = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)

        if prediction == 'cats':
            cats = cat_cascade.detectMultiScale(img_cv2, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
            for (x, y, w, h) in cats:
                cv2.rectangle(img_cv2, (x, y), (x + w, y + h), (0, 0, 255), 2)  # 红色矩形框
            if len(cats) > 0:
                cv2.imwrite("detected_cats_image.jpg", img_cv2)  # 保存带有猫矩形框的图像
                img_detected_cats = Image.open("detected_cats_image.jpg").resize((350, 300), Image.LANCZOS)
                imgTk_detected_cats = ImageTk.PhotoImage(img_detected_cats)
                image_label.config(image=imgTk_detected_cats)
                image_label.image = imgTk_detected_cats
        elif prediction == 'dogs':
            dogs = dog_cascade.detectMultiScale(img_cv2, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
            for (x, y, w, h) in dogs:
                cv2.rectangle(img_cv2, (x, y), (x + w, y + h), (0, 0, 255), 2)  # 红色矩形框
            if len(dogs) > 0:
                cv2.imwrite("detected_dogs_image.jpg", img_cv2)  # 保存带有狗矩形框的图像
                img_detected_dogs = Image.open("detected_dogs_image.jpg").resize((350, 300), Image.LANCZOS)
                imgTk_detected_dogs = ImageTk.PhotoImage(img_detected_dogs)
                image_label.config(image=imgTk_detected_dogs)
                image_label.image = imgTk_detected_dogs
        else:
            print("未检测到猫或狗。")
            # 显示修改后的图像
        img = cv2.cvtColor(img_cv2, cv2.COLOR_BGR2RGB)
        img = cv2.resize(img, (400, 350))
        imgTk = ImageTk.PhotoImage(image=Image.fromarray(img))
        image_label.config(image=imgTk)
        image_label.image = imgTk
    else:
        print("请先选择一张图片。")

9.退出程序的函数:

python 复制代码 
#退出程序的函数
def close():
    subprocess.Popen(["python","主页面.py"])
    root.destroy()

10.创建按钮:

python 复制代码 
#创建按钮
image = Image.open("选择图片.gif")  # 加载一张图片
photo2 = ImageTk.PhotoImage(image)
bt1 = tk.Button(root, image=photo2, width=200, height=32, command=choose_image)
bt1.place(x=60, y=530)

image = Image.open("开始识别.gif")  # 加载一张图片
photo3 = ImageTk.PhotoImage(image)
bt1 = tk.Button(root, image=photo3, width=200, height=32, command=predict_image)
bt1.place(x=300, y=530)

image = Image.open("退出程序.gif")  # 加载一张图片
photo4 = ImageTk.PhotoImage(image)
bt1 = tk.Button(root, image=photo4, width=200, height=32, command=close)
bt1.place(x=535, y=530)

11.运行Tkinter事件循环:

python 复制代码 
#运行Tkinter事件循环
root.mainloop()

12. 完整代码＋运行结果

完整代码：

python 复制代码 
import torch
import numpy as np
import torchvision
from os import path
from torchvision import datasets, models
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
import os
import tkinter as tk
from PIL import Image, ImageTk
from tkinter import filedialog
import cv2
import subprocess
from tkinter import messagebox

# 设置数据目录和模型路径
data_dir = r'data'
model_path = 'cat_dog_classifier.pth'

# 定义图像转换
data_transforms = {
    'test': transforms.Compose([
        transforms.Resize(size=224),
        transforms.CenterCrop(size=224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

# 使用GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# 加载没有预训练权重的ResNet模型
model = models.resnet50(pretrained=False)  # 使用pretrained=False
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, 2)
model.load_state_dict(torch.load(model_path))
model = model.to(device)
model.eval()

# 创建Tkinter窗口
root = tk.Tk()
root.title('图像识别猫狗')
root.geometry('800x650')

image = Image.open("图像识别背景.gif")
image = image.resize((800, 650))  # 调整背景图片大小
photo1 = ImageTk.PhotoImage(image)
canvas = tk.Label(root, image=photo1)
canvas.pack()


# 添加文本标签来显示识别结果
result_label = tk.Label(root, text="", font=('Helvetica', 18))
result_label.place(x=280, y=450)

# 原始图像标签
image_label = tk.Label(root, text="", image="")
image_label.place(x=210, y=55)

# 保存用户选择的图片路径
selected_image_path = None

# 加载测试数据集
image_datasets = {x: datasets.ImageFolder(root=os.path.join(data_dir, x),
                                          transform=data_transforms[x])
                  for x in ['test']}
dataloaders = {x: DataLoader(image_datasets[x], batch_size=1, shuffle=False)
               for x in ['test']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['test']}
class_names = image_datasets['test'].classes  # 定义class_names


# 加载Haar特征级联分类器
cat_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalcatface.xml')
dog_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_alt2.xml')

# 定义一个函数来打开文件选择对话框并显示图片
def choose_image():
    global selected_image_path
    file_path = filedialog.askopenfilename(initialdir=data_dir, title="选择图片",
                                           filetypes=(("图片文件", "*.png *.jpg *.jpeg *.gif *.bmp"), ("所有文件", "*.*")))
    if file_path:
        selected_image_path = file_path
        img = Image.open(file_path)
        img = img.resize((400, 350), Image.LANCZOS)
        imgTk = ImageTk.PhotoImage(img)
        image_label.config(image=imgTk)
        image_label.image = imgTk

# 定义一个函数来使用模型进行预测
def predict_image():
    global selected_image_path
    if selected_image_path:
        img = Image.open(selected_image_path)
        transform = data_transforms['test']
        img_tensor = transform(img).unsqueeze(0).to(device)

        with torch.no_grad():
            outputs = model(img_tensor)
            _, preds = torch.max(outputs, 1)

        prediction = class_names[preds.item()]  # 使用str()来将整数转换为字符串
        result_label.config(text=f"检测到的结果为: {prediction}")

        # 使用OpenCV在原始图像上绘制矩形框
        img_cv2 = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)

        if prediction == 'cats':
            cats = cat_cascade.detectMultiScale(img_cv2, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
            for (x, y, w, h) in cats:
                cv2.rectangle(img_cv2, (x, y), (x + w, y + h), (0, 0, 255), 2)  # 红色矩形框
            if len(cats) > 0:
                cv2.imwrite("detected_cats_image.jpg", img_cv2)  # 保存带有猫矩形框的图像
                img_detected_cats = Image.open("detected_cats_image.jpg").resize((350, 300), Image.LANCZOS)
                imgTk_detected_cats = ImageTk.PhotoImage(img_detected_cats)
                image_label.config(image=imgTk_detected_cats)
                image_label.image = imgTk_detected_cats
        elif prediction == 'dogs':
            dogs = dog_cascade.detectMultiScale(img_cv2, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
            for (x, y, w, h) in dogs:
                cv2.rectangle(img_cv2, (x, y), (x + w, y + h), (0, 0, 255), 2)  # 红色矩形框
            if len(dogs) > 0:
                cv2.imwrite("detected_dogs_image.jpg", img_cv2)  # 保存带有狗矩形框的图像
                img_detected_dogs = Image.open("detected_dogs_image.jpg").resize((350, 300), Image.LANCZOS)
                imgTk_detected_dogs = ImageTk.PhotoImage(img_detected_dogs)
                image_label.config(image=imgTk_detected_dogs)
                image_label.image = imgTk_detected_dogs
        else:
            print("未检测到猫或狗。")
            # 显示修改后的图像
        img = cv2.cvtColor(img_cv2, cv2.COLOR_BGR2RGB)
        img = cv2.resize(img, (400, 350))
        imgTk = ImageTk.PhotoImage(image=Image.fromarray(img))
        image_label.config(image=imgTk)
        image_label.image = imgTk
    else:
        print("请先选择一张图片。")


# 退出程序的函数
def close():
    subprocess.Popen(["python","主页面.py"])
    root.destroy()

# 创建按钮
image = Image.open("选择图片.gif")  # 加载一张图片
photo2 = ImageTk.PhotoImage(image)
bt1 = tk.Button(root, image=photo2, width=200, height=32, command=choose_image)
bt1.place(x=60, y=530)

image = Image.open("开始识别.gif")  # 加载一张图片
photo3 = ImageTk.PhotoImage(image)
bt1 = tk.Button(root, image=photo3, width=200, height=32, command=predict_image)
bt1.place(x=300, y=530)

image = Image.open("退出程序.gif")  # 加载一张图片
photo4 = ImageTk.PhotoImage(image)
bt1 = tk.Button(root, image=photo4, width=200, height=32, command=close)
bt1.place(x=535, y=530)

# 运行Tkinter事件循环
root.mainloop()

运行结果：

相关推荐
ZGIAI2 分钟前
客服知识库更新后，怎么批量验收
人工智能·架构
Asize39 分钟前
AI 协作开发新范式：我用 SDD 做了个排版 npm 包
前端·人工智能
IT_陈寒3 小时前
用了Proxy才发现以前的JavaScript白写了
前端·人工智能·后端
甲维斯3 小时前
Claude Opus5手搓“NewAPI Plus”首轮成果！
人工智能
程序猿DD3 小时前
分享两个我每天都在用的 Skill，拖进豆包就能跑，限时领 30 天会员
人工智能
阿里云大数据AI技术4 小时前
Agentic Search 2.0：从单轮对话迈向企业级 AI 搜索自动驾驶Agent
人工智能·elasticsearch·agent
东风破_4 小时前
从 messages 数组到 Memory：大模型到底是怎么“记住”上一轮对话的？
人工智能
AEI4 小时前
四年间大模型的演进历程
人工智能·面试·程序员
狂师4 小时前
阿里开源：skill-up，一款Agent Skill 评测工具！
人工智能·开源·agent
武子康4 小时前
同一套 Agent Runtime，为什么 Web、Headless 和 Python SDK 仍然不是同一个产品
人工智能·llm·agent
热门推荐
01国内可直接用、免费额度/永久免费的大模型API清单（含 SiliconFlow、火山、阿里、智谱、百度、Kimi、DeepSeek、DMXAPI 等）02GitHub 镜像站点03ZCode 周末送额度活动开启：3 亿 Token 免费领取04历年考研数学一、数学二、数学三真题试卷及答案PDF052026 国产 AI 大模型横评：DeepSeek、通义千问、Kimi、文心一言、星火、豆包谁更能打？06蜘蛛磁力 搜索引擎大全，如何使用蜘蛛磁力查找磁力链接07微信历史版本含下载地址（ Windows PC | 安卓 | MAC ）及设置微信不更新08AI 编程 IDE 全景解析 2026：Agent 全面接管开发链路09Agnes AI 免费 API 接入指南：文本、生图、生视频，一套接口全免费10VSCode+CodeX扩展，无法启动