CREATE: Dockerfile for deployment

.dockerignore

@@ -0,0 +1,113 @@
+# Git
+.git
+.gitignore
+.gitattributes
+
+# Python
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env
+pip-log.txt
+pip-delete-this-directory.txt
+.tox
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.log
+.git
+.mypy_cache
+.pytest_cache
+.hypothesis
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# Environment variables
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Docker
+Dockerfile
+.dockerignore
+docker-compose.yml
+docker-compose.yaml
+
+# Documentation
+README*.md
+DEPLOYMENT_GUIDE.md
+*.md
+
+# Deployment scripts
+deploy_to_spaces.py
+app_spaces.py
+requirements_spaces.txt
+README_spaces.md
+
+# Large files that shouldn't be in container
+*.pth
+*.bin
+*.safetensors
+*.ckpt
+*.h5
+*.hdf5
+*.pkl
+*.pickle
+*.joblib
+*.model
+*.weights
+*.pt
+*.onnx
+*.tflite
+*.pb
+*.savedmodel
+*.mar
+*.mlmodel
+*.mlpackage
+*.mlflow
+*.bundle
+
+# Archives
+*.zip
+*.tar.gz
+*.rar
+*.7z
+*.gz
+*.bz2
+*.xz
+*.lzma
+*.zst
+*.lz4
+*.br
+
+# Temporary files
+*.tmp
+*.temp
+temp/
+tmp/

.gitattributes

@@ -0,0 +1,95 @@
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.hdf5 filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.weights filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.savedmodel filter=lfs diff=lfs merge=lfs -text
+*.mar filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.mlpackage filter=lfs diff=lfs merge=lfs -text
+*.mlflow filter=lfs diff=lfs merge=lfs -text
+*.bundle filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.lzma filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.br filter=lfs diff=lfs merge=lfs -text
+*.z filter=lfs diff=lfs merge=lfs -text
+*.Z filter=lfs diff=lfs merge=lfs -text
+*.ar filter=lfs diff=lfs merge=lfs -text
+*.deb filter=lfs diff=lfs merge=lfs -text
+*.rpm filter=lfs diff=lfs merge=lfs -text
+*.iso filter=lfs diff=lfs merge=lfs -text
+*.img filter=lfs diff=lfs merge=lfs -text
+*.vmdk filter=lfs diff=lfs merge=lfs -text
+*.vdi filter=lfs diff=lfs merge=lfs -text
+*.vhd filter=lfs diff=lfs merge=lfs -text
+*.vhdx filter=lfs diff=lfs merge=lfs -text
+*.qcow2 filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+*.dmg filter=lfs diff=lfs merge=lfs -text
+*.pkg filter=lfs diff=lfs diff=lfs merge=lfs -text
+*.exe filter=lfs diff=lfs merge=lfs -text
+*.msi filter=lfs diff=lfs merge=lfs -text
+*.app filter=lfs diff=lfs merge=lfs -text
+*.dll filter=lfs diff=lfs merge=lfs -text
+*.so filter=lfs diff=lfs merge=lfs -text
+*.dylib filter=lfs diff=lfs merge=lfs -text
+*.a filter=lfs diff=lfs merge=lfs -text
+*.lib filter=lfs diff=lfs diff=lfs merge=lfs -text
+*.o filter=lfs diff=lfs merge=lfs -text
+*.obj filter=lfs diff=lfs merge=lfs -text
+*.ko filter=lfs diff=lfs merge=lfs -text
+*.elf filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.hex filter=lfs diff=lfs merge=lfs -text
+*.s19 filter=lfs diff=lfs merge=lfs -text
+*.ihex filter=lfs diff=lfs merge=lfs -text
+*.mot filter=lfs diff=lfs merge=lfs -text
+*.srec filter=lfs diff=lfs merge=lfs -text
+*.uboot filter=lfs diff=lfs merge=lfs -text
+*.img filter=lfs diff=lfs merge=lfs -text
+*.iso filter=lfs diff=lfs merge=lfs -text
+*.vmdk filter=lfs diff=lfs merge=lfs -text
+*.vdi filter=lfs diff=lfs merge=lfs -text
+*.vhd filter=lfs diff=lfs merge=lfs -text
+*.vhdx filter=lfs diff=lfs merge=lfs -text
+*.qcow2 filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+*.dmg filter=lfs diff=lfs merge=lfs -text
+*.pkg filter=lfs diff=lfs diff=lfs merge=lfs -text
+*.exe filter=lfs diff=lfs merge=lfs -text
+*.msi filter=lfs diff=lfs merge=lfs -text
+*.app filter=lfs diff=lfs merge=lfs -text
+*.dll filter=lfs diff=lfs merge=lfs -text
+*.so filter=lfs diff=lfs merge=lfs -text
+*.dylib filter=lfs diff=lfs merge=lfs -text
+*.a filter=lfs diff=lfs merge=lfs -text
+*.lib filter=lfs diff=lfs diff=lfs merge=lfs -text
+*.o filter=lfs diff=lfs merge=lfs -text
+*.obj filter=lfs diff=lfs merge=lfs -text
+*.ko filter=lfs diff=lfs merge=lfs -text
+*.elf filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.hex filter=lfs diff=lfs merge=lfs -text
+*.s19 filter=lfs diff=lfs merge=lfs -text
+*.ihex filter=lfs diff=lfs merge=lfs -text
+*.mot filter=lfs diff=lfs merge=lfs -text
+*.srec filter=lfs diff=lfs merge=lfs -text
+*.uboot filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,37 @@
+# Use Python 3.9 slim image
+FROM python:3.9-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies for OpenCV and audio
+RUN apt-get update && apt-get install -y \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
+    libavcodec-dev \
+    libavformat-dev \
+    libswscale-dev \
+    libv4l-dev \
+    libxvidcore-dev \
+    libx264-dev \
+    libjpeg-dev \
+    libpng-dev \
+    libtiff-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements and install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the app
+COPY app.py .
+COPY simple_model_manager.py .
+
+# Expose port
+EXPOSE 7860
+
+# Run Streamlit
+CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]

debug_drive.py

@@ -1,185 +0,0 @@
-#!/usr/bin/env python3
-"""
-Debug Google Drive download issues
-"""
-
-import os
-import requests
-import re
-from pathlib import Path
-
-
-# Load .env file manually
-def load_env():
-    env_file = Path(".env")
-    if env_file.exists():
-        with open(env_file, "r") as f:
-            for line in f:
-                line = line.strip()
-                if line and not line.startswith("#") and "=" in line:
-                    key, value = line.split("=", 1)
-                    os.environ[key.strip()] = value.strip().strip('"')
-
-
-def test_drive_bypass(file_id):
-    """Test different bypass methods"""
-    print(f"Testing file ID: {file_id}")
-    print("=" * 50)
-
-    # Method 1: Direct bypass
-    print("\n1. Testing direct bypass...")
-    try:
-        url = f"https://drive.usercontent.google.com/download?id={file_id}&export=download&confirm=t"
-        response = requests.get(url, stream=True)
-        print(f"Status: {response.status_code}")
-        print(f"Content-Type: {response.headers.get('content-type', 'Unknown')}")
-
-        first_chunk = next(response.iter_content(chunk_size=1024), b"")
-        if first_chunk.startswith(b"<!DOCTYPE") or first_chunk.startswith(b"<html"):
-            print("❌ Still getting HTML")
-            html_content = first_chunk.decode("utf-8", errors="ignore")
-            print(f"HTML preview: {html_content[:200]}...")
-        else:
-            print("✅ Got file content!")
-            print(f"First bytes: {first_chunk[:50]}")
-            return True
-    except Exception as e:
-        print(f"❌ Error: {e}")
-
-    # Method 2: Session-based approach
-    print("\n2. Testing session-based approach...")
-    try:
-        session = requests.Session()
-        session.headers.update(
-            {
-                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
-                "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
-                "Accept-Language": "en-US,en;q=0.5",
-            }
-        )
-
-        # First get the virus scan page
-        virus_url = f"https://drive.google.com/uc?export=download&id={file_id}"
-        response = session.get(virus_url)
-        print(f"Virus page status: {response.status_code}")
-
-        # Extract confirm and UUID
-        html_content = response.text
-        confirm_match = re.search(r'name="confirm" value="([^"]+)"', html_content)
-        uuid_match = re.search(r'name="uuid" value="([^"]+)"', html_content)
-
-        if confirm_match and uuid_match:
-            confirm_value = confirm_match.group(1)
-            uuid_value = uuid_match.group(1)
-            print(f"Found confirm: {confirm_value}")
-            print(f"Found UUID: {uuid_value}")
-
-            # Submit form
-            form_data = {
-                "id": file_id,
-                "export": "download",
-                "confirm": confirm_value,
-                "uuid": uuid_value,
-            }
-            form_url = "https://drive.usercontent.google.com/download"
-            response = session.post(form_url, data=form_data, stream=True)
-
-            print(f"Form submission status: {response.status_code}")
-            first_chunk = next(response.iter_content(chunk_size=1024), b"")
-
-            if first_chunk.startswith(b"<!DOCTYPE") or first_chunk.startswith(b"<html"):
-                print("❌ Form submission still returned HTML")
-            else:
-                print("✅ Form submission successful!")
-                return True
-        else:
-            print("❌ Could not extract confirm/UUID")
-            print(f"HTML preview: {html_content[:300]}...")
-
-    except Exception as e:
-        print(f"❌ Error: {e}")
-
-    # Method 3: Extract download URL from file page
-    print("\n3. Testing file page extraction...")
-    try:
-        session = requests.Session()
-        session.headers.update(
-            {
-                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
-                "Referer": "https://drive.google.com/",
-            }
-        )
-
-        file_url = f"https://drive.google.com/file/d/{file_id}/view"
-        response = session.get(file_url)
-        print(f"File page status: {response.status_code}")
-
-        if response.status_code == 200:
-            # Look for download URL in the page
-            download_match = re.search(r'"downloadUrl":"([^"]+)"', response.text)
-            if download_match:
-                download_url = (
-                    download_match.group(1)
-                    .replace("\\u003d", "=")
-                    .replace("\\u0026", "&")
-                )
-                print(f"Found download URL: {download_url}")
-
-                # Try downloading from this URL
-                response = session.get(download_url, stream=True)
-                first_chunk = next(response.iter_content(chunk_size=1024), b"")
-
-                if first_chunk.startswith(b"<!DOCTYPE") or first_chunk.startswith(
-                    b"<html"
-                ):
-                    print("❌ Download URL still returned HTML")
-                else:
-                    print("✅ Download URL successful!")
-                    return True
-            else:
-                print("❌ Could not find download URL in page")
-        else:
-            print(f"❌ Could not access file page")
-
-    except Exception as e:
-        print(f"❌ Error: {e}")
-
-    print("\n❌ All methods failed")
-    return False
-
-
-def main():
-    print("Google Drive Bypass Debug Tool")
-    print("=" * 50)
-
-    # Load environment variables
-    load_env()
-
-    # Get file ID from environment or user input
-    vision_url = os.getenv("VISION_MODEL_DRIVE_LINK", "")
-    audio_url = os.getenv("AUDIO_MODEL_DRIVE_LINK", "")
-
-    if not vision_url and not audio_url:
-        print("❌ No environment variables found!")
-        print("Please set VISION_MODEL_DRIVE_LINK or AUDIO_MODEL_DRIVE_LINK")
-        return
-
-    if vision_url:
-        print(f"\nTesting Vision Model URL: {vision_url}")
-        if "/file/d/" in vision_url:
-            file_id = vision_url.split("/file/d/")[1].split("/")[0]
-            test_drive_bypass(file_id)
-        else:
-            print("❌ Invalid vision model URL format")
-
-    if audio_url:
-        print(f"\nTesting Audio Model URL: {audio_url}")
-        if "/file/d/" in audio_url:
-            file_id = audio_url.split("/file/d/")[1].split("/")[0]
-            test_drive_bypass(file_id)
-        else:
-            print("❌ Invalid audio model URL format")
-
-
-if __name__ == "__main__":
-    main()

run_app.py

@@ -1,65 +0,0 @@
-#!/usr/bin/env python3
-"""
-Startup script for the Sentiment Analysis Testing Ground Streamlit application.
-This script provides an easy way to launch the application with proper configuration.
-"""
-
-import subprocess
-import sys
-import os
-
-
-def main():
-    """Main function to start the Streamlit application."""
-
-    print("🧠 Starting Sentiment Analysis Testing Ground...")
-    print("=" * 50)
-
-    # Check if app.py exists
-    if not os.path.exists("app.py"):
-        print("❌ Error: app.py not found in current directory!")
-        print("Please make sure you're in the correct directory.")
-        sys.exit(1)
-
-    # Check if requirements are installed
-    try:
-        import streamlit
-        import pandas
-        import PIL
-
-        print("✅ Dependencies check passed")
-    except ImportError as e:
-        print(f"❌ Missing dependency: {e}")
-        print("Please install requirements: pip install -r requirements.txt")
-        sys.exit(1)
-
-    print("🚀 Launching Streamlit application...")
-    print("📱 The app will open in your default browser")
-    print("🔗 If it doesn't open automatically, go to: http://localhost:8501")
-    print("⏹️  Press Ctrl+C to stop the application")
-    print("=" * 50)
-
-    try:
-        # Start Streamlit with the app
-        subprocess.run(
-            [
-                sys.executable,
-                "-m",
-                "streamlit",
-                "run",
-                "app.py",
-                "--server.headless",
-                "false",
-                "--server.port",
-                "8501",
-            ]
-        )
-    except KeyboardInterrupt:
-        print("\n👋 Application stopped by user")
-    except Exception as e:
-        print(f"❌ Error starting application: {e}")
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()

simple_model_manager.py

@@ -1,8 +1,3 @@
-#!/usr/bin/env python3
-"""
-Simple Model Manager - Downloads models from Google Drive using gdown
-"""
-
 import os
 import gdown
 from pathlib import Path
@@ -11,22 +6,9 @@ from typing import Tuple, Any
 import torch
 import torch.nn as nn
 from torchvision import models
+from dotenv import load_dotenv
 
-# Try to load .env file if it exists
-try:
-    from dotenv import load_dotenv
-
-    load_dotenv()
-except ImportError:
-    # If python-dotenv is not installed, try to load .env manually
-    env_file = Path(".env")
-    if env_file.exists():
-        with open(env_file, "r") as f:
-            for line in f:
-                line = line.strip()
-                if line and not line.startswith("#") and "=" in line:
-                    key, value = line.split("=", 1)
-                    os.environ[key.strip()] = value.strip()
+load_dotenv()
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)

test_audio_model.py

@@ -1,173 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test script for the Wav2Vec2 audio sentiment analysis model
-"""
-
-import os
-import torch
-import numpy as np
-import librosa
-from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
-import tempfile
-
-
-def test_audio_model():
-    """Test the audio model loading and inference"""
-
-    print("🔊 Testing Wav2Vec2 Audio Sentiment Model")
-    print("=" * 50)
-
-    # Check if model file exists
-    model_path = "models/wav2vec2_model.pth"
-    if not os.path.exists(model_path):
-        print(f"❌ Audio model file not found at: {model_path}")
-        return False
-
-    print(f"✅ Found model file: {model_path}")
-
-    try:
-        # Set device
-        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        print(f"🖥️  Using device: {device}")
-
-        # Load the model checkpoint to check architecture
-        checkpoint = torch.load(model_path, map_location=device)
-        print(f"📊 Checkpoint keys: {list(checkpoint.keys())}")
-
-        # Check for classifier weights
-        if "classifier.weight" in checkpoint:
-            num_classes = checkpoint["classifier.weight"].shape[0]
-            print(f"📊 Model has {num_classes} output classes")
-        else:
-            print("⚠️  Could not determine number of classes from checkpoint")
-            num_classes = 3  # Default assumption
-
-        # Initialize model
-        print("🔄 Initializing Wav2Vec2 model...")
-        model_checkpoint = "facebook/wav2vec2-base"
-        model = AutoModelForAudioClassification.from_pretrained(
-            model_checkpoint, num_labels=num_classes
-        )
-
-        # Load trained weights
-        print("🔄 Loading trained weights...")
-        model.load_state_dict(checkpoint)
-        model.to(device)
-        model.eval()
-
-        print("✅ Model loaded successfully!")
-
-        # Test with dummy audio
-        print("🧪 Testing inference with dummy audio...")
-
-        # Create dummy audio (1 second of random noise at 16kHz)
-        dummy_audio = np.random.randn(16000).astype(np.float32)
-
-        # Load feature extractor
-        feature_extractor = AutoFeatureExtractor.from_pretrained(model_checkpoint)
-
-        # Preprocess audio
-        inputs = feature_extractor(
-            dummy_audio,
-            sampling_rate=16000,
-            max_length=80000,  # 5 seconds * 16000 Hz
-            truncation=True,
-            padding="max_length",
-            return_tensors="pt",
-        )
-
-        # Move to device
-        input_values = inputs.input_values.to(device)
-
-        # Run inference
-        with torch.no_grad():
-            outputs = model(input_values)
-            probabilities = torch.softmax(outputs.logits, dim=1)
-            confidence, predicted = torch.max(probabilities, 1)
-
-            print(f"🔍 Model output shape: {outputs.logits.shape}")
-            print(f"🎯 Predicted class: {predicted.item()}")
-            print(f"📊 Confidence: {confidence.item():.3f}")
-            print(f"📈 All probabilities: {probabilities.squeeze().cpu().numpy()}")
-
-        # Sentiment mapping
-        sentiment_map = {0: "Negative", 1: "Neutral", 2: "Positive"}
-        predicted_sentiment = sentiment_map.get(
-            predicted.item(), f"Class_{predicted.item()}"
-        )
-        print(f"😊 Predicted sentiment: {predicted_sentiment}")
-
-        print("✅ Audio model test completed successfully!")
-        return True
-
-    except Exception as e:
-        print(f"❌ Error testing audio model: {str(e)}")
-        import traceback
-
-        traceback.print_exc()
-        return False
-
-
-def check_audio_model_file():
-    """Check the audio model file details"""
-
-    print("\n🔍 Audio Model File Analysis")
-    print("=" * 30)
-
-    model_path = "models/wav2vec2_model.pth"
-    if not os.path.exists(model_path):
-        print(f"❌ Model file not found: {model_path}")
-        return
-
-    # File size
-    file_size = os.path.getsize(model_path) / (1024 * 1024)  # MB
-    print(f"📁 File size: {file_size:.1f} MB")
-
-    try:
-        # Load checkpoint
-        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        checkpoint = torch.load(model_path, map_location=device)
-
-        print(f"🔑 Checkpoint keys ({len(checkpoint)} total):")
-        for key, value in checkpoint.items():
-            if isinstance(value, torch.Tensor):
-                print(f"  - {key}: {value.shape} ({value.dtype})")
-            else:
-                print(f"  - {key}: {type(value)}")
-
-        # Check classifier
-        if "classifier.weight" in checkpoint:
-            num_classes = checkpoint["classifier.weight"].shape[0]
-            print(f"\n🎯 Classifier output classes: {num_classes}")
-            print(
-                f"📊 Classifier weight shape: {checkpoint['classifier.weight'].shape}"
-            )
-            if "classifier.bias" in checkpoint:
-                print(
-                    f"📊 Classifier bias shape: {checkpoint['classifier.bias'].shape}"
-                )
-
-        # Check wav2vec2 base model
-        if "wav2vec2.feature_extractor.conv_layers.0.conv.weight" in checkpoint:
-            print(f"🔊 Wav2Vec2 base model: Present")
-
-    except Exception as e:
-        print(f"❌ Error analyzing checkpoint: {str(e)}")
-
-
-if __name__ == "__main__":
-    print("🚀 Starting Wav2Vec2 Audio Model Tests")
-    print("=" * 60)
-
-    # Check model file
-    check_audio_model_file()
-
-    print("\n" + "=" * 60)
-
-    # Test model loading and inference
-    success = test_audio_model()
-
-    if success:
-        print("\n🎉 All audio model tests passed!")
-    else:
-        print("\n💥 Audio model tests failed!")

test_download.py

@@ -1,49 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test the updated Google Drive download function
-"""
-
-from simple_model_manager import SimpleModelManager
-
-
-def test_download():
-    """Test the download function"""
-    print("Testing Google Drive Download Function")
-    print("=" * 50)
-
-    # Initialize manager
-    manager = SimpleModelManager()
-
-    # Check model status
-    status = manager.get_model_status()
-    print("Model Status:")
-    for model_type, info in status.items():
-        print(f"  {model_type}: {'✅' if info['configured'] else '❌'} {info['url']}")
-        if info["cached"]:
-            print(f"    📁 Cached: {info['filename']}")
-
-    # Test vision model download
-    if status["vision"]["configured"]:
-        print(f"\nTesting vision model download...")
-        try:
-            vision_model, device, num_classes = manager.load_vision_model()
-            print(f"✅ Vision model loaded: {num_classes} classes")
-        except Exception as e:
-            print(f"❌ Vision model failed: {e}")
-    else:
-        print("❌ Vision model not configured")
-
-    # Test audio model download
-    if status["audio"]["configured"]:
-        print(f"\nTesting audio model download...")
-        try:
-            audio_model, device = manager.load_audio_model()
-            print(f"✅ Audio model loaded")
-        except Exception as e:
-            print(f"❌ Audio model failed: {e}")
-    else:
-        print("❌ Audio model not configured")
-
-
-if __name__ == "__main__":
-    test_download()

test_drive_links.py

@@ -1,96 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test Google Drive links directly to see what's being returned
-"""
-
-import requests
-import os
-from pathlib import Path
-
-
-def test_drive_link(url, filename):
-    """Test a Google Drive link directly"""
-    print(f"\nTesting: {filename}")
-    print(f"URL: {url}")
-
-    try:
-        # Convert Google Drive share link to direct download link
-        if "drive.google.com" in url:
-            if "/file/d/" in url:
-                file_id = url.split("/file/d/")[1].split("/")[0]
-            elif "id=" in url:
-                file_id = url.split("id=")[1].split("&")[0]
-            else:
-                print("❌ Could not extract file ID")
-                return
-
-            direct_url = f"https://drive.google.com/uc?export=download&id={file_id}"
-            print(f"Direct URL: {direct_url}")
-        else:
-            direct_url = url
-
-        # Test the download
-        print("Downloading...")
-        response = requests.get(direct_url, stream=True)
-
-        print(f"Status Code: {response.status_code}")
-        print(f"Content-Type: {response.headers.get('content-type', 'Unknown')}")
-        print(f"Content-Length: {response.headers.get('content-length', 'Unknown')}")
-
-        if response.status_code == 200:
-            # Read first 200 bytes to check content
-            content = response.raw.read(200)
-            print(f"First 200 bytes: {content[:100]}...")
-
-            # Check if it's HTML
-            if content.startswith(b"<!DOCTYPE") or content.startswith(b"<html"):
-                print("❌ ERROR: This is an HTML page, not a model file!")
-                print("   Your Google Drive link is not working properly")
-                print("   Check file permissions and sharing settings")
-            else:
-                print("✅ Looks like a valid file (not HTML)")
-
-                # Save a small sample to check
-                sample_path = f"sample_{filename}"
-                with open(sample_path, "wb") as f:
-                    f.write(content)
-                print(f"Saved sample to: {sample_path}")
-
-        else:
-            print(f"❌ Download failed with status: {response.status_code}")
-
-    except Exception as e:
-        print(f"❌ Error: {e}")
-
-
-def main():
-    print("Google Drive Link Tester")
-    print("=" * 50)
-
-    # Check environment variables
-    vision_url = os.getenv("VISION_MODEL_DRIVE_LINK")
-    audio_url = os.getenv("AUDIO_MODEL_DRIVE_LINK")
-
-    if not vision_url and not audio_url:
-        print("❌ No environment variables found!")
-        print("Please run setup_env.py first or set:")
-        print("  VISION_MODEL_DRIVE_LINK")
-        print("  AUDIO_MODEL_DRIVE_LINK")
-        return
-
-    if vision_url:
-        test_drive_link(vision_url, "resnet50_model.pth")
-
-    if audio_url:
-        test_drive_link(audio_url, "wav2vec2_model.pth")
-
-    print("\n" + "=" * 50)
-    print("If you see HTML content, your Google Drive links need fixing!")
-    print("Make sure:")
-    print("  1. Files are set to 'Anyone with the link can view'")
-    print("  2. You're using direct file links, not folder links")
-    print("  3. Files are not too large for direct download")
-
-
-if __name__ == "__main__":
-    main()

test_vision_model.py

@@ -1,136 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test script for the vision sentiment analysis model.
-This script verifies that the ResNet-50 model can be loaded and run inference.
-"""
-
-import os
-import sys
-import torch
-import torch.nn as nn
-from torchvision import transforms, models
-from PIL import Image
-import numpy as np
-
-
-def get_sentiment_mapping(num_classes):
-    """Get the sentiment mapping based on number of classes"""
-    if num_classes == 3:
-        return {0: "Negative", 1: "Neutral", 2: "Positive"}
-    elif num_classes == 4:
-        # Common 4-class emotion mapping
-        return {0: "Angry", 1: "Sad", 2: "Happy", 3: "Neutral"}
-    elif num_classes == 7:
-        # FER2013 7-class emotion mapping
-        return {0: "Angry", 1: "Disgust", 2: "Fear", 3: "Happy", 4: "Sad", 5: "Surprise", 6: "Neutral"}
-    else:
-        # Generic mapping for unknown number of classes
-        return {i: f"Class_{i}" for i in range(num_classes)}
-
-
-def test_vision_model():
-    """Test the vision sentiment analysis model"""
-
-    print("🧠 Testing Vision Sentiment Analysis Model")
-    print("=" * 50)
-
-    # Check if model file exists
-    model_path = "models/resnet50_model.pth"
-    if not os.path.exists(model_path):
-        print(f"❌ Model file not found: {model_path}")
-        print("Please ensure the model file exists in the models/ directory")
-        return False
-
-    print(f"✅ Model file found: {model_path}")
-
-    try:
-        # Load the model weights first to check the architecture
-        print("📥 Loading model checkpoint...")
-        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        checkpoint = torch.load(model_path, map_location=device)
-        
-        # Check the number of classes from the checkpoint
-        if 'fc.weight' in checkpoint:
-            num_classes = checkpoint['fc.weight'].shape[0]
-            print(f"📊 Model checkpoint has {num_classes} output classes")
-        else:
-            # Fallback: try to infer from the last layer
-            num_classes = 3  # Default assumption
-            print("⚠️ Could not determine number of classes from checkpoint, assuming 3")
-        
-        # Initialize ResNet-50 model with the correct number of classes
-        print("🔧 Initializing ResNet-50 model...")
-        model = models.resnet50(weights=None)  # Don't load ImageNet weights
-        num_ftrs = model.fc.in_features
-        model.fc = nn.Linear(num_ftrs, num_classes)  # Use actual number of classes
-        
-        print(f"📥 Loading trained weights for {num_classes} classes...")
-        model.load_state_dict(checkpoint)
-        model.to(device)
-        model.eval()
-        
-        print(f"✅ Model loaded successfully with {num_classes} classes!")
-        print(f"🖥️  Using device: {device}")
-
-        # Test with a dummy image
-        print("🧪 Testing inference with dummy image...")
-
-        # Create a dummy image (224x224 RGB)
-        dummy_image = Image.fromarray(
-            np.random.randint(0, 255, (224, 224, 3), dtype=np.uint8)
-        )
-
-        # Apply transforms
-        transform = transforms.Compose(
-            [
-                transforms.Resize(224),
-                transforms.CenterCrop(224),
-                transforms.ToTensor(),
-                transforms.Normalize(
-                    mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]
-                ),
-            ]
-        )
-
-        image_tensor = transform(dummy_image).unsqueeze(0).to(device)
-
-        # Run inference
-        with torch.no_grad():
-            outputs = model(image_tensor)
-            print(f"🔍 Model output shape: {outputs.shape}")
-            
-            probabilities = torch.nn.functional.softmax(outputs, dim=1)
-            confidence, predicted = torch.max(probabilities, 1)
-
-            # Get sentiment mapping based on number of classes
-            sentiment_map = get_sentiment_mapping(num_classes)
-            sentiment = sentiment_map[predicted.item()]
-            confidence_score = confidence.item()
-
-        print(f"🎯 Test prediction: {sentiment} (confidence: {confidence_score:.3f})")
-        print(f"📋 Available classes: {list(sentiment_map.values())}")
-        print("✅ Inference test passed!")
-
-        return True
-
-    except Exception as e:
-        print(f"❌ Error testing model: {str(e)}")
-        import traceback
-        traceback.print_exc()
-        return False
-
-
-def main():
-    """Main function"""
-    success = test_vision_model()
-
-    if success:
-        print("\n🎉 All tests passed! The vision model is ready to use.")
-        print("You can now run the Streamlit app with: streamlit run app.py")
-    else:
-        print("\n💥 Tests failed. Please check the error messages above.")
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()