Upload 3 files

app.py

@@ -0,0 +1,386 @@
+"""
+Gradio部署專用腳本
+優化用於Gradio Spaces部署
+"""
+
+import gradio as gr
+import os
+import sys
+import logging
+from typing import Dict, Optional
+import tempfile
+import shutil
+
+# 設定日誌
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# 導入分析模組
+try:
+    from modules.text_analyzer import TextAnalyzer
+    from modules.image_analyzer import ImageAnalyzer
+    from modules.video_analyzer import VideoAnalyzer
+    from modules.multimodal_fusion import MultimodalFusion
+    from utils.file_handler import FileHandler
+    from utils.config import Config
+except ImportError as e:
+    logger.error(f"模組導入失敗: {e}")
+    # 創建簡化版本的分析器
+    class TextAnalyzer:
+        def analyze(self, text, analysis_type="comprehensive"):
+            return {"sentiment": "中性", "keywords": ["測試"], "summary": "測試分析"}
+    
+    class ImageAnalyzer:
+        def analyze(self, image_path, analysis_type="comprehensive"):
+            return {"objects": ["測試物件"], "scene": "測試場景", "summary": "測試分析"}
+    
+    class VideoAnalyzer:
+        def analyze(self, video_path, analysis_type="comprehensive"):
+            return {"actions": ["測試動作"], "audio_sentiment": "中性", "summary": "測試分析"}
+    
+    class MultimodalFusion:
+        def fuse_analysis(self, text_analysis, image_analysis, video_analysis):
+            return {"fused_sentiment": "中性", "summary": "測試融合分析"}
+    
+    class FileHandler:
+        pass
+    
+    class Config:
+        def get(self, key, default=None):
+            return default
+
+class GradioSocialMediaAnalyzer:
+    """Gradio專用社交媒體分析器"""
+    
+    def __init__(self):
+        """初始化分析器"""
+        try:
+            self.config = Config()
+            self.text_analyzer = TextAnalyzer()
+            self.image_analyzer = ImageAnalyzer()
+            self.video_analyzer = VideoAnalyzer()
+            self.multimodal_fusion = MultimodalFusion()
+            self.file_handler = FileHandler()
+            logger.info("所有分析模組載入成功")
+        except Exception as e:
+            logger.error(f"分析器初始化失敗: {e}")
+            # 使用簡化版本
+            self.text_analyzer = TextAnalyzer()
+            self.image_analyzer = ImageAnalyzer()
+            self.video_analyzer = VideoAnalyzer()
+            self.multimodal_fusion = MultimodalFusion()
+    
+    def analyze_content(self, 
+                       text_input: Optional[str] = None,
+                       image_input: Optional[str] = None,
+                       video_input: Optional[str] = None,
+                       analysis_type: str = "comprehensive") -> Dict:
+        """分析多模態內容"""
+        try:
+            results = {
+                "text_analysis": None,
+                "image_analysis": None,
+                "video_analysis": None,
+                "multimodal_analysis": None,
+                "summary": ""
+            }
+            
+            # 文字分析
+            if text_input and text_input.strip():
+                logger.info("開始文字分析...")
+                results["text_analysis"] = self.text_analyzer.analyze(text_input, analysis_type)
+            
+            # 圖片分析
+            if image_input:
+                logger.info("開始圖片分析...")
+                results["image_analysis"] = self.image_analyzer.analyze(image_input, analysis_type)
+            
+            # 影片分析
+            if video_input:
+                logger.info("開始影片分析...")
+                results["video_analysis"] = self.video_analyzer.analyze(video_input, analysis_type)
+            
+            # 多模態融合分析
+            if any([text_input, image_input, video_input]):
+                logger.info("開始多模態融合分析...")
+                results["multimodal_analysis"] = self.multimodal_fusion.fuse_analysis(
+                    results["text_analysis"],
+                    results["image_analysis"],
+                    results["video_analysis"]
+                )
+                
+                # 生成總結
+                results["summary"] = self._generate_summary(results)
+            
+            logger.info("分析完成")
+            return results
+            
+        except Exception as e:
+            logger.error(f"分析過程中發生錯誤: {str(e)}")
+            return {"error": str(e)}
+
+    def _generate_summary(self, results: Dict) -> str:
+        """生成分析總結"""
+        summary_parts = []
+        
+        if results["text_analysis"]:
+            summary_parts.append(f"文字分析: {results['text_analysis'].get('summary', 'N/A')}")
+        
+        if results["image_analysis"]:
+            summary_parts.append(f"圖片分析: {results['image_analysis'].get('summary', 'N/A')}")
+        
+        if results["video_analysis"]:
+            summary_parts.append(f"影片分析: {results['video_analysis'].get('summary', 'N/A')}")
+        
+        if results["multimodal_analysis"]:
+            summary_parts.append(f"綜合分析: {results['multimodal_analysis'].get('summary', 'N/A')}")
+        
+        return "\n".join(summary_parts)
+
+# 創建全局分析器實例
+analyzer = GradioSocialMediaAnalyzer()
+
+def analyze_interface(text: str, image, video, analysis_type: str):
+    """Gradio介面函數"""
+    try:
+        # 處理檔案輸入
+        image_path = None
+        video_path = None
+        
+        if image:
+            image_path = image.name if hasattr(image, 'name') else str(image)
+        
+        if video:
+            video_path = video.name if hasattr(video, 'name') else str(video)
+        
+        # 執行分析
+        results = analyzer.analyze_content(
+            text_input=text if text.strip() else None,
+            image_input=image_path,
+            video_input=video_path,
+            analysis_type=analysis_type
+        )
+        
+        if "error" in results:
+            return f"分析錯誤: {results['error']}", "", "", ""
+        
+        # 格式化輸出
+        text_output = format_text_analysis(results.get("text_analysis", {}))
+        image_output = format_image_analysis(results.get("image_analysis", {}))
+        video_output = format_video_analysis(results.get("video_analysis", {}))
+        summary_output = results.get("summary", "無分析結果")
+        
+        return text_output, image_output, video_output, summary_output
+        
+    except Exception as e:
+        error_msg = f"處理過程中發生錯誤: {str(e)}"
+        logger.error(error_msg)
+        return error_msg, "", "", ""
+
+def format_text_analysis(analysis: Dict) -> str:
+    """格式化文字分析結果"""
+    if not analysis:
+        return "無文字分析結果"
+    
+    formatted = []
+    if "sentiment" in analysis:
+        formatted.append(f"情感分析: {analysis['sentiment']}")
+    if "keywords" in analysis:
+        formatted.append(f"關鍵詞: {', '.join(analysis['keywords'])}")
+    if "topics" in analysis:
+        formatted.append(f"主題: {', '.join(analysis['topics'])}")
+    if "summary" in analysis:
+        formatted.append(f"總結: {analysis['summary']}")
+    
+    return "\n".join(formatted)
+
+def format_image_analysis(analysis: Dict) -> str:
+    """格式化圖片分析結果"""
+    if not analysis:
+        return "無圖片分析結果"
+    
+    formatted = []
+    if "objects" in analysis:
+        formatted.append(f"偵測物件: {', '.join(analysis['objects'])}")
+    if "scene" in analysis:
+        formatted.append(f"場景描述: {analysis['scene']}")
+    if "sentiment" in analysis:
+        formatted.append(f"圖片情感: {analysis['sentiment']}")
+    if "summary" in analysis:
+        formatted.append(f"總結: {analysis['summary']}")
+    
+    return "\n".join(formatted)
+
+def format_video_analysis(analysis: Dict) -> str:
+    """格式化影片分析結果"""
+    if not analysis:
+        return "無影片分析結果"
+    
+    formatted = []
+    if "objects" in analysis:
+        formatted.append(f"偵測物件: {', '.join(analysis['objects'])}")
+    if "actions" in analysis:
+        formatted.append(f"動作識別: {', '.join(analysis['actions'])}")
+    if "audio_sentiment" in analysis:
+        formatted.append(f"音頻情感: {analysis['audio_sentiment']}")
+    if "summary" in analysis:
+        formatted.append(f"總結: {analysis['summary']}")
+    
+    return "\n".join(formatted)
+
+def create_gradio_app():
+    """創建Gradio應用程式"""
+    
+    # 創建Gradio介面
+    with gr.Blocks(
+        title="社交媒體多模態內容分析系統",
+        theme=gr.themes.Soft(),
+        css="""
+        .gradio-container {
+            max-width: 1200px !important;
+            margin: auto !important;
+        }
+        .main-header {
+            text-align: center;
+            margin-bottom: 2rem;
+        }
+        """
+    ) as app:
+        
+        # 標題和說明
+        with gr.Row():
+            gr.HTML("""
+            <div class="main-header">
+                <h1>🔍 社交媒體多模態內容分析系統</h1>
+                <p>支援文字、圖片、影片的智能分析與多模態融合</p>
+            </div>
+            """)
+        
+        # 主要內容區域
+        with gr.Row():
+            # 左側輸入區域
+            with gr.Column(scale=1):
+                gr.Markdown("### 📝 輸入內容")
+                
+                text_input = gr.Textbox(
+                    label="文字內容",
+                    placeholder="請輸入要分析的文字內容...",
+                    lines=5,
+                    max_lines=10
+                )
+                
+                image_input = gr.File(
+                    label="圖片檔案",
+                    file_types=["image"],
+                    file_count="single"
+                )
+                
+                video_input = gr.File(
+                    label="影片檔案",
+                    file_types=["video"],
+                    file_count="single"
+                )
+                
+                analysis_type = gr.Dropdown(
+                    choices=[
+                        ("綜合分析", "comprehensive"),
+                        ("情感分析", "sentiment"),
+                        ("內容分類", "content_classification"),
+                        ("物件檢測", "object_detection")
+                    ],
+                    value="comprehensive",
+                    label="分析類型"
+                )
+                
+                analyze_btn = gr.Button(
+                    "🚀 開始分析",
+                    variant="primary",
+                    size="lg"
+                )
+            
+            # 右側結果區域
+            with gr.Column(scale=1):
+                gr.Markdown("### 📊 分析結果")
+                
+                text_output = gr.Textbox(
+                    label="📝 文字分析結果",
+                    lines=8,
+                    interactive=False,
+                    show_copy_button=True
+                )
+                
+                image_output = gr.Textbox(
+                    label="🖼️ 圖片分析結果",
+                    lines=8,
+                    interactive=False,
+                    show_copy_button=True
+                )
+                
+                video_output = gr.Textbox(
+                    label="🎬 影片分析結果",
+                    lines=8,
+                    interactive=False,
+                    show_copy_button=True
+                )
+                
+                summary_output = gr.Textbox(
+                    label="🎯 綜合分析總結",
+                    lines=6,
+                    interactive=False,
+                    show_copy_button=True
+                )
+        
+        # 範例區域
+        with gr.Row():
+            gr.Markdown("""
+            ### 💡 使用範例
+            
+            **文字分析範例：**
+            - 輸入：「這個新產品真的很棒，我強烈推薦給大家！」
+            - 分析：情感分析、關鍵詞提取、主題識別
+            
+            **圖片分析範例：**
+            - 上傳：風景照片、人物照片、產品圖片
+            - 分析：物件檢測、場景識別、情感分析
+            
+            **影片分析範例：**
+            - 上傳：短影片、廣告影片、教學影片
+            - 分析：動作識別、音頻分析、場景變化
+            
+            **多模態分析：**
+            - 同時上傳多種內容類型
+            - 系統會進行綜合分析並提供融合結果
+            """)
+        
+        # 綁定事件
+        analyze_btn.click(
+            fn=analyze_interface,
+            inputs=[text_input, image_input, video_input, analysis_type],
+            outputs=[text_output, image_output, video_output, summary_output]
+        )
+        
+        # 清除按鈕
+        clear_btn = gr.Button("🗑️ 清除所有", variant="secondary")
+        clear_btn.click(
+            fn=lambda: ("", None, None, "comprehensive", "", "", "", ""),
+            outputs=[text_input, image_input, video_input, analysis_type, 
+                    text_output, image_output, video_output, summary_output]
+        )
+    
+    return app
+
+# Gradio Spaces 部署配置
+if __name__ == "__main__":
+    # 創建應用程式
+    app = create_gradio_app()
+    
+    # 啟動應用程式
+    app.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=False,  # 在Spaces上不需要share
+        debug=False,  # 生產環境關閉debug
+        show_error=True,
+        quiet=False,
+        pinned=False  # 設定pinned為布林值
+    )

config_spaces.json

@@ -0,0 +1,36 @@
+{
+  "models": {
+    "text_model": "distilbert-base-chinese",
+    "image_model": "mobilenet_v2",
+    "video_model": "slowfast",
+    "multimodal_model": "clip"
+  },
+  "analysis": {
+    "max_text_length": 256,
+    "max_image_size": 224,
+    "max_video_duration": 15,
+    "confidence_threshold": 0.5
+  },
+  "api": {
+    "openai_api_key": "",
+    "huggingface_token": "",
+    "google_api_key": ""
+  },
+  "storage": {
+    "temp_dir": "/tmp",
+    "output_dir": "/tmp/output",
+    "max_file_size": 10485760
+  },
+  "logging": {
+    "level": "INFO",
+    "format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+  },
+  "gradio": {
+    "server_name": "0.0.0.0",
+    "server_port": 7860,
+    "share": false,
+    "debug": false,
+    "show_error": true,
+    "quiet": false
+  }
+}

requirements.txt

@@ -0,0 +1,17 @@
+# Gradio Spaces 部署專用依賴套件
+gradio>=4.0.0
+opencv-python-headless>=4.8.0
+numpy>=1.24.0
+jieba>=0.42.1
+librosa>=0.10.0
+scikit-learn>=1.3.0
+Pillow>=10.0.0
+matplotlib>=3.7.0
+pandas>=2.0.0
+requests>=2.31.0
+tqdm>=4.65.0
+
+# 可選的深度學習套件（如果需要更進階的分析）
+# torch>=2.0.0
+# transformers>=4.30.0
+# torchvision>=0.15.0