Use kornia io module to load the image

app.py

@@ -1,61 +1,55 @@
 import gradio as gr
 
-import cv2
-import numpy as np
-
-import torch
 import kornia as K
 from kornia.core import Tensor
 
 def edge_detection(filepath, detector): 
 
-    img_bgr: np.ndarray = cv2.imread(filepath, cv2.IMREAD_COLOR)
-
-    x_bgr: torch.Tensor = K.utils.image_to_tensor(img_bgr)
-    x_bgr = x_bgr[None,...].float() / 255.
+    img: Tensor = K.io.load_image(filepath, K.io.ImageLoadType.RGB32)    
+    img = img[None]
 
-    x_rgb: torch.Tensor = K.color.bgr_to_rgb(x_bgr)
+    x_rgb: Tensor = K.color.bgr_to_rgb(img)
     x_gray = K.color.rgb_to_grayscale(x_rgb)
     
 
     if detector == '1st order derivates in x':
-        grads: torch.Tensor = K.filters.spatial_gradient(x_gray, order=1) 
+        grads: Tensor = K.filters.spatial_gradient(x_gray, order=1) 
         grads_x = grads[:, :, 0]
         grads_y = grads[:, :, 1]
         
         output = K.utils.tensor_to_image(1. - grads_x.clamp(0., 1.))
     
     elif detector == '1st order derivates in y':
-        grads: torch.Tensor = K.filters.spatial_gradient(x_gray, order=1)
+        grads: Tensor = K.filters.spatial_gradient(x_gray, order=1)
         grads_x = grads[:, :, 0]
         grads_y = grads[:, :, 1]
         
         output = K.utils.tensor_to_image(1. - grads_y.clamp(0., 1.))
         
     elif detector == '2nd order derivatives in x':
-        grads: torch.Tensor = K.filters.spatial_gradient(x_gray, order=2) 
+        grads: Tensor = K.filters.spatial_gradient(x_gray, order=2) 
         grads_x = grads[:, :, 0]
         grads_y = grads[:, :, 1]
         
         output = K.utils.tensor_to_image(1. - grads_x.clamp(0., 1.))
         
     elif detector == '2nd order derivatives in y':
-        grads: torch.Tensor = K.filters.spatial_gradient(x_gray, order=2)
+        grads: Tensor = K.filters.spatial_gradient(x_gray, order=2)
         grads_x = grads[:, :, 0]
         grads_y = grads[:, :, 1]
         
         output = K.utils.tensor_to_image(1. - grads_y.clamp(0., 1.))
         
     elif detector == 'Sobel':
-        x_sobel: torch.Tensor = K.filters.sobel(x_gray)
+        x_sobel: Tensor = K.filters.sobel(x_gray)
         output = K.utils.tensor_to_image(1. - x_sobel)
 
     elif detector == 'Laplacian':
-        x_laplacian: torch.Tensor = K.filters.laplacian(x_gray, kernel_size=5)
+        x_laplacian: Tensor = K.filters.laplacian(x_gray, kernel_size=5)
         output = K.utils.tensor_to_image(1. - x_laplacian.clamp(0., 1.))
 
     else:
-        x_canny: torch.Tensor = K.filters.canny(x_gray)[0]
+        x_canny: Tensor = K.filters.canny(x_gray)[0]
         output = K.utils.tensor_to_image(1. - x_canny.clamp(0., 1.0))
 
     return output