update app.py

.gitignore

@@ -0,0 +1 @@
+.venv/

app.py

@@ -1,3 +1,5 @@
+from huggingface_hub import login
+# import spaces
 import os
 import time
 import gradio as gr
@@ -8,8 +10,6 @@ import vision_agent as va
 from vision_agent.tools import register_tool
 from vision_agent.tools import load_image, owl_v2, overlay_bounding_boxes, save_image
 
-from huggingface_hub import login
-import spaces
 
 # Perform login using the token
 hf_token = os.getenv("HF_TOKEN")
@@ -18,7 +18,7 @@ login(token=hf_token, add_to_git_credential=True)
 import numpy as np
 from PIL import Image
 
-def detect_brain_tumor(image, seg_input, debug: bool = False):
+def detect_brain_tumor(image, seg_input, debug: bool = True):
     """
     Detects a brain tumor in the given image and returns the annotated image.
 
@@ -31,27 +31,33 @@ def detect_brain_tumor(image, seg_input, debug: bool = False):
         tuple: (numpy array of image, list of (label, (x1, y1, x2, y2)) tuples)
     """
     if debug:
-        print(f"Image received")
+        print(f"Image received, shape: {image.shape}")
 
     # Step 2: Detect brain tumor using owl_v2
     prompt = "detect brain tumor"
     detections = owl_v2(prompt, image)
     if debug:
-        print(f"Detections: {detections}")
+        print(f"Raw detections: {detections}")
 
     # Step 3: Overlay bounding boxes on the image
     image_with_bboxes = overlay_bounding_boxes(image, detections)
     if debug:
         print("Bounding boxes overlaid on the image")
 
-    # Prepare annotations for AnnotatedImage output
+        # Prepare annotations for AnnotatedImage output
     annotations = []
     for detection in detections:
         label = detection['label']
         score = detection['score']
         bbox = detection['bbox']
         x1, y1, x2, y2 = bbox
-        annotations.append((f"{label} {score:.2f}", (x1, y1, x2, y2)))
+        # Convert normalized coordinates to pixel coordinates
+        height, width = image.shape[:2]
+        x1, y1, x2, y2 = int(x1*width), int(y1*height), int(x2*width), int(y2*height)
+        annotations.append(((x1, y1, x2, y2), f"{label} {score:.2f}"))
+
+    if debug:
+        print(f"Annotations: {annotations}")
 
     # Convert image to numpy array if it's not already
     if isinstance(image_with_bboxes, Image.Image):