Update app.py

app.py

@@ -5,7 +5,7 @@ from PIL import Image, ImageDraw, ImageFont
 import matplotlib.pyplot as plt
 import io
 
-# --- Model Management (No changes in this section) ---
+# --- Model Management ---
 MODEL_REGISTRY = {
     "Single-Class Detection": {
         "yolov10": "yolov10x_bb_detect_model",
@@ -41,13 +41,11 @@ def get_model(task, architecture):
     except Exception as e:
         raise gr.Error(f"Failed to load model. Please check the model name and your connection. Error: {e}")
 
-# --- Visualization and Drawing Functions (No changes in this section) ---
-try:
-    font = ImageFont.truetype("arial.ttf", 60)
-except IOError:
-    font = ImageFont.load_default()
+# --- Visualization and Drawing Functions ---
+# Note: The global font object has been removed from here.
 
-def draw_yolo_predictions(image, results, color="red"):
+def draw_yolo_predictions(image, results, font, color="red"):
+    """Draws YOLO predictions on an image with a dynamically sized font."""
     img_copy = image.copy()
     draw = ImageDraw.Draw(img_copy)
     if not results or not results[0].boxes:
@@ -68,7 +66,8 @@ def draw_yolo_predictions(image, results, color="red"):
         draw.text((coords[0], text_bg_y1), label_text, fill="white", font=font)
     return img_copy
 
-def draw_dino_predictions(image, results, color="green"):
+def draw_dino_predictions(image, results, font, color="green"):
+    """Draws Grounding DINO predictions on an image with a dynamically sized font."""
     img_copy = image.copy()
     draw = ImageDraw.Draw(img_copy)
     if not results: return img_copy
@@ -84,6 +83,7 @@ def draw_dino_predictions(image, results, color="green"):
     return img_copy
 
 def visualize_embedding(embedding):
+    """Visualizes a feature embedding as an image."""
     if embedding is None: return None
     if not hasattr(embedding, 'cpu'): return None
     if len(embedding.shape) == 1:
@@ -102,19 +102,27 @@ def visualize_embedding(embedding):
 
 # --- Main Processing Function ---
 def comprehensive_analysis(image, task, architecture, text_prompt, box_threshold, text_threshold):
+    """Performs the main analysis, including dynamic font calculation."""
     if image is None:
         raise gr.Error("Please upload an image first!")
-    
+
+    # Calculate a dynamic font size based on image width.
+    # The font size will be 4% of the image width, with a minimum size of 15.
+    dynamic_font_size = max(15, int(image.width * 0.04))
+    try:
+        font = ImageFont.truetype("arial.ttf", dynamic_font_size)
+    except IOError:
+        font = ImageFont.load_default(size=dynamic_font_size)
+
     if task == "Zero-Shot Detection":
         architecture = "grounding_dino"
     
     model = get_model(task, architecture)
-    
     outputs = {"annotated_image": None, "model_info": "", "classes_info": "", "embedding_plot": None}
 
     if task in ["Single-Class Detection", "Multi-Class Detection"]:
-        results = model.predict(image) # Corrected line
-        outputs["annotated_image"] = draw_yolo_predictions(image, results)
+        results = model.predict(image)
+        outputs["annotated_image"] = draw_yolo_predictions(image, results, font=font)
         features = model.extract_features(image)
         outputs["model_info"] = f"Architecture: {architecture.upper()}\nTask: {task}\nDevice: {model.device}"
         outputs["classes_info"] = f"Classes: {model.get_classes()}"
@@ -129,7 +137,7 @@ def comprehensive_analysis(image, task, architecture, text_prompt, box_threshold
             text_threshold=text_threshold
         )
         
-        outputs["annotated_image"] = draw_dino_predictions(image, results)
+        outputs["annotated_image"] = draw_dino_predictions(image, results, font=font)
         features = model.extract_features(image, text_prompt=text_prompt)
         outputs["model_info"] = f"Architecture: {architecture.upper()}\nTask: {task}\nDevice: {model.device}\nHF Model ID: {model.model.config._name_or_path}"
         outputs["classes_info"] = f"Prompt: '{text_prompt}'"
@@ -141,8 +149,9 @@ def comprehensive_analysis(image, task, architecture, text_prompt, box_threshold
     
     return outputs["annotated_image"], outputs["model_info"], outputs["classes_info"], outputs["embedding_plot"]
 
-# --- Gradio UI with Blocks and Dynamic UI Updates ---
+# --- Gradio UI ---
 def update_ui_for_task(task):
+    """Updates the UI components based on the selected task."""
     if task in ["Single-Class Detection", "Multi-Class Detection"]:
         arch_choices = list(MODEL_REGISTRY[task].keys())
         return {
@@ -160,16 +169,15 @@ def update_ui_for_task(task):
             text_threshold_slider: gr.update(visible=True)
         }
 
-
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# IBBI - Intelligent Bark Beetle Identifier ")
+    gr.Markdown("# IBBI - Intelligent Bark Beetle Identifier")
     gr.Markdown("An all-in-one interface to analyze images using the `ibbi` library. Upload an image, select a task and model, and view the complete analysis.")
 
     with gr.Row():
         with gr.Column(scale=1):
             gr.Markdown("### 1. Inputs")
             image_input = gr.Image(type="pil", label="Upload Image")
-            # ... all your other input components like task_selector, dropdowns, etc.
+            
             task_selector = gr.Radio(
                 choices=["Single-Class Detection", "Multi-Class Detection", "Zero-Shot Detection"],
                 value="Single-Class Detection",
@@ -207,7 +215,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                 classes_output = gr.Textbox(label="Classes / Prompt")
                 embedding_output = gr.Image(label="Feature Embedding Visualization")
     
-    # --- Event Handlers (No changes here) ---
+    # --- Event Handlers ---
     task_selector.change(
         fn=update_ui_for_task,
         inputs=task_selector,
@@ -220,7 +228,6 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
         outputs=[output_image, model_details_output, classes_output, embedding_output]
     )
     
-    # --- NEW: Use gr.Examples with just the image input ---
     gr.Markdown("---")
     gr.Markdown("### 3. Or Start with an Example Image")
     
@@ -234,8 +241,8 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
 
     gr.Examples(
         examples=example_list,
-        inputs=image_input,  # This is the key change!
-        label="Click an image to load it"
+        inputs=image_input,
+        label="Select an image to load it"
     )
 
 if __name__ == "__main__":