增加embedding方式，可视化的推理界面。
This commit is contained in:
zhanghuan
@@ -0,0 +1,849 @@
|
||||
import os
|
||||
import json
|
||||
import cv2
|
||||
import numpy as np
|
||||
import customtkinter as ctk
|
||||
from tkinter import filedialog, messagebox
|
||||
from PIL import Image, ImageTk
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from typing import List, Optional, Tuple
|
||||
from tkinterdnd2 import DND_FILES, TkinterDnD
|
||||
import threading
|
||||
import time
|
||||
import pickle
|
||||
import faiss
|
||||
from collections import Counter
|
||||
|
||||
from net.resnet_embedding import create_resnet50_embedding
|
||||
from settings import settings
|
||||
|
||||
# 设置customtkinter的外观
|
||||
ctk.set_appearance_mode("System")
|
||||
ctk.set_default_color_theme("blue")
|
||||
|
||||
|
||||
class EmbeddingFoodClassifierApp:
|
||||
def __init__(self, root):
|
||||
self.root = root
|
||||
self.root.title("数字味道-食物识别系统 (Embedding版)")
|
||||
self.root.geometry("1400x800")
|
||||
|
||||
# 设备设置
|
||||
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
print(f"使用设备: {self.device}")
|
||||
|
||||
# 当前上传的图片列表
|
||||
self.uploaded_images = []
|
||||
self.current_results = []
|
||||
|
||||
# 识别时间记录
|
||||
self.recognition_start_time = None
|
||||
self.recognition_duration = 0
|
||||
|
||||
# 模型和FAISS索引相关
|
||||
self.model = None
|
||||
self.faiss_index = None
|
||||
self.image_paths = []
|
||||
self.labels = []
|
||||
self.class_info = {}
|
||||
self.class_names = []
|
||||
self.class_to_idx = {}
|
||||
self.idx_to_class = {}
|
||||
|
||||
# 加载模型和索引
|
||||
self.load_model_and_index()
|
||||
|
||||
# 创建UI组件
|
||||
self.create_widgets()
|
||||
|
||||
def load_model_and_index(self):
|
||||
"""加载训练好的embedding模型和FAISS索引"""
|
||||
try:
|
||||
# 模型路径
|
||||
model_path = "../model/embedding_20250917_145342/best_embedding_model.pth"
|
||||
|
||||
# FAISS索引目录
|
||||
index_dir = "../faiss_vector_db/faiss_index"
|
||||
|
||||
if os.path.exists(model_path) and os.path.exists(index_dir):
|
||||
# 1. 加载embedding模型
|
||||
print("正在加载embedding模型...")
|
||||
self.model = create_resnet50_embedding(
|
||||
embedding_dim=512,
|
||||
pretrained=True,
|
||||
use_internal_preprocess=False
|
||||
)
|
||||
|
||||
# 加载模型权重
|
||||
checkpoint = torch.load(model_path, map_location=self.device)
|
||||
if isinstance(checkpoint, dict):
|
||||
if 'model_state_dict' in checkpoint:
|
||||
self.model.load_state_dict(checkpoint['model_state_dict'])
|
||||
elif 'state_dict' in checkpoint:
|
||||
self.model.load_state_dict(checkpoint['state_dict'])
|
||||
else:
|
||||
self.model.load_state_dict(checkpoint)
|
||||
else:
|
||||
self.model.load_state_dict(checkpoint)
|
||||
|
||||
self.model.to(self.device)
|
||||
self.model.eval()
|
||||
print("Embedding模型加载成功!")
|
||||
|
||||
# 2. 加载FAISS索引
|
||||
print("正在加载FAISS索引...")
|
||||
|
||||
# 加载索引文件
|
||||
index_path = os.path.join(index_dir, 'faiss_index.bin')
|
||||
self.faiss_index = faiss.read_index(index_path)
|
||||
print(f"FAISS索引已加载: {self.faiss_index.ntotal} 个向量")
|
||||
|
||||
# 加载图片路径映射
|
||||
paths_path = os.path.join(index_dir, 'image_paths.pkl')
|
||||
with open(paths_path, 'rb') as f:
|
||||
self.image_paths = pickle.load(f)
|
||||
|
||||
# 加载标签映射
|
||||
labels_path = os.path.join(index_dir, 'labels.pkl')
|
||||
with open(labels_path, 'rb') as f:
|
||||
self.labels = pickle.load(f)
|
||||
|
||||
# 加载类别信息
|
||||
class_info_path = os.path.join(index_dir, 'class_info.json')
|
||||
with open(class_info_path, 'r', encoding='utf-8') as f:
|
||||
self.class_info = json.load(f)
|
||||
|
||||
self.class_names = self.class_info['class_names']
|
||||
self.class_to_idx = self.class_info['class_to_idx']
|
||||
self.idx_to_class = self.class_info['idx_to_class']
|
||||
|
||||
print(f"索引元数据已加载: {len(self.image_paths)} 张图片, {len(self.class_names)} 个类别")
|
||||
print(f"支持的食物类别: {self.class_names}")
|
||||
|
||||
else:
|
||||
print("模型文件或索引文件不存在，将使用模拟识别")
|
||||
self.model = None
|
||||
self.faiss_index = None
|
||||
# 设置默认类别（用于模拟）
|
||||
self.class_names = ['回锅肉', '炒细面', '西红柿鸡蛋', '麻辣小面']
|
||||
|
||||
except Exception as e:
|
||||
print(f"模型或索引加载失败: {e}")
|
||||
self.model = None
|
||||
self.faiss_index = None
|
||||
# 设置默认类别（用于模拟）
|
||||
self.class_names = ['回锅肉', '炒细面', '西红柿鸡蛋', '麻辣小面']
|
||||
|
||||
def extract_true_class_from_path(self, file_path):
|
||||
"""从文件路径中提取真实类别（上一级目录名）"""
|
||||
try:
|
||||
# 标准化路径
|
||||
normalized_path = os.path.normpath(file_path)
|
||||
# 获取目录路径
|
||||
dir_path = os.path.dirname(normalized_path)
|
||||
# 获取上一级目录名（即类别名）
|
||||
true_class = os.path.basename(dir_path)
|
||||
|
||||
# 检查是否是已知的食物类别
|
||||
if true_class in self.class_names:
|
||||
return true_class
|
||||
else:
|
||||
# 如果不是已知类别，返回None表示未知
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
print(f"提取真实类别失败: {e}")
|
||||
return None
|
||||
|
||||
def load_image_with_chinese_path(self, file_path):
|
||||
"""使用支持中文路径的方法加载图片"""
|
||||
try:
|
||||
# 方法1：使用numpy和cv2.imdecode处理中文路径
|
||||
with open(file_path, 'rb') as f:
|
||||
image_data = f.read()
|
||||
|
||||
# 将字节数据转换为numpy数组
|
||||
nparr = np.frombuffer(image_data, np.uint8)
|
||||
|
||||
# 使用cv2.imdecode解码图片
|
||||
image = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
|
||||
|
||||
if image is not None:
|
||||
return image
|
||||
|
||||
except Exception as e:
|
||||
print(f"加载图片失败: {e}")
|
||||
return None
|
||||
|
||||
def create_widgets(self):
|
||||
"""创建UI组件"""
|
||||
# 主框架
|
||||
self.main_frame = ctk.CTkFrame(self.root)
|
||||
self.main_frame.pack(fill="both", expand=True, padx=15, pady=15)
|
||||
|
||||
# 左侧框架 - 图片上传区域
|
||||
self.left_frame = ctk.CTkFrame(self.main_frame, width=600)
|
||||
self.left_frame.pack(side="left", fill="both", expand=True, padx=(0, 10), pady=0)
|
||||
self.left_frame.pack_propagate(False)
|
||||
|
||||
# 左侧标题
|
||||
self.left_title = ctk.CTkLabel(
|
||||
self.left_frame,
|
||||
text="图片上传区域 (Embedding相似度检索)",
|
||||
font=("Arial", 16, "bold")
|
||||
)
|
||||
self.left_title.pack(pady=(15, 10))
|
||||
|
||||
# 拖拽上传区域
|
||||
self.upload_frame = ctk.CTkFrame(self.left_frame, fg_color=("gray90", "gray20"))
|
||||
self.upload_frame.pack(fill="x", padx=15, pady=(0, 10), ipady=50)
|
||||
|
||||
# 拖拽提示标签
|
||||
self.upload_label = ctk.CTkLabel(
|
||||
self.upload_frame,
|
||||
text="拖拽图片到这里\n或点击下方按钮选择图片\n支持多图片上传\n基于特征相似度识别",
|
||||
font=("Arial", 14),
|
||||
text_color=("gray40", "gray60")
|
||||
)
|
||||
self.upload_label.pack(expand=True)
|
||||
|
||||
# 绑定拖放事件
|
||||
self.upload_frame.drop_target_register(DND_FILES)
|
||||
self.upload_frame.dnd_bind('<<Drop>>', self.handle_drop)
|
||||
self.upload_frame.bind('<Enter>', self.on_drag_enter)
|
||||
self.upload_frame.bind('<Leave>', self.on_drag_leave)
|
||||
|
||||
# 按钮区域
|
||||
self.button_frame = ctk.CTkFrame(self.left_frame)
|
||||
self.button_frame.pack(fill="x", padx=15, pady=(0, 10))
|
||||
|
||||
# 选择图片按钮
|
||||
self.select_button = ctk.CTkButton(
|
||||
self.button_frame,
|
||||
text="选择图片",
|
||||
command=self.select_images,
|
||||
width=120,
|
||||
height=35
|
||||
)
|
||||
self.select_button.pack(side="left", padx=(10, 5), pady=10)
|
||||
|
||||
# 清空按钮
|
||||
self.clear_button = ctk.CTkButton(
|
||||
self.button_frame,
|
||||
text="清空图片",
|
||||
command=self.clear_images,
|
||||
width=120,
|
||||
height=35,
|
||||
fg_color="gray",
|
||||
hover_color="darkgray"
|
||||
)
|
||||
self.clear_button.pack(side="left", padx=5, pady=10)
|
||||
|
||||
# 识别按钮
|
||||
self.recognize_button = ctk.CTkButton(
|
||||
self.button_frame,
|
||||
text="开始识别",
|
||||
command=self.start_recognition,
|
||||
width=120,
|
||||
height=35,
|
||||
fg_color="green",
|
||||
hover_color="darkgreen"
|
||||
)
|
||||
self.recognize_button.pack(side="right", padx=(5, 10), pady=10)
|
||||
self.recognize_button.configure(state="disabled")
|
||||
|
||||
# 已上传图片显示区域
|
||||
self.images_display_frame = ctk.CTkScrollableFrame(
|
||||
self.left_frame,
|
||||
label_text="已上传的图片"
|
||||
)
|
||||
self.images_display_frame.pack(fill="both", expand=True, padx=15, pady=(0, 15))
|
||||
|
||||
# 右侧框架 - 识别结果区域
|
||||
self.right_frame = ctk.CTkFrame(self.main_frame, width=700)
|
||||
self.right_frame.pack(side="right", fill="both", expand=True, padx=(10, 0), pady=0)
|
||||
self.right_frame.pack_propagate(False)
|
||||
|
||||
# 右侧标题
|
||||
self.right_title = ctk.CTkLabel(
|
||||
self.right_frame,
|
||||
text="识别结果 (基于特征相似度)",
|
||||
font=("Arial", 16, "bold")
|
||||
)
|
||||
self.right_title.pack(pady=(15, 10))
|
||||
|
||||
# 统计信息框架
|
||||
self.stats_frame = ctk.CTkFrame(self.right_frame)
|
||||
self.stats_frame.pack(fill="x", padx=15, pady=(0, 10))
|
||||
|
||||
# 统计标签
|
||||
self.stats_label = ctk.CTkLabel(
|
||||
self.stats_frame,
|
||||
text="总图片: 0 | 已识别: 0 | 平均准确率: 0%",
|
||||
font=("Arial", 12)
|
||||
)
|
||||
self.stats_label.pack(pady=10)
|
||||
|
||||
# 识别结果显示区域
|
||||
self.results_display_frame = ctk.CTkScrollableFrame(
|
||||
self.right_frame,
|
||||
label_text="识别详情 (相似度排序)"
|
||||
)
|
||||
self.results_display_frame.pack(fill="both", expand=True, padx=15, pady=(0, 15))
|
||||
|
||||
def select_images(self):
|
||||
"""选择图片文件"""
|
||||
file_paths = filedialog.askopenfilenames(
|
||||
title="选择图片文件",
|
||||
filetypes=[
|
||||
("图像文件", "*.jpg *.jpeg *.png *.bmp *.gif"),
|
||||
("JPEG文件", "*.jpg *.jpeg"),
|
||||
("PNG文件", "*.png"),
|
||||
("所有文件", "*.*")
|
||||
]
|
||||
)
|
||||
|
||||
if file_paths:
|
||||
for file_path in file_paths:
|
||||
self.add_image(file_path)
|
||||
|
||||
def handle_drop(self, event):
|
||||
"""处理拖拽文件"""
|
||||
files = event.data.split()
|
||||
for file_path in files:
|
||||
# 清理文件路径
|
||||
file_path = file_path.strip('{}').strip('"')
|
||||
file_path = os.path.normpath(file_path)
|
||||
|
||||
# 检查是否为图片文件
|
||||
valid_extensions = ('.jpg', '.jpeg', '.png', '.bmp', '.gif')
|
||||
if file_path.lower().endswith(valid_extensions):
|
||||
self.add_image(file_path)
|
||||
|
||||
def on_drag_enter(self, event):
|
||||
"""拖拽进入时的视觉反馈"""
|
||||
self.upload_frame.configure(fg_color=("gray80", "gray30"))
|
||||
self.upload_label.configure(text="释放鼠标上传图片")
|
||||
|
||||
def on_drag_leave(self, event):
|
||||
"""拖拽离开时恢复正常"""
|
||||
self.upload_frame.configure(fg_color=("gray90", "gray20"))
|
||||
self.upload_label.configure(text="拖拽图片到这里\n或点击下方按钮选择图片\n支持多图片上传\n基于特征相似度识别")
|
||||
|
||||
def add_image(self, file_path):
|
||||
"""添加图片到上传列表"""
|
||||
try:
|
||||
# 检查文件是否存在
|
||||
if not os.path.exists(file_path):
|
||||
messagebox.showerror("错误", f"文件不存在: {file_path}")
|
||||
return
|
||||
|
||||
# 检查是否已经添加过
|
||||
if file_path in [img['path'] for img in self.uploaded_images]:
|
||||
messagebox.showinfo("提示", "该图片已经添加过了")
|
||||
return
|
||||
|
||||
# 使用支持中文路径的方法加载图片
|
||||
image = self.load_image_with_chinese_path(file_path)
|
||||
if image is None:
|
||||
messagebox.showerror("错误", f"无法读取图片: {file_path}")
|
||||
return
|
||||
|
||||
# 从文件路径中提取真实类别（上一级目录名）
|
||||
true_class = self.extract_true_class_from_path(file_path)
|
||||
|
||||
# 添加到列表
|
||||
image_info = {
|
||||
'path': file_path,
|
||||
'name': os.path.basename(file_path),
|
||||
'image': image,
|
||||
'true_class': true_class,
|
||||
'recognized': False,
|
||||
'result': None
|
||||
}
|
||||
self.uploaded_images.append(image_info)
|
||||
|
||||
# 更新显示
|
||||
self.update_images_display()
|
||||
self.update_recognize_button()
|
||||
|
||||
except Exception as e:
|
||||
messagebox.showerror("错误", f"添加图片时出错: {str(e)}")
|
||||
|
||||
def update_images_display(self):
|
||||
"""更新已上传图片的显示"""
|
||||
# 清空当前显示
|
||||
for widget in self.images_display_frame.winfo_children():
|
||||
widget.destroy()
|
||||
|
||||
# 显示每张图片
|
||||
for i, img_info in enumerate(self.uploaded_images):
|
||||
# 创建图片框架
|
||||
img_frame = ctk.CTkFrame(self.images_display_frame)
|
||||
img_frame.pack(fill="x", padx=5, pady=5)
|
||||
|
||||
# 缩放图片用于显示
|
||||
display_image = self.resize_image_for_display(img_info['image'], 100, 100)
|
||||
display_image = cv2.cvtColor(display_image, cv2.COLOR_BGR2RGB)
|
||||
pil_image = Image.fromarray(display_image)
|
||||
tk_image = ImageTk.PhotoImage(pil_image)
|
||||
|
||||
# 图片标签（可点击预览）
|
||||
img_label = ctk.CTkLabel(img_frame, image=tk_image, text="")
|
||||
img_label.image = tk_image # 保持引用
|
||||
img_label.pack(side="left", padx=10, pady=10)
|
||||
img_label.bind("<Button-1>", lambda e, idx=i: self.preview_image(idx))
|
||||
|
||||
# 信息框架
|
||||
info_frame = ctk.CTkFrame(img_frame)
|
||||
info_frame.pack(side="left", fill="both", expand=True, padx=10, pady=10)
|
||||
|
||||
# 文件名
|
||||
name_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=f"文件名: {img_info['name']}",
|
||||
anchor="w"
|
||||
)
|
||||
name_label.pack(fill="x", padx=5, pady=2)
|
||||
|
||||
# 状态和真实类别
|
||||
if img_info['recognized'] and img_info.get('result'):
|
||||
result = img_info['result']
|
||||
is_correct = result.get('is_correct')
|
||||
if is_correct is True:
|
||||
status = "已识别 ✓"
|
||||
status_color = "green"
|
||||
elif is_correct is False:
|
||||
status = "已识别 ✗"
|
||||
status_color = "red"
|
||||
else:
|
||||
status = "已识别 ?"
|
||||
status_color = "orange"
|
||||
else:
|
||||
status = "未识别"
|
||||
status_color = None
|
||||
|
||||
status_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=f"状态: {status}",
|
||||
anchor="w",
|
||||
text_color=status_color
|
||||
)
|
||||
status_label.pack(fill="x", padx=5, pady=2)
|
||||
|
||||
# 显示真实类别（如果有）
|
||||
true_class = img_info.get('true_class')
|
||||
if true_class:
|
||||
true_class_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=f"真实类别: {true_class}",
|
||||
anchor="w",
|
||||
font=("Arial", 10)
|
||||
)
|
||||
true_class_label.pack(fill="x", padx=5, pady=1)
|
||||
|
||||
# 删除按钮
|
||||
delete_button = ctk.CTkButton(
|
||||
img_frame,
|
||||
text="删除",
|
||||
command=lambda idx=i: self.remove_image(idx),
|
||||
width=60,
|
||||
height=30,
|
||||
fg_color="red",
|
||||
hover_color="darkred"
|
||||
)
|
||||
delete_button.pack(side="right", padx=10, pady=10)
|
||||
|
||||
def preview_image(self, index):
|
||||
"""预览图片"""
|
||||
if index >= len(self.uploaded_images):
|
||||
return
|
||||
|
||||
img_info = self.uploaded_images[index]
|
||||
|
||||
# 创建预览窗口
|
||||
preview_window = ctk.CTkToplevel(self.root)
|
||||
preview_window.title(f"预览 - {img_info['name']}")
|
||||
preview_window.geometry("800x600")
|
||||
|
||||
# 设置窗口属性，确保在主窗口上方
|
||||
preview_window.transient(self.root) # 设置为主窗口的子窗口
|
||||
preview_window.grab_set() # 设置为模态窗口
|
||||
preview_window.lift() # 提升到最前面
|
||||
preview_window.focus_set() # 设置焦点
|
||||
|
||||
# 居中显示
|
||||
preview_window.update_idletasks()
|
||||
x = (preview_window.winfo_screenwidth() // 2) - (800 // 2)
|
||||
y = (preview_window.winfo_screenheight() // 2) - (600 // 2)
|
||||
preview_window.geometry(f"800x600+{x}+{y}")
|
||||
|
||||
# 显示图片
|
||||
display_image = self.resize_image_for_display(img_info['image'], 750, 550)
|
||||
display_image = cv2.cvtColor(display_image, cv2.COLOR_BGR2RGB)
|
||||
pil_image = Image.fromarray(display_image)
|
||||
tk_image = ImageTk.PhotoImage(pil_image)
|
||||
|
||||
img_label = ctk.CTkLabel(preview_window, image=tk_image, text="")
|
||||
img_label.image = tk_image
|
||||
img_label.pack(expand=True, padx=20, pady=20)
|
||||
|
||||
def remove_image(self, index):
|
||||
"""删除图片"""
|
||||
if index < len(self.uploaded_images):
|
||||
self.uploaded_images.pop(index)
|
||||
self.update_images_display()
|
||||
self.update_recognize_button()
|
||||
self.update_results_display()
|
||||
|
||||
def clear_images(self):
|
||||
"""清空所有图片"""
|
||||
if self.uploaded_images:
|
||||
result = messagebox.askyesno("确认", "确定要清空所有图片吗？")
|
||||
if result:
|
||||
self.uploaded_images.clear()
|
||||
self.current_results.clear()
|
||||
# 重置识别时间
|
||||
self.recognition_start_time = None
|
||||
self.recognition_duration = 0
|
||||
self.update_images_display()
|
||||
self.update_recognize_button()
|
||||
self.update_results_display()
|
||||
self.update_stats()
|
||||
|
||||
def update_recognize_button(self):
|
||||
"""更新识别按钮状态"""
|
||||
if self.uploaded_images:
|
||||
self.recognize_button.configure(state="normal")
|
||||
else:
|
||||
self.recognize_button.configure(state="disabled")
|
||||
|
||||
def start_recognition(self):
|
||||
"""开始识别"""
|
||||
if not self.uploaded_images:
|
||||
messagebox.showinfo("提示", "请先上传图片")
|
||||
return
|
||||
|
||||
# 记录识别开始时间
|
||||
self.recognition_start_time = time.time()
|
||||
|
||||
# 在新线程中执行识别，避免界面卡顿
|
||||
self.recognize_button.configure(state="disabled", text="识别中...")
|
||||
threading.Thread(target=self.recognize_images, daemon=True).start()
|
||||
|
||||
def recognize_images(self):
|
||||
"""识别所有图片"""
|
||||
try:
|
||||
self.current_results.clear()
|
||||
|
||||
for i, img_info in enumerate(self.uploaded_images):
|
||||
# 使用embedding相似度识别
|
||||
if self.model is not None and self.faiss_index is not None:
|
||||
# 使用真实的embedding模型和FAISS索引
|
||||
predicted_class, confidence, similar_images = self.predict_with_embedding(img_info['image'])
|
||||
else:
|
||||
# 模拟预测结果
|
||||
predicted_class = np.random.choice(self.class_names)
|
||||
confidence = np.random.uniform(0.6, 0.95)
|
||||
similar_images = []
|
||||
|
||||
# 自动判断识别是否正确
|
||||
true_class = img_info.get('true_class')
|
||||
is_correct = None
|
||||
if true_class is not None:
|
||||
is_correct = (predicted_class == true_class)
|
||||
|
||||
# 保存结果
|
||||
result = {
|
||||
'image_index': i,
|
||||
'image_name': img_info['name'],
|
||||
'predicted_class': predicted_class,
|
||||
'confidence': confidence,
|
||||
'true_class': true_class,
|
||||
'is_correct': is_correct,
|
||||
'similar_images': similar_images # 相似图片列表
|
||||
}
|
||||
|
||||
self.current_results.append(result)
|
||||
img_info['recognized'] = True
|
||||
img_info['result'] = result
|
||||
|
||||
# 更新UI（在主线程中）
|
||||
self.root.after(0, self.update_progress, i + 1, len(self.uploaded_images))
|
||||
|
||||
# 识别完成，更新UI
|
||||
self.root.after(0, self.recognition_completed)
|
||||
|
||||
except Exception as e:
|
||||
self.root.after(0, lambda: messagebox.showerror("错误", f"识别过程中出错: {str(e)}"))
|
||||
self.root.after(0, self.recognition_completed)
|
||||
|
||||
def predict_with_embedding(self, image, k=5):
|
||||
"""使用embedding模型和FAISS索引进行预测"""
|
||||
try:
|
||||
# 将OpenCV图像转换为PIL图像
|
||||
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
||||
pil_image = Image.fromarray(image_rgb)
|
||||
|
||||
# 提取查询图片的特征向量
|
||||
query_embedding = self.model.extract_embedding(pil_image, normalize=True)
|
||||
query_embedding = query_embedding.reshape(1, -1).astype(np.float32)
|
||||
|
||||
# 在FAISS索引中搜索最相似的k张图片
|
||||
scores, indices = self.faiss_index.search(query_embedding, k)
|
||||
|
||||
# 收集相似图片的类别
|
||||
similar_classes = []
|
||||
similar_images = []
|
||||
|
||||
for i in range(k):
|
||||
if i < len(indices[0]) and indices[0][i] < len(self.labels):
|
||||
idx = indices[0][i]
|
||||
score = scores[0][i]
|
||||
class_idx = self.labels[idx]
|
||||
class_name = self.class_names[class_idx]
|
||||
image_path = self.image_paths[idx]
|
||||
|
||||
similar_classes.append(class_name)
|
||||
similar_images.append({
|
||||
'path': image_path,
|
||||
'class': class_name,
|
||||
'score': float(score)
|
||||
})
|
||||
|
||||
# 使用投票机制确定最终预测类别
|
||||
if similar_classes:
|
||||
class_counts = Counter(similar_classes)
|
||||
predicted_class = class_counts.most_common(1)[0][0]
|
||||
|
||||
# 计算置信度（基于最高相似度分数和投票比例）
|
||||
max_score = float(scores[0][0]) if len(scores[0]) > 0 else 0.0
|
||||
vote_ratio = class_counts[predicted_class] / len(similar_classes)
|
||||
confidence = max_score * vote_ratio
|
||||
|
||||
return predicted_class, confidence, similar_images
|
||||
else:
|
||||
# 如果没有找到相似图片，随机选择一个类别
|
||||
predicted_class = np.random.choice(self.class_names)
|
||||
confidence = 0.1
|
||||
return predicted_class, confidence, []
|
||||
|
||||
except Exception as e:
|
||||
print(f"Embedding预测出错: {e}")
|
||||
# 返回随机结果作为备选
|
||||
predicted_class = np.random.choice(self.class_names)
|
||||
confidence = np.random.uniform(0.1, 0.3)
|
||||
return predicted_class, confidence, []
|
||||
|
||||
def update_progress(self, current, total):
|
||||
"""更新识别进度"""
|
||||
self.recognize_button.configure(text=f"识别中... ({current}/{total})")
|
||||
self.update_images_display()
|
||||
self.update_results_display()
|
||||
|
||||
def recognition_completed(self):
|
||||
"""识别完成"""
|
||||
# 计算识别耗时
|
||||
if self.recognition_start_time is not None:
|
||||
self.recognition_duration = time.time() - self.recognition_start_time
|
||||
|
||||
self.recognize_button.configure(state="normal", text="开始识别")
|
||||
self.update_stats()
|
||||
messagebox.showinfo("完成", f"所有图片识别完成！识别耗时: {self.recognition_duration:.2f}秒")
|
||||
|
||||
def resize_image_for_display(self, image, max_width, max_height):
|
||||
"""调整图片大小用于显示"""
|
||||
height, width = image.shape[:2]
|
||||
scale = min(max_width / width, max_height / height)
|
||||
|
||||
if scale < 1:
|
||||
new_width = int(width * scale)
|
||||
new_height = int(height * scale)
|
||||
return cv2.resize(image, (new_width, new_height))
|
||||
|
||||
return image
|
||||
|
||||
def update_results_display(self):
|
||||
"""更新识别结果显示"""
|
||||
# 清空当前显示
|
||||
for widget in self.results_display_frame.winfo_children():
|
||||
widget.destroy()
|
||||
|
||||
if not self.current_results:
|
||||
no_result_label = ctk.CTkLabel(
|
||||
self.results_display_frame,
|
||||
text="暂无识别结果",
|
||||
font=("Arial", 14),
|
||||
text_color="gray"
|
||||
)
|
||||
no_result_label.pack(pady=20)
|
||||
return
|
||||
|
||||
# 显示每个识别结果
|
||||
for i, result in enumerate(self.current_results):
|
||||
# 结果框架
|
||||
result_frame = ctk.CTkFrame(self.results_display_frame)
|
||||
result_frame.pack(fill="x", padx=5, pady=5)
|
||||
|
||||
# 获取原始图片
|
||||
img_info = self.uploaded_images[result['image_index']]
|
||||
display_image = self.resize_image_for_display(img_info['image'], 120, 120)
|
||||
display_image = cv2.cvtColor(display_image, cv2.COLOR_BGR2RGB)
|
||||
pil_image = Image.fromarray(display_image)
|
||||
tk_image = ImageTk.PhotoImage(pil_image)
|
||||
|
||||
# 图片标签
|
||||
img_label = ctk.CTkLabel(result_frame, image=tk_image, text="")
|
||||
img_label.image = tk_image
|
||||
img_label.pack(side="left", padx=10, pady=10)
|
||||
img_label.bind("<Button-1>", lambda e, idx=result['image_index']: self.preview_image(idx))
|
||||
|
||||
# 信息框架
|
||||
info_frame = ctk.CTkFrame(result_frame)
|
||||
info_frame.pack(side="left", fill="both", expand=True, padx=10, pady=10)
|
||||
|
||||
# 文件名
|
||||
name_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=f"文件: {result['image_name']}",
|
||||
anchor="w",
|
||||
font=("Arial", 12, "bold")
|
||||
)
|
||||
name_label.pack(fill="x", padx=5, pady=2)
|
||||
|
||||
# 识别结果标题
|
||||
result_title_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text="识别结果 (基于相似度):",
|
||||
anchor="w",
|
||||
font=("Arial", 11)
|
||||
)
|
||||
result_title_label.pack(fill="x", padx=5, pady=(2, 0))
|
||||
|
||||
# 识别结果内容（大字体、加粗，颜色根据正确性决定）
|
||||
is_correct = result.get('is_correct')
|
||||
if is_correct is True:
|
||||
result_color = "green" # 识别正确显示绿色
|
||||
elif is_correct is False:
|
||||
result_color = "red" # 识别错误显示红色
|
||||
else:
|
||||
result_color = "orange" # 无法判断显示橙色
|
||||
|
||||
result_content_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=result['predicted_class'],
|
||||
anchor="w",
|
||||
font=("Arial", 18, "bold"),
|
||||
text_color=result_color
|
||||
)
|
||||
result_content_label.pack(fill="x", padx=5, pady=(0, 2))
|
||||
|
||||
# 置信度
|
||||
confidence_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=f"相似度得分: {result['confidence']:.3f}",
|
||||
anchor="w",
|
||||
font=("Arial", 11)
|
||||
)
|
||||
confidence_label.pack(fill="x", padx=5, pady=2)
|
||||
|
||||
# 真实类别
|
||||
true_class = result.get('true_class')
|
||||
if true_class is not None:
|
||||
true_class_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=f"真实类别: {true_class}",
|
||||
anchor="w",
|
||||
font=("Arial", 11)
|
||||
)
|
||||
true_class_label.pack(fill="x", padx=5, pady=2)
|
||||
|
||||
# 自动判断结果
|
||||
is_correct = result.get('is_correct')
|
||||
if is_correct is not None:
|
||||
if is_correct:
|
||||
status_text = "✓ 识别正确"
|
||||
status_color = "green"
|
||||
else:
|
||||
status_text = "✗ 识别错误"
|
||||
status_color = "red"
|
||||
|
||||
status_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=status_text,
|
||||
anchor="w",
|
||||
font=("Arial", 12, "bold"),
|
||||
text_color=status_color
|
||||
)
|
||||
status_label.pack(fill="x", padx=5, pady=5)
|
||||
else:
|
||||
# 如果无法自动判断，显示未知状态
|
||||
status_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text="? 无法自动判断（路径中未包含已知类别）",
|
||||
anchor="w",
|
||||
font=("Arial", 11),
|
||||
text_color="orange"
|
||||
)
|
||||
status_label.pack(fill="x", padx=5, pady=5)
|
||||
|
||||
# 显示相似图片信息（如果有）
|
||||
similar_images = result.get('similar_images', [])
|
||||
if similar_images:
|
||||
similar_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=f"基于前{len(similar_images)}张最相似图片的投票结果",
|
||||
anchor="w",
|
||||
font=("Arial", 10),
|
||||
text_color="gray"
|
||||
)
|
||||
similar_label.pack(fill="x", padx=5, pady=(5, 2))
|
||||
|
||||
# 显示前3张最相似的图片信息
|
||||
for j, sim_img in enumerate(similar_images[:3]):
|
||||
sim_info = f" {j+1}. {sim_img['class']} (相似度: {sim_img['score']:.3f})"
|
||||
sim_info_label = ctk.CTkLabel(
|
||||
info_frame,
|
||||
text=sim_info,
|
||||
anchor="w",
|
||||
font=("Arial", 9),
|
||||
text_color="gray"
|
||||
)
|
||||
sim_info_label.pack(fill="x", padx=15, pady=1)
|
||||
|
||||
def update_stats(self):
|
||||
"""更新统计信息"""
|
||||
total_images = len(self.uploaded_images)
|
||||
recognized_images = len(self.current_results)
|
||||
|
||||
# 计算准确率（基于自动判断的结果）
|
||||
auto_judged_results = [r for r in self.current_results if r.get('is_correct') is not None]
|
||||
if auto_judged_results:
|
||||
correct_count = sum(1 for r in auto_judged_results if r['is_correct'])
|
||||
accuracy = (correct_count / len(auto_judged_results)) * 100
|
||||
|
||||
# 构建统计文本，包含识别时间
|
||||
if self.recognition_duration > 0:
|
||||
stats_text = f"总图片: {total_images} | 已识别: {recognized_images} | 可判断: {len(auto_judged_results)} | 识别时间: {self.recognition_duration:.2f}秒 | 平均准确率: {accuracy:.1f}%"
|
||||
else:
|
||||
stats_text = f"总图片: {total_images} | 已识别: {recognized_images} | 可判断: {len(auto_judged_results)} | 平均准确率: {accuracy:.1f}%"
|
||||
else:
|
||||
# 如果没有可自动判断的结果
|
||||
if self.recognition_duration > 0:
|
||||
stats_text = f"总图片: {total_images} | 已识别: {recognized_images} | 可判断: 0 | 识别时间: {self.recognition_duration:.2f}秒 | 平均准确率: 0%"
|
||||
else:
|
||||
stats_text = f"总图片: {total_images} | 已识别: {recognized_images} | 可判断: 0 | 平均准确率: 0%"
|
||||
|
||||
self.stats_label.configure(text=stats_text)
|
||||
|
||||
|
||||
def main():
|
||||
# 创建支持拖放的窗口
|
||||
root = TkinterDnD.Tk()
|
||||
app = EmbeddingFoodClassifierApp(root)
|
||||
root.mainloop()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user