ConvNeXt V2による画像分類（入力：動画像）（ImageNet 1000クラス）（ソースコードと説明と利用ガイド）

REM Python をシステム領域にインストール
winget install --scope machine --id Python.Python.3.12 -e --silent
REM Python のパス設定
set "PYTHON_PATH=C:\Program Files\Python312"
set "PYTHON_SCRIPTS_PATH=C:\Program Files\Python312\Scripts"
echo "%PATH%" | find /i "%PYTHON_PATH%" >nul
if errorlevel 1 setx PATH "%PATH%;%PYTHON_PATH%" /M >nul
echo "%PATH%" | find /i "%PYTHON_SCRIPTS_PATH%" >nul
if errorlevel 1 setx PATH "%PATH%;%PYTHON_SCRIPTS_PATH%" /M >nul

winget install --scope machine Codeium.Windsurf -e --silent

"""
プログラム名: ConvNeXt V2による画像分類プログラム（ImageNet 1000クラス）
特徴技術名: ConvNeXt V2
出典: Woo, S., et al. (2023). ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders.
      CVPR 2023. https://arxiv.org/abs/2301.00808
特徴機能: Global Response Normalization (GRN) - チャネル間の特徴競合を強化し、
          Masked Autoencoder (MAE) による自己教師あり事前学習で表現力を向上
学習済みモデル: convnextv2_base.fcmae_ft_in22k_in1k（timm実装版、ImageNet-22k→1k事前学習済み、約89Mパラメータ）
               URL: https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k
特徴技術および学習済モデルの利用制限: **CC BY-NC 4.0ライセンス（非商用利用のみ）。商用利用には制限があります。必ず利用者自身で利用制限を確認すること。**
方式設計:
  関連利用技術:
    - timm（PyTorch Image Models）: 学習済みモデル提供
    - OpenCV: 動画・カメラ入力とリアルタイム表示
    - PIL/Pillow: 画像前処理と日本語フォント描画
    - tkinter: ファイル選択UI
  入力と出力: 入力: 動画（ユーザは「0:動画ファイル，1:カメラ，2:サンプル動画」のメニューで選択．0:動画ファイルの場合はtkinterでファイル選択．1の場合はOpenCVでカメラが開く．2の場合はhttps://raw.githubusercontent.com/opencv/opencv/master/samples/data/vtest.aviを使用）、出力: OpenCV画面でリアルタイム表示、各フレームごとにprint()による分類結果表示、プログラム終了時result.txtファイル保存
  処理手順: 1.動画入力の取得・前処理（RGB変換、timm標準変換）→2.ConvNeXt V2モデルによる推論実行→3.Top-5分類結果の算出・日本語表示→4.リアルタイム画面描画・結果保存
  前処理、後処理: 前処理：timm標準データ変換（正規化、リサイズ）によるImageNet互換形式変換、後処理：ソフトマックス確率変換、Top-k選択、日本語フォント描画
  調整を必要とする設定値: MODEL_NAME（学習済みモデル選択）、TOP_K（表示する上位分類結果数、デフォルト5）、FONT_SIZE（表示サイズ）
将来方策: プログラム内でのモデル性能比較機能（複数ConvNeXt V2モデルの精度・速度測定）
その他の重要事項: Windows環境対応、DirectShowバックエンド使用（Windows環境時）、ImageNet-1000クラス全て分類可能
前準備:
pip install -U torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
pip install timm opencv-python pillow
"""
import cv2
import numpy as np
import torch
import timm
import torch.nn.functional as F
import tkinter as tk
from tkinter import filedialog
from PIL import Image, ImageDraw, ImageFont
import urllib.request
import time
import sys
import io
from datetime import datetime
import threading

# Windows文字エンコーディング設定
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', line_buffering=True)

# GPU/CPU自動選択
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f'デバイス: {str(device)}')

# GPU使用時の最適化
if device.type == 'cuda':
    torch.backends.cudnn.benchmark = True

# モデル情報の構造化
MODEL_INFO = {
    'convnextv2_base.fcmae_ft_in22k_in1k': {
        'name': 'ConvNeXt V2 Base',
        'params': '89M',
        'top1_acc': '86.8%',
        'desc': 'デフォルト推奨モデル'
    },
    'convnextv2_tiny.fcmae_ft_in22k_in1k': {
        'name': 'ConvNeXt V2 Tiny',
        'params': '29M',
        'top1_acc': '83.0%',
        'desc': '軽量'
    },
    'convnextv2_nano.fcmae_ft_in22k_in1k': {
        'name': 'ConvNeXt V2 Nano',
        'params': '15M',
        'top1_acc': '82.0%',
        'desc': '超軽量'
    },
    'convnextv2_large.fcmae_ft_in22k_in1k_384': {
        'name': 'ConvNeXt V2 Large',
        'params': '198M',
        'top1_acc': '87.3%',
        'desc': '高精度'
    }
}

# 調整可能な設定値
MODEL_NAME = 'convnextv2_base.fcmae_ft_in22k_in1k'
TOP_K = 5
FONT_PATH = 'C:/Windows/Fonts/meiryo.ttc'
FONT_SIZE = 18
WINDOW_NAME = "ImageNet 1000-Class Classification"

# ImageNet クラス名リスト
IMAGENET_CLASSES = [
    'tench', 'goldfish', 'great white shark', 'tiger shark', 'hammerhead', 'electric ray', 'stingray', 'cock', 'hen', 'ostrich',
    'brambling', 'goldfinch', 'house finch', 'junco', 'indigo bunting', 'robin', 'bulbul', 'jay', 'magpie', 'chickadee',
    'water ouzel', 'kite', 'bald eagle', 'vulture', 'great grey owl', 'European fire salamander', 'common newt', 'eft', 'spotted salamander', 'axolotl',
    'bullfrog', 'tree frog', 'tailed frog', 'loggerhead', 'leatherback turtle', 'mud turtle', 'terrapin', 'box turtle', 'banded gecko', 'common iguana',
    'American chameleon', 'whiptail', 'agama', 'frilled lizard', 'alligator lizard', 'Gila monster', 'green lizard', 'African chameleon', 'Komodo dragon', 'African crocodile',
    'American alligator', 'triceratops', 'thunder snake', 'ringneck snake', 'hognose snake', 'green snake', 'king snake', 'garter snake', 'water snake', 'vine snake',
    'night snake', 'boa constrictor', 'rock python', 'Indian cobra', 'green mamba', 'sea snake', 'horned viper', 'diamondback', 'sidewinder', 'trilobite',
    'harvestman', 'scorpion', 'black and gold garden spider', 'barn spider', 'garden spider', 'black widow', 'tarantula', 'wolf spider', 'tick', 'centipede',
    'black grouse', 'ptarmigan', 'ruffed grouse', 'prairie chicken', 'peacock', 'quail', 'partridge', 'African grey', 'macaw', 'sulphur-crested cockatoo',
    'lorikeet', 'coucal', 'bee eater', 'hornbill', 'hummingbird', 'jacamar', 'toucan', 'drake', 'red-breasted merganser', 'goose',
    'black swan', 'tusker', 'echidna', 'platypus', 'wallaby', 'koala', 'wombat', 'jellyfish', 'sea anemone', 'brain coral',
    'flatworm', 'nematode', 'conch', 'snail', 'slug', 'sea slug', 'chiton', 'chambered nautilus', 'Dungeness crab', 'rock crab',
    'fiddler crab', 'king crab', 'American lobster', 'spiny lobster', 'crayfish', 'hermit crab', 'isopod', 'white stork', 'black stork', 'spoonbill',
    'flamingo', 'little blue heron', 'American egret', 'bittern', 'crane', 'limpkin', 'European gallinule', 'American coot', 'bustard', 'ruddy turnstone',
    'red-backed sandpiper', 'redshank', 'dowitcher', 'oystercatcher', 'pelican', 'king penguin', 'albatross', 'grey whale', 'killer whale', 'dugong',
    'sea lion', 'Chihuahua', 'Japanese spaniel', 'Maltese dog', 'Pekinese', 'Shih-Tzu', 'Blenheim spaniel', 'papillon', 'toy terrier', 'Rhodesian ridgeback',
    'Afghan hound', 'basset', 'beagle', 'bloodhound', 'bluetick', 'black-and-tan coonhound', 'Walker hound', 'English foxhound', 'redbone', 'borzoi',
    'Irish wolfhound', 'Italian greyhound', 'whippet', 'Ibizan hound', 'Norwegian elkhound', 'otterhound', 'Saluki', 'Scottish deerhound', 'Weimaraner', 'Staffordshire bullterrier',
    'American Staffordshire terrier', 'Bedlington terrier', 'Border terrier', 'Kerry blue terrier', 'Irish terrier', 'Norfolk terrier', 'Norwich terrier', 'Yorkshire terrier', 'wire-haired fox terrier', 'Lakeland terrier',
    'Sealyham terrier', 'Airedale', 'cairn', 'Australian terrier', 'Dandie Dinmont', 'Boston bull', 'miniature schnauzer', 'giant schnauzer', 'standard schnauzer', 'Scotch terrier',
    'Tibetan terrier', 'silky terrier', 'soft-coated wheaten terrier', 'West Highland white terrier', 'Lhasa', 'flat-coated retriever', 'curly-coated retriever', 'golden retriever', 'Labrador retriever', 'Chesapeake Bay retriever',
    'German short-haired pointer', 'vizsla', 'English setter', 'Irish setter', 'Gordon setter', 'Brittany spaniel', 'clumber', 'English springer', 'Welsh springer spaniel', 'cocker spaniel',
    'Sussex spaniel', 'Irish water spaniel', 'kuvasz', 'schipperke', 'groenendael', 'malinois', 'briard', 'kelpie', 'komondor', 'Old English sheepdog',
    'Shetland sheepdog', 'collie', 'Border collie', 'Bouvier des Flandres', 'Rottweiler', 'German shepherd', 'Doberman', 'miniature pinscher', 'Greater Swiss Mountain dog', 'Bernese mountain dog',
    'Appenzeller', 'EntleBucher', 'boxer', 'bull mastiff', 'Tibetan mastiff', 'French bulldog', 'Great Dane', 'Saint Bernard', 'Eskimo dog', 'malamute',
    'Siberian husky', 'dalmatian', 'affenpinscher', 'basenji', 'pug', 'Leonberg', 'Newfoundland', 'Great Pyrenees', 'Samoyed', 'Pomeranian',
    'chow', 'keeshond', 'Brabancon griffon', 'Pembroke', 'Cardigan', 'toy poodle', 'miniature poodle', 'standard poodle', 'Mexican hairless', 'timber wolf',
    'white wolf', 'red wolf', 'coyote', 'dingo', 'dhole', 'African hunting dog', 'hyena', 'red fox', 'kit fox', 'Arctic fox',
    'grey fox', 'tabby', 'tiger cat', 'Persian cat', 'Siamese cat', 'Egyptian cat', 'cougar', 'lynx', 'leopard', 'snow leopard',
    'jaguar', 'lion', 'tiger', 'cheetah', 'brown bear', 'American black bear', 'ice bear', 'sloth bear', 'mongoose', 'meerkat',
    'tiger beetle', 'ladybug', 'ground beetle', 'long-horned beetle', 'leaf beetle', 'dung beetle', 'rhinoceros beetle', 'weevil', 'fly', 'bee',
    'ant', 'grasshopper', 'cricket', 'walking stick', 'cockroach', 'mantis', 'cicada', 'leafhopper', 'lacewing', 'dragonfly',
    'damselfly', 'admiral', 'ringlet', 'monarch', 'cabbage butterfly', 'sulphur butterfly', 'lycaenid', 'starfish', 'sea urchin', 'sea cucumber',
    'wood rabbit', 'hare', 'Angora', 'hamster', 'porcupine', 'fox squirrel', 'marmot', 'beaver', 'guinea pig', 'sorrel',
    'zebra', 'hog', 'wild boar', 'warthog', 'hippopotamus', 'ox', 'water buffalo', 'bison', 'ram', 'bighorn',
    'ibex', 'hartebeest', 'impala', 'gazelle', 'Arabian camel', 'llama', 'weasel', 'mink', 'polecat', 'black-footed ferret',
    'otter', 'skunk', 'badger', 'armadillo', 'three-toed sloth', 'orangutan', 'gorilla', 'chimpanzee', 'gibbon', 'siamang',
    'guenon', 'patas', 'baboon', 'macaque', 'langur', 'colobus', 'proboscis monkey', 'marmoset', 'capuchin', 'howler monkey',
    'titi', 'spider monkey', 'squirrel monkey', 'Madagascar cat', 'indri', 'Indian elephant', 'African elephant', 'lesser panda', 'giant panda', 'barracouta',
    'eel', 'coho', 'rock beauty', 'anemone fish', 'sturgeon', 'gar', 'lionfish', 'puffer', 'abacus', 'abaya',
    'academic gown', 'accordion', 'acoustic guitar', 'aircraft carrier', 'airliner', 'airship', 'altar', 'ambulance', 'amphibian', 'analog clock',
    'apiary', 'apron', 'ashcan', 'assault rifle', 'backpack', 'bakery', 'balance beam', 'balloon', 'ballpoint', 'Band Aid',
    'banjo', 'bannister', 'barbell', 'barber chair', 'barbershop', 'barn', 'barometer', 'barrel', 'barrow', 'baseball',
    'basketball', 'bassinet', 'bassoon', 'bathing cap', 'bath towel', 'bathtub', 'beach wagon', 'beacon', 'beaker', 'bearskin',
    'beer bottle', 'beer glass', 'bell cote', 'bib', 'bicycle-built-for-two', 'bikini', 'binder', 'binoculars', 'birdhouse', 'boathouse',
    'bobsled', 'bolo tie', 'bonnet', 'bookcase', 'bookshop', 'bottlecap', 'bow', 'bow tie', 'brass', 'brassiere',
    'breakwater', 'breastplate', 'broom', 'bucket', 'buckle', 'bulletproof vest', 'bullet train', 'butcher shop', 'cab', 'caldron',
    'candle', 'cannon', 'canoe', 'can opener', 'cardigan', 'car mirror', 'carousel', 'carpenter\'s kit', 'carton', 'car wheel',
    'cash machine', 'cassette', 'cassette player', 'castle', 'catamaran', 'CD player', 'cello', 'cellular telephone', 'chain', 'chainlink fence',
    'chain mail', 'chain saw', 'chest', 'chiffonier', 'chime', 'china cabinet', 'Christmas stocking', 'church', 'cinema', 'cleaver',
    'cliff dwelling', 'cloak', 'clog', 'cocktail shaker', 'coffee mug', 'coffeepot', 'coil', 'combination lock', 'computer keyboard', 'confectionery',
    'container ship', 'convertible', 'corkscrew', 'cornet', 'cowboy boot', 'cowboy hat', 'cradle', 'crane', 'crash helmet', 'crate',
    'crib', 'Crock Pot', 'croquet ball', 'crutch', 'cuirass', 'dam', 'desk', 'desktop computer', 'dial telephone', 'diaper',
    'digital clock', 'digital watch', 'dining table', 'dishrag', 'dishwasher', 'disk brake', 'dock', 'dogsled', 'dome', 'doormat',
    'drilling platform', 'drum', 'drumstick', 'dumbbell', 'Dutch oven', 'electric fan', 'electric guitar', 'electric locomotive', 'entertainment center', 'envelope',
    'espresso maker', 'face powder', 'feather boa', 'file', 'fireboat', 'fire engine', 'fire screen', 'flagpole', 'flute', 'folding chair',
    'football helmet', 'forklift', 'fountain', 'fountain pen', 'four-poster', 'freight car', 'French horn', 'frying pan', 'fur coat', 'garbage truck',
    'gasmask', 'gas pump', 'goblet', 'go-kart', 'golf ball', 'golfcart', 'gondola', 'gong', 'gown', 'grand piano',
    'greenhouse', 'grille', 'grocery store', 'guillotine', 'hair slide', 'hair spray', 'half track', 'hammer', 'hamper', 'hand blower',
    'hand-held computer', 'handkerchief', 'hard disc', 'harmonica', 'harp', 'harvester', 'hatchet', 'holster', 'home theater', 'honeycomb',
    'hook', 'hoopskirt', 'horizontal bar', 'horse cart', 'hourglass', 'iPod', 'iron', 'jack-o\'-lantern', 'jean', 'jeep',
    'jersey', 'jigsaw puzzle', 'jinrikisha', 'joystick', 'kimono', 'knee pad', 'knot', 'lab coat', 'ladle', 'lampshade',
    'laptop', 'lawn mower', 'lens cap', 'letter opener', 'library', 'lifeboat', 'lighter', 'limousine', 'liner', 'lipstick',
    'Loafer', 'lotion', 'loudspeaker', 'loupe', 'lumbermill', 'magnetic compass', 'mailbag', 'mailbox', 'maillot', 'maillot (tank suit)',
    'manhole cover', 'maraca', 'marimba', 'mask', 'matchstick', 'maypole', 'maze', 'measuring cup', 'medicine chest', 'megalith',
    'microphone', 'microwave', 'military uniform', 'milk can', 'minibus', 'miniskirt', 'minivan', 'missile', 'mitten', 'mixing bowl',
    'mobile home', 'Model T', 'modem', 'monastery', 'monitor', 'moped', 'mortar', 'mortarboard', 'mosque', 'mosquito net',
    'motor scooter', 'mountain bike', 'mountain tent', 'mouse', 'mousetrap', 'moving van', 'muzzle', 'nail', 'neck brace', 'necklace',
    'nipple', 'notebook', 'obelisk', 'oboe', 'ocarina', 'odometer', 'oil filter', 'organ', 'oscilloscope', 'overskirt',
    'oxcart', 'oxygen mask', 'packet', 'paddle', 'paddlewheel', 'padlock', 'paintbrush', 'pajama', 'palace', 'panpipe',
    'paper towel', 'parachute', 'parallel bars', 'park bench', 'parking meter', 'passenger car', 'patio', 'pay-phone', 'pedestal', 'pencil box',
    'pencil sharpener', 'perfume', 'Petri dish', 'photocopier', 'pick', 'pickelhaube', 'picket fence', 'pickup', 'pier', 'piggy bank',
    'pill bottle', 'pillow', 'ping-pong ball', 'pinwheel', 'pirate', 'pitcher', 'plane', 'planetarium', 'plastic bag', 'plate rack',
    'plow', 'plunger', 'Polaroid camera', 'pole', 'police van', 'poncho', 'pool table', 'pop bottle', 'pot', 'potter\'s wheel',
    'power drill', 'prayer rug', 'printer', 'prison', 'projectile', 'projector', 'puck', 'punching bag', 'purse', 'quill',
    'quilt', 'racer', 'racket', 'radiator', 'radio', 'radio telescope', 'rain barrel', 'recreational vehicle', 'reel', 'reflex camera',
    'refrigerator', 'remote control', 'restaurant', 'revolver', 'rifle', 'rocking chair', 'rotisserie', 'rubber eraser', 'rugby ball', 'rule',
    'running shoe', 'safe', 'safety pin', 'saltshaker', 'sandal', 'sarong', 'sax', 'scabbard', 'scale', 'school bus',
    'schooner', 'scoreboard', 'screen', 'screw', 'screwdriver', 'seat belt', 'sewing machine', 'shield', 'shoe shop', 'shoji',
    'shopping basket', 'shopping cart', 'shovel', 'shower cap', 'shower curtain', 'ski', 'ski mask', 'sleeping bag', 'slide rule', 'sliding door',
    'slot', 'snorkel', 'snowmobile', 'snowplow', 'soap dispenser', 'soccer ball', 'sock', 'solar dish', 'sombrero', 'soup bowl',
    'space bar', 'space heater', 'space shuttle', 'spatula', 'speedboat', 'spider web', 'spindle', 'sports car', 'spotlight', 'stage',
    'steam locomotive', 'steel arch bridge', 'steel drum', 'stethoscope', 'stole', 'stone wall', 'stopwatch', 'stove', 'strainer', 'streetcar',
    'stretcher', 'studio couch', 'stupa', 'submarine', 'suit', 'sundial', 'sunglass', 'sunglasses', 'sunscreen', 'suspension bridge',
    'swab', 'sweatshirt', 'swimming trunks', 'swing', 'switch', 'syringe', 'table lamp', 'tank', 'tape player', 'teapot',
    'teddy', 'television', 'tennis ball', 'thatch', 'theater curtain', 'thimble', 'thresher', 'throne', 'tile roof', 'toaster',
    'tobacco shop', 'toilet seat', 'torch', 'totem pole', 'tow truck', 'toyshop', 'tractor', 'trailer truck', 'tray', 'trench coat',
    'tricycle', 'trimaran', 'tripod', 'triumphal arch', 'trolleybus', 'trombone', 'tub', 'turnstile', 'typewriter keyboard', 'umbrella',
    'unicycle', 'upright', 'vacuum', 'vase', 'vault', 'velvet', 'vending machine', 'vestment', 'viaduct', 'violin',
    'volleyball', 'waffle iron', 'wall clock', 'wallet', 'wardrobe', 'warplane', 'washbasin', 'washer', 'water bottle', 'water jug',
    'water tower', 'whiskey jug', 'whistle', 'wig', 'window screen', 'window shade', 'Windsor tie', 'wine bottle', 'wing', 'wok',
    'wooden spoon', 'wool', 'worm fence', 'wreck', 'yawl', 'yurt', 'web site', 'comic book', 'crossword puzzle', 'street sign',
    'traffic light', 'book jacket', 'menu', 'plate', 'guacamole', 'consomme', 'hot pot', 'trifle', 'ice cream', 'ice lolly',
    'French loaf', 'bagel', 'pretzel', 'cheeseburger', 'hotdog', 'mashed potato', 'head cabbage', 'broccoli', 'cauliflower', 'zucchini',
    'spaghetti squash', 'acorn squash', 'butternut squash', 'cucumber', 'artichoke', 'bell pepper', 'cardoon', 'mushroom', 'Granny Smith', 'strawberry',
    'orange', 'lemon', 'fig', 'pineapple', 'banana', 'jackfruit', 'custard apple', 'pomegranate', 'hay', 'carbonara',
    'chocolate sauce', 'dough', 'meat loaf', 'pizza', 'potpie', 'burrito', 'red wine', 'espresso', 'cup', 'eggnog',
    'alp', 'bubble', 'cliff', 'coral reef', 'geyser', 'lakeside', 'promontory', 'sandbar', 'seashore', 'valley',
    'volcano', 'ballplayer', 'groom', 'scuba diver', 'rapeseed', 'daisy', 'yellow lady\'s slipper', 'corn', 'acorn', 'hip',
    'buckeye', 'coral fungus', 'agaric', 'gyromitra', 'stinkhorn', 'earthstar', 'hen-of-the-woods', 'bolete', 'ear', 'toilet tissue'
]

# BGR→RGB色変換のヘルパー関数
def bgr_to_rgb(color_bgr):
    """BGRカラーをRGBカラーに変換"""
    return (color_bgr[2], color_bgr[1], color_bgr[0])

# クラスごとの色生成（HSVからBGRに変換）
def generate_class_colors(num_classes):
    colors = []
    for i in range(num_classes):
        hue = int(180.0 * i / num_classes)
        hsv = np.uint8([[[hue, 255, 255]]])
        bgr = cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR)[0][0]
        colors.append((int(bgr[0]), int(bgr[1]), int(bgr[2])))
    return colors

# 1000クラス分の色を生成
CLASS_COLORS = generate_class_colors(1000)

# 日本語フォント設定
font_main = ImageFont.truetype(FONT_PATH, FONT_SIZE)

# グローバル変数
frame_count = 0
results_log = []
class_counts = {}
model = None
transforms = None

class ThreadedVideoCapture:
    """スレッド化されたVideoCapture（常に最新フレームを取得）"""
    def __init__(self, src, is_camera=False):
        if is_camera:
            self.cap = cv2.VideoCapture(src, cv2.CAP_DSHOW)
            fourcc = cv2.VideoWriter_fourcc('M', 'J', 'P', 'G')
            self.cap.set(cv2.CAP_PROP_FOURCC, fourcc)
            self.cap.set(cv2.CAP_PROP_FPS, 60)
        else:
            self.cap = cv2.VideoCapture(src)

        self.grabbed, self.frame = self.cap.read()
        self.stopped = False
        self.lock = threading.Lock()
        self.thread = threading.Thread(target=self.update, args=())
        self.thread.daemon = True
        self.thread.start()

    def update(self):
        """バックグラウンドでフレームを取得し続ける"""
        while not self.stopped:
            grabbed, frame = self.cap.read()
            with self.lock:
                self.grabbed = grabbed
                if grabbed:
                    self.frame = frame

    def read(self):
        """最新フレームを返す"""
        with self.lock:
            return self.grabbed, self.frame.copy() if self.grabbed else None

    def isOpened(self):
        return self.cap.isOpened()

    def get(self, prop):
        return self.cap.get(prop)

    def release(self):
        self.stopped = True
        self.thread.join()
        self.cap.release()

def display_program_header():
    print('=' * 60)
    print('=== ConvNeXt V2画像分類プログラム ===')
    print('=' * 60)
    print('概要: ImageNet 1000クラス分類をリアルタイムで実行')
    print('機能: ConvNeXt V2による画像分類（ImageNet 1000クラス）')
    print('技術: Global Response Normalization (GRN), Masked Autoencoder事前学習')
    print('操作: qキーで終了')
    print('出力: 各フレームごとに処理結果を表示し、終了時にresult.txtへ保存')
    print()

def get_confidence_color(prob):
    """確信度に応じた色を返す"""
    if prob >= 0.7:
        return (0, 255, 0)
    elif prob >= 0.5:
        return (0, 255, 255)
    elif prob >= 0.3:
        return (0, 165, 255)
    else:
        return (0, 0, 255)

def draw_classification_results(frame, classifications):
    """画像分類の描画処理"""
    texts_to_draw = []

    texts_to_draw.append({
        'text': f'画像分類結果 (上位{TOP_K}位):',
        'org': (10, 30),
        'color': (255, 255, 255),
        'font_type': 'main'
    })

    for i, cls in enumerate(classifications):
        color = get_confidence_color(cls['conf'])
        result_text = f'{i+1}位: {cls["name"]} ({cls["conf"]:.3f})'

        texts_to_draw.append({
            'text': result_text,
            'org': (10, 60 + i * 25),
            'color': bgr_to_rgb(color),
            'font_type': 'main'
        })

    frame = draw_texts_with_pillow(frame, texts_to_draw)

    info_text = f"Classes: {len(classifications)} | Frame: {frame_count}"
    cv2.putText(frame, info_text, (10, frame.shape[0] - 20),
                cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)

    return frame

def format_classification_output(classifications):
    """画像分類の出力フォーマット"""
    if len(classifications) == 0:
        return 'count=0'
    else:
        parts = []
        for cls in classifications:
            class_name = cls['name']
            conf = cls['conf']
            parts.append(f'class={class_name},conf={conf:.3f}')
        return f'count={len(classifications)}; ' + ' | '.join(parts)

def draw_texts_with_pillow(bgr_frame, texts):
    """テキスト描画, texts: list of dict with keys {text, org, color, font_type}"""
    img_pil = Image.fromarray(cv2.cvtColor(bgr_frame, cv2.COLOR_BGR2RGB))
    draw = ImageDraw.Draw(img_pil)

    for item in texts:
        text = item['text']
        x, y = item['org']
        color = item['color']
        draw.text((x, y), text, font=font_main, fill=color)

    return cv2.cvtColor(np.array(img_pil), cv2.COLOR_RGB2BGR)

def classify_image(frame):
    """共通の分類処理（前処理、推論、分類を実行）"""
    global model, transforms

    pil_image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
    input_tensor = transforms(pil_image).unsqueeze(0).to(device)

    with torch.no_grad():
        outputs = model(input_tensor)
        probabilities = F.softmax(outputs, dim=1)
        topk_prob, topk_indices = torch.topk(probabilities, TOP_K)
        topk_prob = topk_prob.cpu().numpy()[0]
        topk_indices = topk_indices.cpu().numpy()[0]

    curr_classifications = []
    for i, (class_index, confidence) in enumerate(zip(topk_indices, topk_prob)):
        if class_index < len(IMAGENET_CLASSES):
            name = IMAGENET_CLASSES[class_index]
            curr_classifications.append({
                'conf': confidence,
                'class': class_index,
                'name': name
            })

    return curr_classifications

def process_video_frame(frame, timestamp_ms, is_camera):
    """動画用ラッパー"""
    classifications = classify_image(frame)

    global class_counts
    for cls in classifications:
        name = cls['name']
        if name not in class_counts:
            class_counts[name] = 0
        class_counts[name] += 1

    frame = draw_classification_results(frame, classifications)
    result = format_classification_output(classifications)

    return frame, result

def video_frame_processing(frame, timestamp_ms, is_camera):
    """動画フレーム処理（標準形式）"""
    global frame_count
    current_time = time.time()
    frame_count += 1

    processed_frame, result = process_video_frame(frame, timestamp_ms, is_camera)
    return processed_frame, result, current_time

# プログラムヘッダー表示
display_program_header()

# モデル選択（対話的実装）
print("\n=== ConvNeXt V2モデル選択 ===")
print('使用するConvNeXt V2モデルを選択してください:')
model_list = list(MODEL_INFO.keys())
for i, key in enumerate(model_list, 1):
    info = MODEL_INFO[key]
    print(f'{i}: {info["name"]} ({info["params"]} params, Top-1 {info["top1_acc"]}) - {info["desc"]}')
print()

model_choice = ''
while model_choice not in ['1', '2', '3', '4']:
    model_choice = input("選択 (1/2/3/4) [デフォルト: 1]: ").strip()
    if model_choice == '':
        model_choice = '1'
        break
    if model_choice not in ['1', '2', '3', '4']:
        print("無効な選択です。もう一度入力してください。")

selected_model = model_list[int(model_choice) - 1]

print(f"\nConvNeXt V2モデルをロード中...")
try:
    model = timm.create_model(selected_model, pretrained=True)
    model = model.to(device)
    model.eval()

    data_config = timm.data.resolve_model_data_config(model)
    transforms = timm.data.create_transform(**data_config, is_training=False)

    print(f"\n分類可能なクラス数: {len(IMAGENET_CLASSES)}")
    print(f"モデル情報: {MODEL_INFO[selected_model]['name']} ({MODEL_INFO[selected_model]['params']} params, Top-1 {MODEL_INFO[selected_model]['top1_acc']})")
    print("モデルのロード完了")
except Exception as e:
    print(f"モデルのロードに失敗しました: {e}")
    raise SystemExit(1)

# 入力選択
print("\n=== ConvNeXt V2リアルタイム画像分類（ImageNet 1000クラス） ===")
print("0: 動画ファイル")
print("1: カメラ")
print("2: サンプル動画")

choice = input("選択: ")

is_camera = (choice == '1')

if choice == '0':
    root = tk.Tk()
    root.withdraw()
    path = filedialog.askopenfilename()
    if not path:
        raise SystemExit(1)
    cap = cv2.VideoCapture(path)
elif choice == '1':
    cap = ThreadedVideoCapture(0, is_camera=True)
else:
    SAMPLE_URL = 'https://raw.githubusercontent.com/opencv/opencv/master/samples/data/vtest.avi'
    SAMPLE_FILE = 'vtest.avi'
    print('サンプル動画をダウンロード中...')
    urllib.request.urlretrieve(SAMPLE_URL, SAMPLE_FILE)
    cap = cv2.VideoCapture(SAMPLE_FILE)

if not cap.isOpened():
    print('動画ファイル・カメラを開けませんでした')
    raise SystemExit(1)

# フレームレートの取得とタイムスタンプ増分の計算
if is_camera:
    actual_fps = cap.get(cv2.CAP_PROP_FPS)
    print(f'カメラのfps: {actual_fps}')
    timestamp_increment = int(1000 / actual_fps) if actual_fps > 0 else 33
else:
    video_fps = cap.get(cv2.CAP_PROP_FPS)
    timestamp_increment = int(1000 / video_fps) if video_fps > 0 else 33

# メイン処理
print('\n=== 動画処理開始 ===')
print('操作方法:')
print('  q キー: プログラム終了')

start_time = time.time()
last_info_time = start_time
info_interval = 10.0
timestamp_ms = 0
total_processing_time = 0.0

try:
    while True:
        ret, frame = cap.read()
        if not ret:
            break

        timestamp_ms += timestamp_increment

        processing_start = time.time()
        processed_frame, result, current_time = video_frame_processing(frame, timestamp_ms, is_camera)
        processing_time = time.time() - processing_start
        total_processing_time += processing_time
        cv2.imshow(WINDOW_NAME, processed_frame)

        if result:
            if is_camera:
                timestamp = datetime.fromtimestamp(current_time).strftime("%Y-%m-%d %H:%M:%S.%f")[:-3]
                print(f'{timestamp}, {result}')
            else:
                print(f'Frame {frame_count}: {result}')

            results_log.append(result)

        if is_camera:
            elapsed = current_time - last_info_time
            if elapsed >= info_interval:
                total_elapsed = current_time - start_time
                actual_fps = frame_count / total_elapsed if total_elapsed > 0 else 0
                avg_processing_time = (total_processing_time / frame_count * 1000) if frame_count > 0 else 0
                print(f'[情報] 経過時間: {total_elapsed:.1f}秒, 処理フレーム数: {frame_count}, 実測fps: {actual_fps:.1f}, 平均処理時間: {avg_processing_time:.1f}ms')
                last_info_time = current_time

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

finally:
    print('\n=== プログラム終了 ===')
    cap.release()
    cv2.destroyAllWindows()

    if results_log:
        with open('result.txt', 'w', encoding='utf-8') as f:
            f.write('=== ConvNeXt V2画像分類結果 ===\n')
            f.write(f'処理フレーム数: {frame_count}\n')
            f.write(f'使用モデル: {selected_model}\n')
            f.write(f'モデル情報: {MODEL_INFO[selected_model]["name"]} ({MODEL_INFO[selected_model]["params"]} params, Top-1 {MODEL_INFO[selected_model]["top1_acc"]})\n')
            f.write(f'使用デバイス: {str(device).upper()}\n')
            if device.type == 'cuda':
                f.write(f'GPU: {torch.cuda.get_device_name(0)}\n')
            f.write(f'\n分類されたクラス一覧:\n')
            for class_name, count in sorted(class_counts.items()):
                f.write(f'  {class_name}: {count}回\n')
            f.write('\n')
            f.write('\n'.join(results_log))
        print(f'\n処理結果をresult.txtに保存しました')
        print(f'分類されたクラス数: {len(class_counts)}')