Spaces:
Runtime error
Runtime error
Upload folder using huggingface_hub
Browse files- README.md +3 -9
- __pycache__/gemini_ai.cpython-313.pyc +0 -0
- __pycache__/image_converter.cpython-313.pyc +0 -0
- __pycache__/target.cpython-313.pyc +0 -0
- gemini_ai.py +159 -0
- image_converter.py +62 -0
- main.py +280 -0
- main_ver2.py +263 -0
- requirements.txt +7 -0
- target.py +32 -0
- 讀我.md +23 -0
README.md
CHANGED
|
@@ -1,12 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
|
| 4 |
-
colorFrom: pink
|
| 5 |
-
colorTo: yellow
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 5.
|
| 8 |
-
app_file: app.py
|
| 9 |
-
pinned: false
|
| 10 |
---
|
| 11 |
-
|
| 12 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
| 1 |
---
|
| 2 |
+
title: multi_model_detection
|
| 3 |
+
app_file: main.py
|
|
|
|
|
|
|
| 4 |
sdk: gradio
|
| 5 |
+
sdk_version: 5.39.0
|
|
|
|
|
|
|
| 6 |
---
|
|
|
|
|
|
__pycache__/gemini_ai.cpython-313.pyc
ADDED
|
Binary file (4.58 kB). View file
|
|
|
__pycache__/image_converter.cpython-313.pyc
ADDED
|
Binary file (2.63 kB). View file
|
|
|
__pycache__/target.cpython-313.pyc
ADDED
|
Binary file (914 Bytes). View file
|
|
|
gemini_ai.py
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!pip install -q -U google-generativeai
|
| 2 |
+
import google.generativeai as genai
|
| 3 |
+
import PIL.Image
|
| 4 |
+
import image_converter as img_converter
|
| 5 |
+
import random
|
| 6 |
+
import os
|
| 7 |
+
import ast
|
| 8 |
+
import target
|
| 9 |
+
|
| 10 |
+
# 基本設定都放這邊----------------------------------------
|
| 11 |
+
#
|
| 12 |
+
#
|
| 13 |
+
# 設定圖檔位置 (此處僅為範例,純文字查詢時可忽略)
|
| 14 |
+
image_path = r"D:\Practice\Python_YOLO_AI_ENV\test_images\input\CAT1.png"
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
# 要使用的模型種類,免費版一分鐘只能跑最多十筆
|
| 18 |
+
gemini_model = "gemini-2.5-flash"
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
# 要求AI的提示語放這邊
|
| 22 |
+
# image_prompt = """您現在扮演一位圖片分類大師,擅長解讀圖片中的一些抽象涵義並加以分類。
|
| 23 |
+
# 請在各大類中選最近似的一樣,輸出結果如範例:"A[開心],B[學習],C[學校]"。
|
| 24 |
+
# 若您覺得,該圖片不具上列特徵,請回覆"A[NIL]",加上NIL表示該類未再提供的選項內。
|
| 25 |
+
# 以下是我們要請您分辨的種類:
|
| 26 |
+
# A情感類-人物表情: A[面無表情,開心,生氣,悲傷,緊張,輕視,想睡,疲憊,興奮,自信滿滿,臉部遮蔽]。
|
| 27 |
+
# B動作類-B[學習,工作,飲食,遊戲,駕駛,睡覺,冥想,醫療行為,會議,團隊討論,聽音樂,看電視,畫畫,騎車,烹飪,走路]。
|
| 28 |
+
# C場景類-C[辦公室等工作空間,書房,臥室,客廳,學校,網咖,超現實場景,車內,外太空]。"""
|
| 29 |
+
|
| 30 |
+
# image_prompt = """您現在扮演一位圖片分類大師,擅長解讀圖片中的一些抽象涵義並加以分類。
|
| 31 |
+
# 請在各大類中選最近似的一樣,輸出結果如範例:"物理環境[辦公室],技術應用[人工智慧,虛擬實境,其他],資訊設備[其他]"。
|
| 32 |
+
# 若您覺得,該圖片不具上列特徵,請回覆"XXX[NIL]",XXX為該類別,加上NIL表示該類未再提供的選項內。
|
| 33 |
+
# 以下是我們要請您分辨的種類,會以JSON標示:
|
| 34 |
+
# 物理環境[辦公室,臥室,工作室,工廠]。
|
| 35 |
+
# 技術應用[人工智慧,虛擬實境,大數據分析,其他]。
|
| 36 |
+
# 社交關係[獨立工作(1人),,團隊合作(2人以上),遠程協作(遠端控制)]。
|
| 37 |
+
# 職業情感[快樂,睡覺,壓力/焦慮,成就感]。
|
| 38 |
+
# 資訊設備[AI助手,投影儀,手機,眼鏡投影,智慧手錶,機械手臂,平板,電腦,鍵盤,滑鼠,其他]。
|
| 39 |
+
# 物體[床,椅子,桌子,書架,PC,肖像,監視器,窗戶,冷氣機,其他]。
|
| 40 |
+
# 角色[機器人,教師,學生,動物,工作人員]。
|
| 41 |
+
# """
|
| 42 |
+
|
| 43 |
+
image_prompt = """您現在扮演一位圖片分類大師,擅長解讀圖片中的一些抽象涵義並加以分類。
|
| 44 |
+
請在各大類中選最近似的一樣,輸出結果如範例:"物理環境[辦公室],技術應用[人工智慧,虛擬實境,其他],資訊設備[其他]"。
|
| 45 |
+
若您覺得,該圖片不具上列特徵,請回覆"XXX[NIL]",XXX為該類別,加上NIL表示該類未再提供的選項內。
|
| 46 |
+
以下是我們要請您分辨的種類,會以JSON標示:""" + str(
|
| 47 |
+
target.target_JSON
|
| 48 |
+
)
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
# --------------------------------------------------------
|
| 52 |
+
## 替換冒號和逗號為換行符號
|
| 53 |
+
def replace_colon_comma_with_newline(input_string):
|
| 54 |
+
processed_string = (
|
| 55 |
+
input_string.replace(":", "\n").replace(":", "\n").replace("],", "]\n")
|
| 56 |
+
)
|
| 57 |
+
return processed_string
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
def getApiToken():
|
| 61 |
+
try:
|
| 62 |
+
my_api_key = os.getenv("my_api_key")
|
| 63 |
+
my_list = ast.literal_eval(
|
| 64 |
+
my_api_key
|
| 65 |
+
) # Convert string to list因為存在環境變數中是字串格式
|
| 66 |
+
|
| 67 |
+
return random.choice(my_list)
|
| 68 |
+
except Exception as e:
|
| 69 |
+
return ""
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
# function,輸入是文字或是圖檔的位置
|
| 73 |
+
def analyze_content_with_gemini(input_content, user_prompt=None):
|
| 74 |
+
"""
|
| 75 |
+
透過 Gemini API 辨識內容,可處理純文字或圖片。
|
| 76 |
+
|
| 77 |
+
Args:
|
| 78 |
+
input_content (str or PIL.Image.Image):
|
| 79 |
+
如果輸入是字串,則代表要辨識的文字訊息或圖片路徑。
|
| 80 |
+
如果輸入是 PIL.Image.Image 物件,則直接使用該圖片。
|
| 81 |
+
user_prompt (str, optional):
|
| 82 |
+
使用者提供的自訂 prompt。如果為 None,則使用預設的 prompt。
|
| 83 |
+
Defaults to None.
|
| 84 |
+
|
| 85 |
+
Returns:
|
| 86 |
+
str: 辨識結果的文字描述。
|
| 87 |
+
"""
|
| 88 |
+
|
| 89 |
+
try:
|
| 90 |
+
# 請將 'YOUR_API_KEY' 替換為您的實際 API 金鑰。
|
| 91 |
+
my_api_key = getApiToken() # 從環境變數中獲取API金鑰
|
| 92 |
+
print(my_api_key)
|
| 93 |
+
genai.configure(api_key=my_api_key)
|
| 94 |
+
except Exception as e:
|
| 95 |
+
return f"發生錯誤:{e}"
|
| 96 |
+
|
| 97 |
+
# 根據 user_prompt 決定要使用的 prompt
|
| 98 |
+
prompt_to_use = (
|
| 99 |
+
image_prompt + user_prompt
|
| 100 |
+
if user_prompt and user_prompt.strip()
|
| 101 |
+
else image_prompt
|
| 102 |
+
)
|
| 103 |
+
|
| 104 |
+
try:
|
| 105 |
+
# 判斷輸入的類型
|
| 106 |
+
if isinstance(input_content, str):
|
| 107 |
+
# 如果輸入是字串,嘗試判斷是否為圖片路徑
|
| 108 |
+
if input_content.lower().endswith(
|
| 109 |
+
(".png", ".jpg", ".jpeg", ".gif", ".webp")
|
| 110 |
+
):
|
| 111 |
+
if input_content.lower().endswith((".webp")):
|
| 112 |
+
input_content = img_converter.convert_webp_to_jpg(
|
| 113 |
+
input_content
|
| 114 |
+
) # 如果是 webp 圖片,先轉換為 jpg
|
| 115 |
+
|
| 116 |
+
model = genai.GenerativeModel(gemini_model)
|
| 117 |
+
image_obj = PIL.Image.open(input_content)
|
| 118 |
+
response = model.generate_content([prompt_to_use, image_obj])
|
| 119 |
+
else:
|
| 120 |
+
# 純文字輸入
|
| 121 |
+
model = genai.GenerativeModel(gemini_model)
|
| 122 |
+
response = model.generate_content(
|
| 123 |
+
input_content
|
| 124 |
+
) # 純文字直接使用輸入內容當 prompt
|
| 125 |
+
elif isinstance(input_content, PIL.Image.Image):
|
| 126 |
+
model = genai.GenerativeModel(gemini_model)
|
| 127 |
+
response = model.generate_content([prompt_to_use, input_content])
|
| 128 |
+
else:
|
| 129 |
+
return "錯誤:輸入必須是文字、圖片路徑(字串)或 PIL.Image 物件。"
|
| 130 |
+
|
| 131 |
+
return replace_colon_comma_with_newline(response.text)
|
| 132 |
+
|
| 133 |
+
except Exception as e:
|
| 134 |
+
return f"發生錯誤:{e}"
|
| 135 |
+
|
| 136 |
+
|
| 137 |
+
if __name__ == "__main__":
|
| 138 |
+
# --- 程式碼使用範例 ---
|
| 139 |
+
|
| 140 |
+
# 範例 1:傳送純文字訊息
|
| 141 |
+
# print("正在處理純文字訊息...")
|
| 142 |
+
# text_message = "你好,請簡要說明一下Python是什麼?"
|
| 143 |
+
# response_text = analyze_content_with_gemini(text_message)
|
| 144 |
+
# print("回應結果:")
|
| 145 |
+
# print(response_text)
|
| 146 |
+
# print("-" * 20)
|
| 147 |
+
|
| 148 |
+
# 範例 2:傳送圖片路徑
|
| 149 |
+
# 請確保 image_path 指向有效的圖片檔案
|
| 150 |
+
print("正在處理圖片訊息...")
|
| 151 |
+
my_prompt =""
|
| 152 |
+
# my_prompt = """{
|
| 153 |
+
# "物品": ["辦公室", "臥室", "工作室", "工廠","牛","鴨","船"]
|
| 154 |
+
# }"""
|
| 155 |
+
|
| 156 |
+
response_image = analyze_content_with_gemini(image_path)
|
| 157 |
+
print("回應結果:")
|
| 158 |
+
print(response_image)
|
| 159 |
+
print("-" * 20)
|
image_converter.py
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# 這個程式將 webp 圖片轉換為 jpg 格式,
|
| 2 |
+
# 並儲存到指定的資料夾或與原檔案相同的資料夾中。
|
| 3 |
+
# 使用 PIL 庫來處理圖片格式轉換。
|
| 4 |
+
|
| 5 |
+
from PIL import Image
|
| 6 |
+
import os
|
| 7 |
+
|
| 8 |
+
def convert_webp_to_jpg(webp_path, output_folder=None):
|
| 9 |
+
"""
|
| 10 |
+
將 webp 檔案轉換為 jpg 檔案。
|
| 11 |
+
|
| 12 |
+
:param webp_path: 輸入的 webp 檔案路徑。
|
| 13 |
+
:param output_folder: 輸出的資料夾路徑。如果為 None,則輸出到與輸入檔案相同的資料夾。
|
| 14 |
+
:return: 輸出的 jpg 檔案路徑。
|
| 15 |
+
"""
|
| 16 |
+
try:
|
| 17 |
+
# 開啟 webp 圖片
|
| 18 |
+
img = Image.open(webp_path).convert("RGB")
|
| 19 |
+
|
| 20 |
+
# 決定輸出的檔案名稱與路徑
|
| 21 |
+
file_name = os.path.splitext(os.path.basename(webp_path))[0]
|
| 22 |
+
if output_folder:
|
| 23 |
+
if not os.path.exists(output_folder):
|
| 24 |
+
os.makedirs(output_folder)
|
| 25 |
+
output_path = os.path.join(output_folder, f"{file_name}.jpg")
|
| 26 |
+
else:
|
| 27 |
+
output_path = os.path.join(os.path.dirname(webp_path), f"{file_name}.jpg")
|
| 28 |
+
|
| 29 |
+
# 儲存為 jpg
|
| 30 |
+
img.save(output_path, "jpeg")
|
| 31 |
+
|
| 32 |
+
print(f"成功將 {webp_path} 轉換為 {output_path}")
|
| 33 |
+
return output_path
|
| 34 |
+
except Exception as e:
|
| 35 |
+
print(f"轉換失敗:{e}")
|
| 36 |
+
return None
|
| 37 |
+
|
| 38 |
+
if __name__ == '__main__':
|
| 39 |
+
|
| 40 |
+
# 建立一個假的 webp 檔案以供測試
|
| 41 |
+
if not os.path.exists("input_images"):
|
| 42 |
+
os.makedirs("input_images")
|
| 43 |
+
|
| 44 |
+
try:
|
| 45 |
+
# 建立一個簡單的白色圖片
|
| 46 |
+
#G:\Python\tools\input_images\1411032040-楊宗祥.webp
|
| 47 |
+
dummy_webp_path = r"G:\Python\tools\input_images\1411032040-楊宗祥.webp"
|
| 48 |
+
|
| 49 |
+
# 測試轉換函數
|
| 50 |
+
# 範例 1: 轉換並儲存在相同資料夾
|
| 51 |
+
print("\n--- 範例 1: 轉換並儲存在相同資料夾 ---")
|
| 52 |
+
output_path = convert_webp_to_jpg(dummy_webp_path)
|
| 53 |
+
|
| 54 |
+
# 範例 2: 轉換並儲存在指定資料夾
|
| 55 |
+
print("\n--- 範例 2: 轉換並儲存在指定資料夾 ---")
|
| 56 |
+
if not os.path.exists("output_images"):
|
| 57 |
+
os.makedirs("output_images")
|
| 58 |
+
output_path = convert_webp_to_jpg(dummy_webp_path, "output_images")
|
| 59 |
+
|
| 60 |
+
print(output_path)
|
| 61 |
+
except Exception as e:
|
| 62 |
+
print(f"執行範例時發生錯誤: {e}")
|
main.py
ADDED
|
@@ -0,0 +1,280 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Required packages:
|
| 2 |
+
# - gradio
|
| 3 |
+
# - transformers
|
| 4 |
+
# - opencv-python
|
| 5 |
+
# - ultralytics
|
| 6 |
+
# - Pillow # Pillow is a common dependency for image processing libraries like OpenCV and Gradio
|
| 7 |
+
|
| 8 |
+
import gradio as gr
|
| 9 |
+
from transformers import pipeline
|
| 10 |
+
import os
|
| 11 |
+
import cv2
|
| 12 |
+
from ultralytics import YOLO
|
| 13 |
+
import shutil # Import shutil for copying files
|
| 14 |
+
import zipfile # Import zipfile for creating zip archives
|
| 15 |
+
|
| 16 |
+
def multi_model_detection(image_paths_list: list, model_paths_list: list, output_dir: str = 'detection_results', conf_threshold: float = 0.25):
|
| 17 |
+
"""
|
| 18 |
+
使用多個 YOLOv8 模型對多張圖片進行物件辨識,
|
| 19 |
+
並將結果繪製在圖片上,同時保存辨識資訊到文字檔案。
|
| 20 |
+
|
| 21 |
+
Args:
|
| 22 |
+
image_paths_list (list): 包含所有待辨識圖片路徑的列表。
|
| 23 |
+
model_paths_list (list): 包含所有模型 (.pt 檔案) 路徑的列表。
|
| 24 |
+
output_dir (str): 儲存結果圖片和文字檔案的目錄。
|
| 25 |
+
如果不存在,函式會自動創建。
|
| 26 |
+
conf_threshold (float): 置信度閾值,只有高於此值的偵測結果會被標示。
|
| 27 |
+
|
| 28 |
+
Returns:
|
| 29 |
+
list: A list of paths to the annotated images.
|
| 30 |
+
list: A list of paths to the text files with detection information.
|
| 31 |
+
"""
|
| 32 |
+
|
| 33 |
+
# 確保輸出目錄存在
|
| 34 |
+
if not os.path.exists(output_dir):
|
| 35 |
+
os.makedirs(output_dir)
|
| 36 |
+
print(f"已創建輸出目錄: {output_dir}")
|
| 37 |
+
|
| 38 |
+
# 載入所有模型
|
| 39 |
+
loaded_models = []
|
| 40 |
+
print("\n--- 載入模型 ---")
|
| 41 |
+
# If no models are uploaded, use the default yolov8n.pt
|
| 42 |
+
if not model_paths_list:
|
| 43 |
+
default_model_path = 'yolov8n.pt'
|
| 44 |
+
try:
|
| 45 |
+
model = YOLO(default_model_path)
|
| 46 |
+
loaded_models.append((default_model_path, model))
|
| 47 |
+
print(f"成功載入預設模型: {default_model_path}")
|
| 48 |
+
except Exception as e:
|
| 49 |
+
print(f"錯誤: 無法載入預設模型 '{default_model_path}' - {e}")
|
| 50 |
+
return [], []
|
| 51 |
+
else:
|
| 52 |
+
for model_path in model_paths_list:
|
| 53 |
+
try:
|
| 54 |
+
model = YOLO(model_path)
|
| 55 |
+
loaded_models.append((model_path, model)) # 儲存模型路徑和模型物件
|
| 56 |
+
print(f"成功載入模型: {model_path}")
|
| 57 |
+
except Exception as e:
|
| 58 |
+
print(f"錯誤: 無法載入模型 '{model_path}' - {e}")
|
| 59 |
+
continue # 如果模型載入失敗,跳過它
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
if not loaded_models:
|
| 63 |
+
print("沒有模型成功載入,請檢查模型路徑或預設模型。")
|
| 64 |
+
return [], []
|
| 65 |
+
|
| 66 |
+
annotated_image_paths = []
|
| 67 |
+
txt_output_paths = []
|
| 68 |
+
|
| 69 |
+
# 處理每張圖片
|
| 70 |
+
print("\n--- 開始圖片辨識 ---")
|
| 71 |
+
for image_path in image_paths_list:
|
| 72 |
+
if not os.path.exists(image_path):
|
| 73 |
+
print(f"警告: 圖片 '{image_path}' 不存在,跳過。")
|
| 74 |
+
continue
|
| 75 |
+
|
| 76 |
+
print(f"\n處理圖片: {os.path.basename(image_path)}")
|
| 77 |
+
original_image = cv2.imread(image_path)
|
| 78 |
+
if original_image is None:
|
| 79 |
+
print(f"錯誤: 無法讀取圖片 '{image_path}',跳過。")
|
| 80 |
+
continue
|
| 81 |
+
|
| 82 |
+
# 複製圖片用於繪製,避免修改原始圖片
|
| 83 |
+
# 使用 NumPy 複製,而不是直接賦值
|
| 84 |
+
annotated_image = original_image.copy()
|
| 85 |
+
|
| 86 |
+
# 準備寫入文字檔的內容
|
| 87 |
+
txt_output_content = []
|
| 88 |
+
txt_output_content.append(f"檔案: {os.path.basename(image_path)}\n")
|
| 89 |
+
|
| 90 |
+
# 對每張圖片使用所有模型進行辨識
|
| 91 |
+
all_detections_for_image = [] # 儲存所有模型在當前圖片上的偵測結果
|
| 92 |
+
|
| 93 |
+
for model_path_str, model_obj in loaded_models:
|
| 94 |
+
model_name = os.path.basename(model_path_str) # 獲取模型檔案名
|
| 95 |
+
print(f" 使用模型 '{model_name}' 進行辨識...")
|
| 96 |
+
|
| 97 |
+
# 執行推論, device="cpu" ensures it runs on CPU if GPU is not available or preferred
|
| 98 |
+
results = model_obj(image_path, verbose=False, device="cpu")[0]
|
| 99 |
+
|
| 100 |
+
# 將辨識結果添加到 txt 輸出內容和繪圖列表
|
| 101 |
+
txt_output_content.append(f"\n--- 模型: {model_name} ---")
|
| 102 |
+
|
| 103 |
+
if results.boxes: # 檢查是否有偵測到物件
|
| 104 |
+
for box in results.boxes:
|
| 105 |
+
# 取得邊界框座標和置信度
|
| 106 |
+
conf = float(box.conf[0])
|
| 107 |
+
if conf >= conf_threshold: # 檢查置信度是否達到閾值
|
| 108 |
+
x1, y1, x2, y2 = map(int, box.xyxy[0])
|
| 109 |
+
cls_id = int(box.cls[0])
|
| 110 |
+
cls_name = model_obj.names[cls_id] # 取得類別名稱
|
| 111 |
+
|
| 112 |
+
detection_info = {
|
| 113 |
+
'model_name': model_name,
|
| 114 |
+
'class_name': cls_name,
|
| 115 |
+
'confidence': conf,
|
| 116 |
+
'bbox': (x1, y1, x2, y2)
|
| 117 |
+
}
|
| 118 |
+
all_detections_for_image.append(detection_info)
|
| 119 |
+
|
| 120 |
+
# 加入到文字檔內容
|
| 121 |
+
txt_output_content.append(f" - {cls_name} (Conf: {conf:.2f}) [x1:{x1}, y1:{y1}, x2:{x2}, y2:{y2}]")
|
| 122 |
+
else:
|
| 123 |
+
txt_output_content.append(" 沒有偵測到任何物件。")
|
| 124 |
+
|
| 125 |
+
# 繪製所有模型在當前圖片上的偵測結果
|
| 126 |
+
# 我們會根據模型來源給予不同的顏色或樣式,讓結果更容易區分
|
| 127 |
+
|
| 128 |
+
# 定義一個顏色循環列表,方便給不同模型分配不同顏色
|
| 129 |
+
colors = [
|
| 130 |
+
(255, 0, 0), # 紅色 (例如給模型 A)
|
| 131 |
+
(0, 255, 0), # 綠色 (例如給模型 B)
|
| 132 |
+
(0, 0, 255), # 藍色
|
| 133 |
+
(255, 255, 0), # 黃色
|
| 134 |
+
(255, 0, 255), # 紫色
|
| 135 |
+
(0, 255, 255), # 青色
|
| 136 |
+
(128, 0, 0), # 深紅
|
| 137 |
+
(0, 128, 0) # 深綠
|
| 138 |
+
]
|
| 139 |
+
color_map = {} # 用來映射模型名稱到顏色
|
| 140 |
+
|
| 141 |
+
for idx, (model_path_str, _) in enumerate(loaded_models):
|
| 142 |
+
model_name = os.path.basename(model_path_str)
|
| 143 |
+
color_map[model_name] = colors[idx % len(colors)] # 確保顏色循環使用
|
| 144 |
+
|
| 145 |
+
for det in all_detections_for_image:
|
| 146 |
+
x1, y1, x2, y2 = det['bbox']
|
| 147 |
+
conf = det['confidence']
|
| 148 |
+
cls_name = det['class_name']
|
| 149 |
+
model_name = det['model_name']
|
| 150 |
+
|
| 151 |
+
color = color_map.get(model_name, (200, 200, 200)) # 預設灰色
|
| 152 |
+
|
| 153 |
+
# 繪製邊界框
|
| 154 |
+
cv2.rectangle(annotated_image, (x1, y1), (x2, y2), color, 2)
|
| 155 |
+
|
| 156 |
+
# 繪製標籤 (類別名稱 + 置信度 + 模型名稱縮寫)
|
| 157 |
+
# 為了避免標籤過長,模型名稱只取前幾個字母
|
| 158 |
+
model_abbr = "".join([s[0] for s in model_name.split('.')[:-1]]) # 例如 'a.pt' -> 'a'
|
| 159 |
+
label = f'{cls_name} {conf:.2f} ({model_abbr})'
|
| 160 |
+
cv2.putText(annotated_image, label, (x1, y1 - 10),
|
| 161 |
+
cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
|
| 162 |
+
|
| 163 |
+
# 保存繪製後的圖片
|
| 164 |
+
image_base_name = os.path.basename(image_path)
|
| 165 |
+
image_name_without_ext = os.path.splitext(image_base_name)[0]
|
| 166 |
+
output_image_path = os.path.join(output_dir, f"{image_name_without_ext}_detected.jpg")
|
| 167 |
+
cv2.imwrite(output_image_path, annotated_image)
|
| 168 |
+
annotated_image_paths.append(output_image_path)
|
| 169 |
+
print(f" 結果圖片保存至: {output_image_path}")
|
| 170 |
+
|
| 171 |
+
# 保存辨識資訊到文字檔案
|
| 172 |
+
output_txt_path = os.path.join(output_dir, f"{image_name_without_ext}.txt")
|
| 173 |
+
with open(output_txt_path, 'w', encoding='utf-8') as f:
|
| 174 |
+
f.write("\n".join(txt_output_content))
|
| 175 |
+
txt_output_paths.append(output_txt_path)
|
| 176 |
+
print(f" 辨識資訊保存至: {output_txt_path}")
|
| 177 |
+
|
| 178 |
+
|
| 179 |
+
print("\n--- 所有圖片處理完成 ---")
|
| 180 |
+
return annotated_image_paths, txt_output_paths
|
| 181 |
+
|
| 182 |
+
def create_zip_archive(files, zip_filename):
|
| 183 |
+
"""Creates a zip archive from a list of files."""
|
| 184 |
+
with zipfile.ZipFile(zip_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
|
| 185 |
+
for file in files:
|
| 186 |
+
if os.path.exists(file):
|
| 187 |
+
zipf.write(file, os.path.basename(file))
|
| 188 |
+
else:
|
| 189 |
+
print(f"警告: 檔案 '{file}' 不存在,無法加入壓縮檔。")
|
| 190 |
+
return zip_filename
|
| 191 |
+
|
| 192 |
+
|
| 193 |
+
# --- Gradio Interface ---
|
| 194 |
+
def gradio_multi_model_detection(image_files, model_files, conf_threshold, output_subdir):
|
| 195 |
+
"""
|
| 196 |
+
Gradio 的主要處理函式。
|
| 197 |
+
接收上傳的檔案和參數,呼叫後端辨識函式,並返回結果。
|
| 198 |
+
|
| 199 |
+
Args:
|
| 200 |
+
image_files (list): Gradio File 元件回傳的圖片檔案列表 (暫存路徑)。
|
| 201 |
+
model_files (list): Gradio File 元件回傳的模型檔案列表 (暫存路徑)。
|
| 202 |
+
conf_threshold (float): 置信度閾值。
|
| 203 |
+
output_subdir (str): 用於儲存本次執行結果的子目錄名稱。
|
| 204 |
+
|
| 205 |
+
Returns:
|
| 206 |
+
tuple: 更新 Gradio 介面所需的多個輸出。
|
| 207 |
+
"""
|
| 208 |
+
if not image_files:
|
| 209 |
+
return None, "請上傳圖片檔案。", None, None
|
| 210 |
+
|
| 211 |
+
# Get the temporary file paths from Gradio File objects
|
| 212 |
+
image_paths = [file.name for file in image_files]
|
| 213 |
+
# Use uploaded model paths or an empty list if none are uploaded
|
| 214 |
+
model_paths = [file.name for file in model_files] if model_files else []
|
| 215 |
+
|
| 216 |
+
|
| 217 |
+
# Define the output directory for this run within the main results directory
|
| 218 |
+
base_output_dir = 'gradio_detection_results'
|
| 219 |
+
run_output_dir = os.path.join(base_output_dir, output_subdir)
|
| 220 |
+
|
| 221 |
+
# Perform detection
|
| 222 |
+
annotated_images, detection_texts = multi_model_detection(
|
| 223 |
+
image_paths_list=image_paths,
|
| 224 |
+
model_paths_list=model_paths,
|
| 225 |
+
output_dir=run_output_dir,
|
| 226 |
+
conf_threshold=conf_threshold
|
| 227 |
+
)
|
| 228 |
+
|
| 229 |
+
if not annotated_images:
|
| 230 |
+
return None, "辨識失敗,請檢查輸入或模型。", None, None
|
| 231 |
+
|
| 232 |
+
# Combine detection texts for display in one textbox
|
| 233 |
+
combined_detection_text = "--- 辨識結果 ---\n\n"
|
| 234 |
+
for txt_path in detection_texts:
|
| 235 |
+
with open(txt_path, 'r', encoding='utf-8') as f:
|
| 236 |
+
combined_detection_text += f.read() + "\n\n"
|
| 237 |
+
|
| 238 |
+
# Create a zip file containing both annotated images and text files
|
| 239 |
+
all_result_files = annotated_images + detection_texts
|
| 240 |
+
zip_filename = os.path.join(run_output_dir, f"{output_subdir}_results.zip")
|
| 241 |
+
created_zip_path = create_zip_archive(all_result_files, zip_filename)
|
| 242 |
+
|
| 243 |
+
|
| 244 |
+
# Return annotated images and combined text for Gradio output
|
| 245 |
+
# Gradio Gallery expects a list of image paths
|
| 246 |
+
return annotated_images, combined_detection_text, f"結果儲存於: {os.path.abspath(run_output_dir)}", created_zip_path
|
| 247 |
+
|
| 248 |
+
|
| 249 |
+
# Create the Gradio interface
|
| 250 |
+
with gr.Blocks() as demo:
|
| 251 |
+
gr.Markdown("# 支援多模型YOLO物件辨識(demo)")
|
| 252 |
+
gr.Markdown("上傳您的圖片和模型,並設定置信度閾值進行物件辨識。若未上傳模型,將使用預設的 yolov8n.pt 進行辨識。")
|
| 253 |
+
|
| 254 |
+
with gr.Row():
|
| 255 |
+
with gr.Column():
|
| 256 |
+
image_input = gr.File(label="上傳圖片", file_count="multiple", file_types=["image"])
|
| 257 |
+
model_input = gr.File(label="上傳模型 (.pt)", file_count="multiple", file_types=[".pt"])
|
| 258 |
+
conf_slider = gr.Slider(minimum=0, maximum=1, value=0.25, step=0.05, label="置信度閾值")
|
| 259 |
+
output_subdir_input = gr.Textbox(label="結果子目錄名稱", value="run_1", placeholder="請輸入儲存結果的子目錄名稱")
|
| 260 |
+
run_button = gr.Button("開始辨識")
|
| 261 |
+
|
| 262 |
+
with gr.Column():
|
| 263 |
+
# show_label=False hides the class name label below each image
|
| 264 |
+
# allow_preview=True enables double-clicking to zoom
|
| 265 |
+
# allow_download=True adds a download button for each image in the gallery
|
| 266 |
+
output_gallery = gr.Gallery(label="辨識結果圖片", height=400, allow_preview=True, object_fit="contain")
|
| 267 |
+
output_text = gr.Textbox(label="辨識資訊", lines=10)
|
| 268 |
+
output_status = gr.Textbox(label="狀態/儲存路徑")
|
| 269 |
+
download_button = gr.File(label="下載所有結果 (.zip)", file_count="single")
|
| 270 |
+
|
| 271 |
+
|
| 272 |
+
# Link the button click to the function
|
| 273 |
+
run_button.click(
|
| 274 |
+
fn=gradio_multi_model_detection,
|
| 275 |
+
inputs=[image_input, model_input, conf_slider, output_subdir_input],
|
| 276 |
+
outputs=[output_gallery, output_text, output_status, download_button]
|
| 277 |
+
)
|
| 278 |
+
|
| 279 |
+
# Launch the interface
|
| 280 |
+
demo.launch(debug=True)
|
main_ver2.py
ADDED
|
@@ -0,0 +1,263 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# -*- coding: utf-8 -*-
|
| 2 |
+
"""
|
| 3 |
+
系統需求:
|
| 4 |
+
- gradio: 用於建立 Web UI
|
| 5 |
+
- opencv-python: 用於圖片處理
|
| 6 |
+
- ultralytics: YOLOv8 官方函式庫
|
| 7 |
+
- Pillow: 圖片處理基礎庫
|
| 8 |
+
- transformers: (可選,若YOLO模型需要)
|
| 9 |
+
"""
|
| 10 |
+
|
| 11 |
+
import gradio as gr
|
| 12 |
+
import os
|
| 13 |
+
import cv2
|
| 14 |
+
from ultralytics import YOLO
|
| 15 |
+
import shutil
|
| 16 |
+
import zipfile
|
| 17 |
+
import uuid # 匯入 uuid 以生成唯一的執行 ID
|
| 18 |
+
from pathlib import Path # 匯入 Path 以更方便地操作路徑
|
| 19 |
+
|
| 20 |
+
# 假設 gemini_ai.py 在同一個目錄或 Python 路徑中
|
| 21 |
+
import gemini_ai as genai
|
| 22 |
+
|
| 23 |
+
def create_zip_archive(files, zip_filename):
|
| 24 |
+
"""
|
| 25 |
+
將一系列檔案壓縮成一個 zip 檔案。
|
| 26 |
+
|
| 27 |
+
Args:
|
| 28 |
+
files (list): 要壓縮的檔案路徑列表。
|
| 29 |
+
zip_filename (str): 產生的 zip 檔案路徑。
|
| 30 |
+
|
| 31 |
+
Returns:
|
| 32 |
+
str: 產生的 zip 檔案路徑。
|
| 33 |
+
"""
|
| 34 |
+
with zipfile.ZipFile(zip_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
|
| 35 |
+
for file in files:
|
| 36 |
+
if os.path.exists(file):
|
| 37 |
+
# 使用 os.path.basename 確保只寫入檔案名稱,而非完整路徑
|
| 38 |
+
zipf.write(file, os.path.basename(file))
|
| 39 |
+
else:
|
| 40 |
+
print(f"警告: 檔案 '{file}' 不存在,無法加入壓縮檔。")
|
| 41 |
+
return zip_filename
|
| 42 |
+
|
| 43 |
+
def gradio_multi_model_detection(
|
| 44 |
+
image_files,
|
| 45 |
+
model_files,
|
| 46 |
+
conf_threshold,
|
| 47 |
+
enable_mllm,
|
| 48 |
+
mllm_prompt,
|
| 49 |
+
progress=gr.Progress(track_tqdm=True)
|
| 50 |
+
):
|
| 51 |
+
"""
|
| 52 |
+
Gradio 的主要處理函式,使用生成器 (yield) 實現流式輸出。
|
| 53 |
+
|
| 54 |
+
Args:
|
| 55 |
+
image_files (list): Gradio File 元件回傳的圖片檔案列表。
|
| 56 |
+
model_files (list): Gradio File 元件回傳的模型檔案列表。
|
| 57 |
+
conf_threshold (float): 置信度閾值。
|
| 58 |
+
enable_mllm (bool): 是否啟用 MLLM 分析。
|
| 59 |
+
mllm_prompt (str): 使用者自訂的 MLLM prompt。
|
| 60 |
+
progress (gr.Progress): Gradio 的進度條元件。
|
| 61 |
+
|
| 62 |
+
Yields:
|
| 63 |
+
dict: 用於更新 Gradio 介面元件的字典。
|
| 64 |
+
"""
|
| 65 |
+
if not image_files:
|
| 66 |
+
yield {
|
| 67 |
+
output_status: gr.update(value="錯誤:請至少上傳一張圖片。"),
|
| 68 |
+
output_gallery: None,
|
| 69 |
+
output_text: None,
|
| 70 |
+
download_button: None
|
| 71 |
+
}
|
| 72 |
+
return
|
| 73 |
+
|
| 74 |
+
# --- 1. 初始化設定 ---
|
| 75 |
+
# 為本次執行創建一個唯一的子目錄
|
| 76 |
+
run_id = str(uuid.uuid4())
|
| 77 |
+
base_output_dir = Path('gradio_detection_results')
|
| 78 |
+
run_output_dir = base_output_dir / f"run_{run_id[:8]}"
|
| 79 |
+
run_output_dir.mkdir(parents=True, exist_ok=True)
|
| 80 |
+
|
| 81 |
+
image_paths = [file.name for file in image_files]
|
| 82 |
+
model_paths = [file.name for file in model_files] if model_files else []
|
| 83 |
+
|
| 84 |
+
# --- 2. 載入模型 ---
|
| 85 |
+
yield {output_status: gr.update(value="正在載入模型...")}
|
| 86 |
+
loaded_models = []
|
| 87 |
+
if not model_paths:
|
| 88 |
+
# 如果沒有上傳模型,使用預設模型
|
| 89 |
+
default_model_path = 'yolov8n.pt'
|
| 90 |
+
try:
|
| 91 |
+
model = YOLO(default_model_path)
|
| 92 |
+
loaded_models.append((default_model_path, model))
|
| 93 |
+
except Exception as e:
|
| 94 |
+
yield {output_status: gr.update(value=f"錯誤: 無法載入預設模型 '{default_model_path}' - {e}")}
|
| 95 |
+
return
|
| 96 |
+
else:
|
| 97 |
+
for model_path in model_paths:
|
| 98 |
+
try:
|
| 99 |
+
model = YOLO(model_path)
|
| 100 |
+
loaded_models.append((model_path, model))
|
| 101 |
+
except Exception as e:
|
| 102 |
+
print(f"警告: 無法載入模型 '{model_path}' - {e},將跳過此模型。")
|
| 103 |
+
continue
|
| 104 |
+
|
| 105 |
+
if not loaded_models:
|
| 106 |
+
yield {output_status: gr.update(value="錯誤: 沒有任何模型成功載入。")}
|
| 107 |
+
return
|
| 108 |
+
|
| 109 |
+
# --- 3. 逐一處理圖片 ---
|
| 110 |
+
total_images = len(image_paths)
|
| 111 |
+
annotated_image_paths = []
|
| 112 |
+
all_result_files = []
|
| 113 |
+
# results_map 儲存圖片路徑與其對應的文字檔路徑,用於後續點擊查詢
|
| 114 |
+
results_map = {}
|
| 115 |
+
# all_texts 用於收集所有圖片的辨識結果文字
|
| 116 |
+
all_texts = []
|
| 117 |
+
|
| 118 |
+
for i, image_path_str in enumerate(image_paths):
|
| 119 |
+
image_path = Path(image_path_str)
|
| 120 |
+
progress(i / total_images, desc=f"處理中: {image_path.name}")
|
| 121 |
+
yield {
|
| 122 |
+
output_status: gr.update(value=f"處理中... ({i+1}/{total_images}) - {image_path.name}"),
|
| 123 |
+
output_gallery: gr.update(value=annotated_image_paths)
|
| 124 |
+
}
|
| 125 |
+
|
| 126 |
+
original_image = cv2.imread(str(image_path))
|
| 127 |
+
if original_image is None:
|
| 128 |
+
print(f"警告: 無法讀取圖片 '{image_path}',跳過。")
|
| 129 |
+
continue
|
| 130 |
+
|
| 131 |
+
annotated_image = original_image.copy()
|
| 132 |
+
image_base_name = image_path.stem
|
| 133 |
+
|
| 134 |
+
# --- 3a. YOLO 物件偵測 ---
|
| 135 |
+
yolo_output_content = [f"--- 檔案: {image_path.name} ---"]
|
| 136 |
+
all_detections_for_image = []
|
| 137 |
+
|
| 138 |
+
for model_path_str, model_obj in loaded_models:
|
| 139 |
+
model_name = Path(model_path_str).name
|
| 140 |
+
yolo_output_content.append(f"--- 模型: {model_name} ---")
|
| 141 |
+
results = model_obj(str(image_path), verbose=False, device="cpu")[0]
|
| 142 |
+
|
| 143 |
+
if results.boxes:
|
| 144 |
+
for box in results.boxes:
|
| 145 |
+
conf = float(box.conf[0])
|
| 146 |
+
if conf >= conf_threshold:
|
| 147 |
+
x1, y1, x2, y2 = map(int, box.xyxy[0])
|
| 148 |
+
cls_id = int(box.cls[0])
|
| 149 |
+
cls_name = model_obj.names[cls_id]
|
| 150 |
+
|
| 151 |
+
detection_info = {'model_name': model_name, 'class_name': cls_name, 'confidence': conf, 'bbox': (x1, y1, x2, y2)}
|
| 152 |
+
all_detections_for_image.append(detection_info)
|
| 153 |
+
yolo_output_content.append(f" - {cls_name} (信賴度: {conf:.2f}) [座標: {x1},{y1},{x2},{y2}]")
|
| 154 |
+
else:
|
| 155 |
+
yolo_output_content.append(" 未偵測到任何物件。")
|
| 156 |
+
|
| 157 |
+
# 繪製偵測框
|
| 158 |
+
colors = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255), (0, 255, 255)]
|
| 159 |
+
color_map = {Path(p).name: colors[idx % len(colors)] for idx, (p, _) in enumerate(loaded_models)}
|
| 160 |
+
for det in all_detections_for_image:
|
| 161 |
+
x1, y1, x2, y2 = det['bbox']
|
| 162 |
+
color = color_map.get(det['model_name'], (200, 200, 200))
|
| 163 |
+
label = f"{det['class_name']} {det['confidence']:.2f}"
|
| 164 |
+
cv2.rectangle(annotated_image, (x1, y1), (x2, y2), color, 2)
|
| 165 |
+
cv2.putText(annotated_image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
|
| 166 |
+
|
| 167 |
+
# 儲存 YOLO 標註圖
|
| 168 |
+
output_image_path = run_output_dir / f"{image_base_name}_yolo_detected.jpg"
|
| 169 |
+
cv2.imwrite(str(output_image_path), annotated_image)
|
| 170 |
+
annotated_image_paths.append(str(output_image_path))
|
| 171 |
+
all_result_files.append(str(output_image_path))
|
| 172 |
+
|
| 173 |
+
# 儲存 YOLO 辨識資訊
|
| 174 |
+
output_yolo_txt_path = run_output_dir / f"{image_base_name}_yolo_objects.txt"
|
| 175 |
+
output_yolo_txt_path.write_text("\n".join(yolo_output_content), encoding='utf-8')
|
| 176 |
+
all_result_files.append(str(output_yolo_txt_path))
|
| 177 |
+
|
| 178 |
+
# --- 3b. MLLM 分析 (如果啟用) ---
|
| 179 |
+
output_mllm_txt_path = None
|
| 180 |
+
if enable_mllm:
|
| 181 |
+
try:
|
| 182 |
+
prompt_to_use = mllm_prompt if mllm_prompt and mllm_prompt.strip() else None
|
| 183 |
+
mllm_str = genai.analyze_content_with_gemini(str(image_path), prompt_to_use)
|
| 184 |
+
mllm_result_content = f"--- MLLM 分析結果 ---\n{mllm_str}"
|
| 185 |
+
except Exception as e:
|
| 186 |
+
mllm_result_content = f"--- MLLM 分析失敗 ---\n原因: {e}"
|
| 187 |
+
|
| 188 |
+
output_mllm_txt_path = run_output_dir / f"{image_base_name}_mllm_result.txt"
|
| 189 |
+
output_mllm_txt_path.write_text(mllm_result_content, encoding='utf-8')
|
| 190 |
+
all_result_files.append(str(output_mllm_txt_path))
|
| 191 |
+
|
| 192 |
+
# 將本次圖片的結果加入到總列表中
|
| 193 |
+
all_texts.append("\n".join(yolo_output_content))
|
| 194 |
+
if output_mllm_txt_path:
|
| 195 |
+
all_texts.append(output_mllm_txt_path.read_text(encoding='utf-8'))
|
| 196 |
+
|
| 197 |
+
|
| 198 |
+
# --- 4. 完成處理,打包並更新最終結果 ---
|
| 199 |
+
progress(1, desc="打包結果中...")
|
| 200 |
+
zip_filename = run_output_dir / f"run_{run_id[:8]}_results.zip"
|
| 201 |
+
created_zip_path = create_zip_archive(all_result_files, str(zip_filename))
|
| 202 |
+
|
| 203 |
+
final_status = f"處理完成!共 {total_images} 張圖片。結果儲存於: {run_output_dir.absolute()}"
|
| 204 |
+
combined_text_output = "\n\n".join(all_texts)
|
| 205 |
+
|
| 206 |
+
yield {
|
| 207 |
+
output_status: gr.update(value=final_status),
|
| 208 |
+
download_button: gr.update(value=created_zip_path, visible=True),
|
| 209 |
+
output_text: gr.update(value=combined_text_output),
|
| 210 |
+
output_gallery: gr.update(value=annotated_image_paths) # 確保最終 gallery 也被更新
|
| 211 |
+
}
|
| 212 |
+
|
| 213 |
+
def toggle_mllm_prompt(is_enabled):
|
| 214 |
+
"""
|
| 215 |
+
根據 Checkbox 狀態,顯示或隱藏 MLLM prompt 輸入框。
|
| 216 |
+
"""
|
| 217 |
+
return gr.update(visible=is_enabled)
|
| 218 |
+
|
| 219 |
+
# --- Gradio Interface ---
|
| 220 |
+
with gr.Blocks(theme=gr.themes.Soft()) as demo:
|
| 221 |
+
gr.Markdown("# 智慧影像分析工具 (YOLO + MLLM)")
|
| 222 |
+
gr.Markdown("上傳圖片與YOLO模型進行物件偵測,並可選用MLLM進行進階圖像理解。")
|
| 223 |
+
|
| 224 |
+
with gr.Row():
|
| 225 |
+
with gr.Column(scale=1):
|
| 226 |
+
# 輸入元件
|
| 227 |
+
image_input = gr.File(label="上傳圖片", file_count="multiple", file_types=["image"])
|
| 228 |
+
#model_input = gr.File(label="上傳YOLO模型 (.pt)", file_count="multiple", file_types=[".pt"], info="若不提供,將使用預設的 yolov8n.pt 模型。")
|
| 229 |
+
model_input = gr.File(label="上傳YOLO模型 (.pt)", file_count="multiple", file_types=[".pt"])
|
| 230 |
+
|
| 231 |
+
with gr.Accordion("進階設定", open=False):
|
| 232 |
+
conf_slider = gr.Slider(minimum=0.1, maximum=1, value=0.40, step=0.05, label="信賴度閾值")
|
| 233 |
+
mllm_enabled_checkbox = gr.Checkbox(label="開啟MLLM辨識", value=False)
|
| 234 |
+
mllm_prompt_input = gr.Textbox(label="自訂 MLLM Prompt (選填)", placeholder="例如:請描述圖中人物的穿著與場景。", visible=False)
|
| 235 |
+
|
| 236 |
+
run_button = gr.Button("開始辨識", variant="primary")
|
| 237 |
+
|
| 238 |
+
with gr.Column(scale=2):
|
| 239 |
+
# 輸出元件
|
| 240 |
+
output_gallery = gr.Gallery(label="辨識結果預覽", height=500, object_fit="contain", allow_preview=True)
|
| 241 |
+
output_text = gr.Textbox(label="詳細辨識資訊", lines=15, placeholder="辨識完成後,所有結果將顯示於此。")
|
| 242 |
+
output_status = gr.Textbox(label="執行狀態", interactive=False)
|
| 243 |
+
download_button = gr.File(label="下載所有結果 (.zip)", file_count="single", visible=False)
|
| 244 |
+
|
| 245 |
+
# --- 事件綁定 ---
|
| 246 |
+
|
| 247 |
+
# 點擊 "開始辨識" 按鈕
|
| 248 |
+
run_button.click(
|
| 249 |
+
fn=gradio_multi_model_detection,
|
| 250 |
+
inputs=[image_input, model_input, conf_slider, mllm_enabled_checkbox, mllm_prompt_input],
|
| 251 |
+
outputs=[output_gallery, output_status, download_button, output_text]
|
| 252 |
+
)
|
| 253 |
+
|
| 254 |
+
# 勾選/取消 "開啟MLLM辨識"
|
| 255 |
+
mllm_enabled_checkbox.change(
|
| 256 |
+
fn=toggle_mllm_prompt,
|
| 257 |
+
inputs=mllm_enabled_checkbox,
|
| 258 |
+
outputs=mllm_prompt_input
|
| 259 |
+
)
|
| 260 |
+
|
| 261 |
+
# 啟動 Gradio 應用
|
| 262 |
+
if __name__ == "__main__":
|
| 263 |
+
demo.launch(debug=True)
|
requirements.txt
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
google-generativeai
|
| 2 |
+
Pillow
|
| 3 |
+
gradio
|
| 4 |
+
ultralytics
|
| 5 |
+
numpy
|
| 6 |
+
PyYAML
|
| 7 |
+
transformers
|
target.py
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
target_JSON = {
|
| 2 |
+
"物理環境": ["辦公室", "臥室", "工作室", "工廠"],
|
| 3 |
+
"技術應用": ["人工智慧", "虛擬實境", "大數據分析", "其他"],
|
| 4 |
+
"社交關係": ["獨立工作(1人)", "團隊合作(2人以上)", "遠程協作(遠端控制)"],
|
| 5 |
+
"職業情感": ["快樂", "睡覺", "壓力/焦慮", "成就感"],
|
| 6 |
+
"資訊設備": [
|
| 7 |
+
"AI助手",
|
| 8 |
+
"投影儀",
|
| 9 |
+
"手機",
|
| 10 |
+
"眼鏡投影",
|
| 11 |
+
"智慧手錶",
|
| 12 |
+
"機械手臂",
|
| 13 |
+
"平板",
|
| 14 |
+
"電腦",
|
| 15 |
+
"鍵盤",
|
| 16 |
+
"滑鼠",
|
| 17 |
+
"其他",
|
| 18 |
+
],
|
| 19 |
+
"物體": [
|
| 20 |
+
"床",
|
| 21 |
+
"椅子",
|
| 22 |
+
"桌子",
|
| 23 |
+
"書架",
|
| 24 |
+
"PC",
|
| 25 |
+
"肖像",
|
| 26 |
+
"監視器",
|
| 27 |
+
"窗戶",
|
| 28 |
+
"冷氣機",
|
| 29 |
+
"其他",
|
| 30 |
+
],
|
| 31 |
+
"角色": ["機器人", "教師", "學生", "動物", "工作人員"],
|
| 32 |
+
}
|
讀我.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# 如果有多個金鑰,可以放在列表中
|
| 3 |
+
my_api_key = ['AIzaSyC6nBDxCuiE5GzBdTRQd-roYqVCGYCRy5M','AIzaSyDKHts9C72a68x58z1ItSRxgIU65UKN_xw','AIzaSyCgUnkkgAsBpsfrKe2Lqy5WgAbP0ktxKbg']
|
| 4 |
+
# 隨機選擇一個金鑰避免同時間大量使用同一個金鑰會被停用API服務
|
| 5 |
+
my_api_key = random.choice(my_api_key)
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
# 如何寫進去
|
| 9 |
+
* For the Command Prompt: `set MYKEY=123`
|
| 10 |
+
* For PowerShell: `$env:MYKEY="123"`
|
| 11 |
+
|
| 12 |
+
# 如何讀出來
|
| 13 |
+
* For the Command Prompt: `echo %MYKEY%`
|
| 14 |
+
* For PowerShell: `echo $env:MYKEY`
|
| 15 |
+
* 程式 os.getenv('MYKEY')
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
-----
|
| 20 |
+
vscode 的終端機是cmd 所以
|
| 21 |
+
set my_api_key=['AIzaSyC6nBDxCuiE5GzBdTRQd-roYqVCGYCRy5M','AIzaSyDKHts9C72a68x58z1ItSRxgIU65UKN_xw','AIzaSyCgUnkkgAsBpsfrKe2Lqy5WgAbP0ktxKbg','AIzaSyA80kB4KJ7DM8AVAqPpNP6gl49RD_lwSs4','AIzaSyAbOxdAWYwgXzvSI45BkvTNOpvZW6q-pNw']
|
| 22 |
+
|
| 23 |
+
echo %my_api_key%
|