Delete app.py

app.py

@@ -1,130 +0,0 @@
-import gradio as gr
-import os
-from io import BytesIO
-from PIL import Image, ImageDraw, ImageFont
-from PIL import ImageColor
-import json
-from google import genai
-from google.genai import types
-
-# Initialize Google Gemini client
-client = genai.Client(api_key=os.environ['GOOGLE_API_KEY'])
-model_name = "gemini-2.0-flash-exp"
-
-
-#Skin issue detection system instructions
-bounding_box_system_instructions = """
-Return bounding boxes as a JSON array with labels specific to medical ultrasound imaging. Never return masks or code fencing. Limit to 25 objects per frame."""
-
-# Additional colors f
-
-# Additional colors for bounding box visualization
-additional_colors = [colorname for (colorname, colorcode) in ImageColor.colormap.items()]
-
-def parse_json(json_output):
-    """
-    Parse JSON output from the Gemini model.
-    """
-    try:
-        json_start = json_output.find("[")
-        json_end = json_output.rfind("]")
-        if json_start == -1 or json_end == -1:
-            raise ValueError("Bounding box JSON not found in response.")
-        return json_output[json_start:json_end + 1]
-    except Exception as e:
-        print(f"Error parsing JSON: {e}")
-        return None
-
-def plot_bounding_boxes(im, bounding_boxes):
-    """
-    Plots bounding boxes on an image with labels.
-    """
-    im = im.copy()
-    draw = ImageDraw.Draw(im)
-    colors = ['red', 'green', 'blue', 'yellow', 'pink'] + additional_colors
-
-    try:
-        bounding_boxes_json = json.loads(bounding_boxes)
-        for i, bounding_box in enumerate(bounding_boxes_json):
-            color = colors[i % len(colors)]
-            x_min, y_min = bounding_box["x_min"], bounding_box["y_min"]
-            x_max, y_max = bounding_box["x_max"], bounding_box["y_max"]
-            draw.rectangle(((x_min, y_min), (x_max, y_max)), outline=color, width=4)
-            if "label" in bounding_box:
-                label = f"{bounding_box['label']} ({bounding_box['metadata']['severity']})"
-                draw.text((x_min + 5, y_min - 10), label, fill=color)
-    except Exception as e:
-        print(f"Error drawing bounding boxes: {e}")
-
-    return im
-
-def predict_bounding_boxes(image, prompt):
-    """
-    Process the image and prompt through Gemini and draw bounding boxes.
-    """
-    try:
-        image = image.resize((1024, int(1024 * image.height / image.width)))
-        buffered = BytesIO()
-        image.save(buffered, format="JPEG")
-        image_bytes = buffered.getvalue()
-
-        response = client.models.generate_content(
-            model=model_name,
-            contents=[prompt, image],
-            config=types.GenerateContentConfig(
-                system_instruction=bounding_box_system_instructions,
-                temperature=0.5
-            )
-        )
-
-        bounding_boxes = parse_json(response.text)
-        if not bounding_boxes:
-            raise ValueError("No bounding boxes returned.")
-        return plot_bounding_boxes(image, bounding_boxes)
-    except Exception as e:
-        print(f"Error: {e}")
-        return image
-
-def gradio_interface():
-    """
-    Gradio app interface for skin issue detection.
-    """
-    examples = [
-        ["skin_example1.jpg", "Detect and label skin abnormalities."],
-        ["skin_example2.jpg", "Find acne lesions and classify severity."],
-        ["skin_example3.jpg", "Identify suspicious moles and discolorations."],
-    ]
-
-    with gr.Blocks() as demo:
-        gr.Markdown("# Skin Issue Detection with Gemini")
-
-        with gr.Row():
-            with gr.Column():
-                input_image = gr.Image(type="pil", label="Input Image")
-                input_prompt = gr.Textbox(
-                    lines=2,
-                    label="Input Prompt",
-                    placeholder="Describe what to detect (e.g., 'Identify acne lesions').",
-                    value="Identify and label skin abnormalities."
-                )
-                submit_btn = gr.Button("Generate")
-
-            with gr.Column():
-                output_image = gr.Image(type="pil", label="Output Image")
-
-        gr.Examples(
-            examples=examples,
-            inputs=[input_image, input_prompt]
-        )
-
-        submit_btn.click(
-            predict_bounding_boxes,
-            inputs=[input_image, input_prompt],
-            outputs=[output_image]
-        )
-
-    return demo
-
-if __name__ == "__main__":
-    app = gradio_interface()
-    app.launch()