multiple inputs

app.py

@@ -9,6 +9,9 @@ from utils import Image2Text
 @spaces.GPU(duration=15)
 def greet(input_img):
     global image_to_text
+    print('-----------')
+    print(input_img[0])
+    print('-----------')
     contents = image_to_text.get_text(input_img[0], num_beams=4)
     return '\n'.join(contents)
 

utils.py

@@ -1,3 +1,44 @@
+import os
+from typing import Union
+
+import PIL.Image
+import PIL.ImageOps
+import requests
+
+
+def load_image(image: Union[str, PIL.Image.Image]) -> PIL.Image.Image:
+    """
+    Loads `image` to a PIL Image.
+
+    Args:
+        image (`str` or `PIL.Image.Image`):
+            The image to convert to the PIL Image format.
+    Returns:
+        `PIL.Image.Image`:
+            A PIL Image.
+    """
+    if isinstance(image, str):
+        if image.startswith("http://") or image.startswith("https://"):
+            image = PIL.Image.open(requests.get(image, stream=True).raw)
+        elif os.path.isfile(image):
+            image = PIL.Image.open(image)
+        else:
+            raise ValueError(
+                f"Incorrect path or url, URLs must start with `http://` or `https://`, and {image} is not a valid path"
+            )
+    elif isinstance(image, PIL.Image.Image):
+        image = image
+    else:
+        raise ValueError(
+            "Incorrect format used for image. Should be an url linking to an image, a local path, or a PIL image."
+        )
+    image = PIL.ImageOps.exif_transpose(image)
+    image = image.convert("RGB")
+    return image
+
+
+
+
 import re
 import torch
 import numpy as np
@@ -52,7 +93,8 @@ class Image2Text:
         return model, processor
 
     def load_img(self, inputs, width=480, height=480):
-        image = Image.fromarray(inputs)
+        # image = Image.fromarray(inputs)
+        image = load_image(inputs)
         image = aspect_ratio_preserving_resize_and_crop(image, target_width=width, target_height=height).convert("RGB")
         img = self.processor(image , return_tensors="pt", size=(width, height)).pixel_values
         pixel_values = img.to(self.device)