Update app.py

app.py

@@ -97,7 +97,46 @@ num_to_char = layers.StringLookup(
     vocabulary=char_to_num.get_vocabulary(), mask_token=None, invert=True
 )
 
+def distortion_free_resize(image, img_size):
+  w, h = img_size
+  image = tf.image.resize(image, size=(h, w), preserve_aspect_ratio=True)
+
+  # Check tha amount of padding needed to be done.
+  pad_height = h - tf.shape(image)[0]
+  pad_width = w - tf.shape(image)[1]
+
+  # only necessary if you want to do same amount of padding on both sides.
+  if pad_height % 2 != 0:
+    height = pad_height // 2
+    pad_height_top = height +1
+    pad_height_bottom = height
+  else:
+    pad_height_top = pad_height_bottom = pad_height // 2
+
+  if pad_width % 2 != 0:
+    width = pad_width // 2
+    pad_width_left = width + 1
+    pad_width_right = width
+  else:
+    pad_width_left = pad_width_right = pad_width // 2
+
+  image = tf.pad(
+      image, paddings=[
+          [pad_height_top, pad_height_bottom],
+          [pad_width_left, pad_width_right],
+          [0, 0],
+      ],
+  image = tf.transpose(image, perm=[1,0,2])
+  image = tf.image.flip_left_right(image)
+  return image
+
 def decode_batch_predictions(input_image):
+    
+    width, height = input_image.size
+    img_size=(width, height)
+    input_image = distortion_free_resize(input_image, img_size)
+    input_image = tf.image.convert_image_dtype(input_image, tf.float32)/255.0
+    
     pred = loaded_model.predict(input_image)
     input_len = np.ones(pred.shape[0]) * pred.shape[1]
     # Use greedy search. For complex tasks, you can use beam search.