app.py

import gradio as gr
from datasets import load_dataset
from PIL import Image, ImageDraw
import numpy as np

# Load the dataset
dataset = load_dataset("dwb2023/brain-tumor-image-dataset-semantic-segmentation", split="test")

# Function to filter dataset based on category ID
def filter_dataset_by_category(category_id):
    filtered_indices = [i for i, record in enumerate(dataset) if record["category_id"] == category_id]
    return filtered_indices

# Function to draw annotations
def draw_annotations(index, category_id):
    filtered_indices = filter_dataset_by_category(category_id)
    
    if index >= len(filtered_indices):
        index = 0
    
    try:
        # Fetch the image and annotations from the dataset
        record = dataset[filtered_indices[index]]
        
        # Convert image to PIL Image if it's a numpy array
        if isinstance(record['image'], np.ndarray):
            img = Image.fromarray(record['image'])
        else:
            img = record['image']
        
        img = img.convert("RGB")  # Ensure the image is in RGB mode
        
        draw = ImageDraw.Draw(img)

        # Draw bounding box
        bbox = record["bbox"]
        draw.rectangle([bbox[0], bbox[1], bbox[0] + bbox[2], bbox[1] + bbox[3]], outline="red", width=2)

        # Draw segmentation mask
        segmentation = record["segmentation"]
        for seg in segmentation:
            draw.polygon(seg, outline="blue", width=2)

        # Prepare additional information
        category_id = record["category_id"]
        area = record["area"]
        file_name = record["file_name"]

        info = f"File Name: {file_name}\n"
        info += f"Image ID: {record['id']}\n"
        info += f"Category ID: {category_id}\n"
        info += f"Bounding Box: [{bbox[0]:.2f}, {bbox[1]:.2f}, {bbox[2]:.2f}, {bbox[3]:.2f}]\n"
        info += f"Segmentation: {segmentation}\n"
        info += f"Area: {area:.2f}"

        return img, info, len(filtered_indices) - 1
    except Exception as e:
        print(f"Error processing image at index {index}: {e}")
        return Image.new('RGB', (300, 300), color='gray'), f"Error loading image information: {str(e)}", len(filtered_indices) - 1

# Create Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Brain Tumor Image Dataset Viewer")
    gr.Markdown("## Refer to the [dwb2023/brain-tumor-image-dataset-semantic-segmentation](https://huggingface.co/datasets/dwb2023/brain-tumor-image-dataset-semantic-segmentation/viewer/default/test) dataset for more information")
    
    with gr.Row():
        with gr.Column(scale=1):
            image_output = gr.Image(label="Annotated Image")
        with gr.Column(scale=1):
            category_id_dropdown = gr.Dropdown(choices=[1, 2], value=1, label="Category ID")
            image_index = gr.Slider(minimum=0, maximum=0, step=1, value=0, label="Image ID Slider")
            info_output = gr.Textbox(label="Image Information", lines=10)
    
    def update_slider(category_id):
        img, info, max_index = draw_annotations(0, category_id)
        return gr.Slider.update(maximum=max_index), img, info

    # Update image and info when slider or category changes
    category_id_dropdown.change(update_slider, inputs=category_id_dropdown, outputs=[image_index, image_output, info_output])
    image_index.change(draw_annotations, inputs=[image_index, category_id_dropdown], outputs=[image_output, info_output, image_index])

    # Display initial image and info
    demo.load(draw_annotations, inputs=[image_index, category_id_dropdown], outputs=[image_output, info_output, image_index])

demo.launch(debug=True)