Update app.py

app.py

@@ -349,7 +349,7 @@ def save_dxf_spline(inflated_contours, scaling_factor, height, finger_clearance=
 
 def add_rectangular_boundary(doc, polygons_inch, boundary_length, boundary_width, offset_unit, annotation_text="", image_height_in=None, image_width_in=None):
     msp = doc.modelspace()
-    # Convert from mm if necessary.
+    # Convert from mm if necessary
     if offset_unit.lower() == "mm":
         if boundary_length < 50:
             boundary_length = boundary_length * 25.4
@@ -361,7 +361,7 @@ def add_rectangular_boundary(doc, polygons_inch, boundary_length, boundary_width
         boundary_length_in = boundary_length
         boundary_width_in = boundary_width
 
-    # Compute bounding box of inner contours.
+    # Compute bounding box of inner contours
     min_x = float("inf")
     min_y = float("inf")
     max_x = -float("inf")
@@ -376,30 +376,30 @@ def add_rectangular_boundary(doc, polygons_inch, boundary_length, boundary_width
         print("No tool polygons found, skipping boundary.")
         return None
 
-    # Compute inner bounding box dimensions.
+    # Compute inner bounding box dimensions
     inner_width = max_x - min_x
     inner_length = max_y - min_y
 
-    # Set clearance margins.
+    # Set clearance margins
     clearance_side = 0.25  # left/right clearance
     clearance_tb = 0.25    # top/bottom clearance
     if annotation_text.strip():
         clearance_tb = 0.75
 
-    # Check if the boundary dimensions are at least larger than the inner box plus clearance.
+    # Check if boundary dimensions are at least larger than inner box plus clearance
     if boundary_width_in <= inner_width + 2 * clearance_side or boundary_length_in <= inner_length + 2 * clearance_tb:
         raise BoundaryOverlapError("Error: The specified boundary dimensions are too small and overlap with the inner contours. Please provide larger values.")
 
-    # Check if boundary exceeds image limits (for example, 1 inch less than the image dimensions).
+    # Check if boundary exceeds image limits (1 inch less than image dimensions)
     if image_height_in is not None and image_width_in is not None:
         if boundary_length_in > (image_height_in - 1) or boundary_width_in > (image_width_in - 1):
             raise BoundaryExceedsError("Error: The specified boundary dimensions exceed the allowed image dimensions. Please enter smaller values.")
 
-    # Calculate the center of the inner contours.
+    # Calculate center of inner contours
     center_x = (min_x + max_x) / 2
     center_y = (min_y + max_y) / 2
 
-    # Draw rectangle centered at (center_x, center_y).
+    # Draw rectangle centered at (center_x, center_y)
     left = center_x - boundary_width_in / 2
     right = center_x + boundary_width_in / 2
     bottom = center_y - boundary_length_in / 2
@@ -445,7 +445,7 @@ def predict(
     annotation_text: str
 ):
     overall_start = time.time()
-    # Convert image to NumPy array if needed.
+    # Convert image to NumPy array if needed
     if isinstance(image, str):
         if os.path.exists(image):
             image = np.array(Image.open(image).convert("RGB"))
@@ -455,7 +455,7 @@ def predict(
             except Exception:
                 raise ValueError("Invalid base64 image data")
 
-    # Apply brightness and sharpness enhancement.
+    # Apply brightness and sharpness enhancement
     if isinstance(image, np.ndarray):
         pil_image = Image.fromarray(image)
         enhanced_image = ImageEnhance.Sharpness(pil_image).enhance(0.5)
@@ -470,7 +470,7 @@ def predict(
         print("Drawer detection completed in {:.2f} seconds".format(time.time() - t))
     except DrawerNotDetectedError as e:
         return None, None, None, None, f"Error: {str(e)}"
-    # Ensure that shrunked_img is defined only after successful detection.
+    # Ensure that shrunked_img is defined only after successful detection
     t = time.time()
     shrunked_img = make_square(shrink_bbox(drawer_img, 0.90))
     del drawer_img
@@ -492,7 +492,7 @@ def predict(
     # ---------------------
     t = time.time()
     reference_obj_img = make_square(reference_obj_img)
-    reference_square_mask = remove_bg(reference_obj_img)
+    reference_square_mask = remove_bg_u2netp(reference_obj_img)
     print("Reference image processing completed in {:.2f} seconds".format(time.time() - t))
 
     t = time.time()