app.py

import os
import sys
import torch
from PIL import Image as PILImage
from PIL import ImageDraw, ImageFont
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, AutoProcessor
from loguru import logger
import gradio as gr
import spaces

# Note: The perceptron package needs to be installed or included in the Space
try:
    from perceptron.tensorstream import VisionType
    from perceptron.tensorstream.ops import tensor_stream_token_view, modality_mask
    from perceptron.pointing.parser import extract_points
except ImportError:
    logger.error("perceptron package not found. Please ensure it's installed in your Hugging Face Space.")
    raise

# Load model at startup
hf_path = "PerceptronAI/Isaac-0.1"
logger.info(f"Loading processor and config from HF checkpoint: {hf_path}")
config = AutoConfig.from_pretrained(hf_path, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(hf_path, trust_remote_code=True, use_fast=False)
processor = AutoProcessor.from_pretrained(hf_path, trust_remote_code=True)
processor.tokenizer = tokenizer  # Ensure tokenizer is set

logger.info(f"Loading AutoModelForCausalLM from HF checkpoint: {hf_path}")
model = AutoModelForCausalLM.from_pretrained(hf_path, trust_remote_code=True)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
model = model.to(device=device, dtype=dtype)
model.eval()

logger.info(f"Model loaded on {device} with dtype {dtype}")

def document_to_messages(document, vision_token="<image>"):
    messages = []
    images = []
    for item in document:
        itype = item.get("type")
        if itype == "text":
            content = item.get("content")
            if content:
                messages.append({"role": item.get("role", "user"), "content": content})
        elif itype == "image":
            if "content" in item and item["content"] is not None:
                img = PILImage.open(item["content"]).convert("RGB")
                images.append(img)
                messages.append({"role": item.get("role", "user"), "content": vision_token})
    return messages, images

def decode_tensor_stream(tensor_stream, tokenizer):
    token_view = tensor_stream_token_view(tensor_stream)
    mod = modality_mask(tensor_stream)
    text_tokens = token_view[(mod != VisionType.image.value)]
    decoded = tokenizer.decode(text_tokens[0] if len(text_tokens.shape) > 1 else text_tokens)
    return decoded

def visualize_predictions(generated_text, image, output_path="prediction.jpeg"):
    boxes = extract_points(generated_text, expected="box")
    if not boxes:
        logger.info("No bounding boxes found in the generated text")
        image.save(output_path)
        return output_path

    img_width, img_height = image.size
    img_with_boxes = image.copy()
    draw = ImageDraw.Draw(img_with_boxes)

    try:
        font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", 16)
    except:
        font = ImageFont.load_default()

    colors = ["red", "green", "blue", "yellow", "magenta", "cyan", "orange", "purple"]

    for idx, box in enumerate(boxes):
        color = colors[idx % len(colors)]
        norm_x1, norm_y1 = box.top_left.x, box.top_left.y
        norm_x2, norm_y2 = box.bottom_right.x, box.bottom_right.y
        x1 = int((norm_x1 / 1000.0) * img_width)
        y1 = int((norm_y1 / 1000.0) * img_height)
        x2 = int((norm_x2 / 1000.0) * img_width)
        y2 = int((norm_y2 / 1000.0) * img_height)

        x1 = max(0, min(x1, img_width - 1))
        y1 = max(0, min(y1, img_height - 1))
        x2 = max(0, min(x2, img_width - 1))
        y2 = max(0, min(y2, img_height - 1))

        draw.rectangle([x1, y1, x2, y2], outline=color, width=3)

        if box.mention:
            text_y = max(y1 - 20, 5)
            text_bbox = draw.textbbox((x1, text_y), box.mention, font=font)
            draw.rectangle(text_bbox, fill=color)
            draw.text((x1, text_y), box.mention, fill="white", font=font)

    img_with_boxes.save(output_path, "JPEG")
    return output_path

@spaces.GPU(duration=120)
def generate_response(image, prompt):
    document = [
        {"type": "text", "content": "<hint>BOX</hint>", "role": "user"},
        {"type": "image", "content": image, "role": "user"},
        {"type": "text", "content": prompt, "role": "user"},
    ]

    messages, images = document_to_messages(document, vision_token=config.vision_token)
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(text=text, images=images, return_tensors="pt")
    tensor_stream = inputs["tensor_stream"].to(device)
    input_ids = inputs["input_ids"].to(device)

    decoded_content = decode_tensor_stream(tensor_stream, processor.tokenizer)

    with torch.no_grad():
        generated_ids = model.generate(
            tensor_stream=tensor_stream,
            max_new_tokens=256,
            do_sample=False,
            pad_token_id=processor.tokenizer.eos_token_id,
            eos_token_id=processor.tokenizer.eos_token_id,
        )

        generated_text = processor.tokenizer.decode(generated_ids[0], skip_special_tokens=False)

        if images:
            vis_path = visualize_predictions(generated_text, images[0])
            return generated_text, vis_path
        else:
            return generated_text, None

# Example images and prompts
examples = [
    ["example.webp", "Determine whether it is safe to cross the street. Look for signage and moving traffic."],
]

with gr.Blocks(title="Perceptron Isaac Vision Model", theme=gr.themes.Soft()) as demo:
    gr.Markdown("# 🔍 Perceptron Isaac Vision Model")
    gr.Markdown("Built with [anycoder](https://huggingface.co/spaces/akhaliq/anycoder)")
    gr.Markdown("""
    This demo showcases the Perceptron Isaac-0.1 model for multimodal understanding with bounding box visualization.
    Upload an image and provide a prompt to analyze the image and see detected objects with bounding boxes.
    """)

    with gr.Row():
        with gr.Column(scale=1):
            image_input = gr.Image(
                type="filepath", 
                label="Upload Image", 
                sources=["upload", "webcam", "clipboard"],
                height=400
            )
            prompt_input = gr.Textbox(
                label="Prompt",
                value="Determine whether it is safe to cross the street. Look for signage and moving traffic.",
                lines=3,
                placeholder="Enter your prompt here..."
            )
            generate_btn = gr.Button("🚀 Generate Response", variant="primary", size="lg")
            
        with gr.Column(scale=1):
            visualized_image = gr.Image(
                label="Visualized Predictions (with Bounding Boxes)",
                height=400
            )
            generated_text = gr.Textbox(
                label="Generated Text", 
                lines=10,
                max_lines=20
            )

    gr.Examples(
        examples=examples,
        inputs=[image_input, prompt_input],
        outputs=[generated_text, visualized_image],
        fn=generate_response,
        cache_examples=False
    )

    generate_btn.click(
        generate_response, 
        inputs=[image_input, prompt_input], 
        outputs=[generated_text, visualized_image]
    )

if __name__ == "__main__":
    demo.launch()