Update doc and default value of TextNetImageProcessor (#35563)

update doc and default value

src/transformers/models/textnet/image_processing_textnet.py

@@ -56,7 +56,7 @@ class TextNetImageProcessor(BaseImageProcessor):
         do_resize (`bool`, *optional*, defaults to `True`):
             Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by
             `do_resize` in the `preprocess` method.
-        size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 224}`):
+        size (`Dict[str, int]` *optional*, defaults to `{"shortest_edge": 640}`):
             Size of the image after resizing. The shortest edge of the image is resized to size["shortest_edge"], with
             the longest edge resized to keep the input aspect ratio. Can be overridden by `size` in the `preprocess`
             method.
@@ -108,7 +108,7 @@ class TextNetImageProcessor(BaseImageProcessor):
         **kwargs,
     ) -> None:
         super().__init__(**kwargs)
-        size = size if size is not None else {"shortest_edge": 224}
+        size = size if size is not None else {"shortest_edge": 640}
         size = get_size_dict(size, default_to_square=False)
         crop_size = crop_size if crop_size is not None else {"height": 224, "width": 224}
         crop_size = get_size_dict(crop_size, param_name="crop_size")

src/transformers/models/textnet/modeling_textnet.py

@@ -370,7 +370,7 @@ class TextNetForImageClassification(TextNetPreTrainedModel):
         >>> processor = TextNetImageProcessor.from_pretrained("czczup/textnet-base")
         >>> model = TextNetForImageClassification.from_pretrained("czczup/textnet-base")
 
-        >>> inputs = processor(images=image, return_tensors="pt", size={"height": 640, "width": 640})
+        >>> inputs = processor(images=image, return_tensors="pt")
         >>> with torch.no_grad():
         ...     outputs = model(**inputs)
         >>> outputs.logits.shape