Update app.py

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 import torch
 import kornia as K
 from kornia.geometry.transform import resize
-import cv2
 import numpy as np
 from torchvision import transforms
 from torchvision.utils import make_grid
@@ -14,6 +13,8 @@ def read_image(img):
     image_to_tensor = transforms.ToTensor()
     if isinstance(img, np.ndarray):
         img = Image.fromarray(img)
+    elif isinstance(img, str):
+        img = Image.open(img).convert('RGB')
     img_tensor = image_to_tensor(img)
     resized_image = resize(img_tensor.unsqueeze(0), (50, 50)).squeeze(0)
     return resized_image
@@ -31,14 +32,14 @@ def predict(images, eps):
 title = 'ZCA Whitening with Kornia!'
 description = '''[ZCA Whitening](https://paperswithcode.com/method/zca-whitening) is an image preprocessing method that leads to a transformation of data such that the covariance matrix is the identity matrix, leading to decorrelated features:
 *Note that you can upload only image files, e.g. jpg, png etc and there should be at least 2 images!* 
-Learn more about [ZCA Whitening and Kornia](https://kornia.readthedocs.io/en/v0.6.4/_modules/kornia/enhance/zca.html)'''
+Learn more about [ZCA Whitening and Kornia](https://kornia.readthedocs.io/en/latest/enhance.zca.html)'''
 
 with gr.Blocks(title=title) as demo:
     gr.Markdown(f"# {title}")
     gr.Markdown(description)
     
     with gr.Row():
-        input_images = gr.File(file_count="multiple", label="Input Images")
+        input_images = gr.Files(label="Input Images")
         eps_slider = gr.Slider(minimum=0.01, maximum=1, value=0.01, label="Epsilon")
     
     output_image = gr.Image(label="ZCA Whitened Images")