example.py

"""
Simple example script to test Moondream2 model.
Based on the README usage example.
"""

from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
import torch
import os

def main():
    print("Loading Moondream2 model...")
    print(f"CUDA available: {torch.cuda.is_available()}")
    
    # Load model from HuggingFace
    # Note: The model uses trust_remote_code=True to load custom model classes
    model_id = "vikhyatk/moondream2"
    print(f"Loading model from HuggingFace: {model_id}...")
    
    device = "cuda" if torch.cuda.is_available() else "cpu"
    print(f"Using device: {device}")
    
    model = AutoModelForCausalLM.from_pretrained(
        model_id,
        trust_remote_code=True,
        device_map=device if device == "cuda" else None
    )
    if device == "cpu":
        model = model.to(device)
    
    tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
    
    print("Model loaded successfully!")
    
    # Check if we have a test image
    # You can provide an image path as command line argument
    import sys
    if len(sys.argv) > 1:
        image_path = sys.argv[1]
        image = Image.open(image_path).convert("RGB")
        print(f"Loaded image from: {image_path}")
    else:
        print("\nNo image provided. Creating a simple test image...")
        # Create a simple test image
        from PIL import ImageDraw
        img = Image.new('RGB', (400, 300), color='white')
        draw = ImageDraw.Draw(img)
        draw.rectangle([50, 50, 350, 250], fill='lightblue', outline='black', width=3)
        draw.text((150, 140), "Test Image", fill='black')
        image = img
        print("Created test image with a blue rectangle and text.")
    
    print("\n" + "="*50)
    print("Testing Captioning (Short)")
    print("="*50)
    try:
        result = model.caption(image, length="short")
        print(f"Short caption: {result['caption']}")
    except Exception as e:
        print(f"Error during captioning: {e}")
    
    print("\n" + "="*50)
    print("Testing Visual Query")
    print("="*50)
    try:
        question = "What is in this image?"
        result = model.query(image, question)
        print(f"Question: {question}")
        print(f"Answer: {result['answer']}")
    except Exception as e:
        print(f"Error during query: {e}")
    
    print("\n" + "="*50)
    print("Testing complete!")
    print("="*50)

if __name__ == "__main__":
    main()