Fix #3446 (#3457)

* update Pillow version

* compare version

Author: JunnYu

paddlenlp/transformers/clip/feature_extraction.py

@@ -18,12 +18,19 @@
 
 import paddle
 import numpy as np
+import PIL.Image
 from PIL import Image
-from PIL.Image import Resampling
 from ..feature_extraction_utils import BatchFeature
 from ..tokenizer_utils_base import TensorType
 from ..image_utils import ImageFeatureExtractionMixin
 
+from ...utils.tools import compare_version
+
+if compare_version(PIL.__version__, "9.1.0") >= 0:
+    Resampling = PIL.Image.Resampling
+else:
+    Resampling = PIL.Image
+
 __all__ = ["CLIPFeatureExtractor"]
 
 
@@ -37,10 +44,10 @@ class CLIPFeatureExtractor(ImageFeatureExtractionMixin):
             Whether to resize the input to a certain `size`.
         size (`int`, *optional*, defaults to 224):
             Resize the input to the given size. Only has an effect if `do_resize` is set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BICUBIC`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.Resampling.BOX`,
-            `PIL.Image.Resampling.BILINEAR`, `PIL.Image.Resampling.HAMMING`, `PIL.Image.Resampling.BICUBIC` or 
-            `PIL.Image.Resampling.LANCZOS`. Only has an effect if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.[Resampling.]BICUBIC`):
+            An optional resampling filter. This can be one of `PIL.Image.[Resampling.]NEAREST`, `PIL.Image.[Resampling.]BOX`,
+            `PIL.Image.[Resampling.]BILINEAR`, `PIL.Image.[Resampling.]HAMMING`, `PIL.Image.[Resampling.]BICUBIC` or 
+            `PIL.Image.[Resampling.]LANCZOS`. Only has an effect if `do_resize` is set to `True`.
         do_center_crop (`bool`, *optional*, defaults to `True`):
             Whether to crop the input at the center. If the input size is smaller than `crop_size` along any edge, the
             image is padded with 0's and then center cropped.

paddlenlp/transformers/ernie_vil/feature_extraction.py

@@ -19,13 +19,20 @@
 
 import paddle
 import numpy as np
+import PIL.Image
 from PIL import Image
-from PIL.Image import Resampling
 
 from ..feature_extraction_utils import BatchFeature
 from ..tokenizer_utils_base import TensorType
 from ..image_utils import ImageFeatureExtractionMixin
 
+from ...utils.tools import compare_version
+
+if compare_version(PIL.__version__, "9.1.0") >= 0:
+    Resampling = PIL.Image.Resampling
+else:
+    Resampling = PIL.Image
+
 __all__ = ["ErnieViLFeatureExtractor"]
 
 
@@ -39,10 +46,10 @@ class ErnieViLFeatureExtractor(ImageFeatureExtractionMixin):
             Whether to resize the input to a certain `size`.
         size (`int`, *optional*, defaults to 224):
             Resize the input to the given size. Only has an effect if `do_resize` is set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BICUBIC`):
-            An optional resampling filter. This can be one of `PIL.Image.Resampling.NEAREST`, `PIL.Image.Resampling.BOX`,
-            `PIL.Image.Resampling.BILINEAR`, `PIL.Image.Resampling.HAMMING`, `PIL.Image.Resampling.BICUBIC` or 
-            `PIL.Image.Resampling.LANCZOS`. Only has an effect if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.[Resampling.]BICUBIC`):
+            An optional resampling filter. This can be one of `PIL.Image.[Resampling.]NEAREST`, `PIL.Image.[Resampling.]BOX`,
+            `PIL.Image.[Resampling.]BILINEAR`, `PIL.Image.[Resampling.]HAMMING`, `PIL.Image.[Resampling.]BICUBIC` or 
+            `PIL.Image.[Resampling.]LANCZOS`. Only has an effect if `do_resize` is set to `True`.
         do_center_crop (`bool`, *optional*, defaults to `True`):
             Whether to crop the input at the center. If the input size is smaller than `crop_size` along any edge, the
             image is padded with 0's and then center cropped.

paddlenlp/transformers/guided_diffusion_utils/transforms.py

@@ -511,7 +511,7 @@ def affine(
         interpolation (InterpolationMode): Desired interpolation enum defined by
             :class:`torchvision.transforms.InterpolationMode`. Default is ``InterpolationMode.NEAREST``.
             If input is Tensor, only ``InterpolationMode.NEAREST``, ``InterpolationMode.BILINEAR`` are supported.
-            For backward compatibility integer values (e.g. ``PIL.Image[.Resampling].NEAREST``) are still accepted,
+            For backward compatibility integer values (e.g. ``PIL.Image.[Resampling.]NEAREST``) are still accepted,
             but deprecated since 0.13 and will be removed in 0.15. Please use InterpolationMode enum.
         fill (sequence or number, optional): Pixel fill value for the area outside the transformed
             image. If given a number, the value is used for all bands respectively.
@@ -660,7 +660,7 @@ class RandomAffine(nn.Layer):
         interpolation (InterpolationMode): Desired interpolation enum defined by
             :class:`torchvision.transforms.InterpolationMode`. Default is ``InterpolationMode.NEAREST``.
             If input is Tensor, only ``InterpolationMode.NEAREST``, ``InterpolationMode.BILINEAR`` are supported.
-            For backward compatibility integer values (e.g. ``PIL.Image[.Resampling].NEAREST``) are still accepted,
+            For backward compatibility integer values (e.g. ``PIL.Image.[Resampling.]NEAREST``) are still accepted,
             but deprecated since 0.13 and will be removed in 0.15. Please use InterpolationMode enum.
         fill (sequence or number): Pixel fill value for the area outside the transformed
             image. Default is ``0``. If given a number, the value is used for all bands respectively.

paddlenlp/transformers/image_utils.py

@@ -20,9 +20,14 @@
 import numpy as np
 import PIL.Image
 import PIL.ImageOps
-from PIL.Image import Resampling
 
 import requests
+from ..utils.tools import compare_version
+
+if compare_version(PIL.__version__, "9.1.0") >= 0:
+    Resampling = PIL.Image.Resampling
+else:
+    Resampling = PIL.Image
 
 IMAGENET_DEFAULT_MEAN = [0.485, 0.456, 0.406]
 IMAGENET_DEFAULT_STD = [0.229, 0.224, 0.225]
@@ -224,7 +229,7 @@ def resize(self,
                 If `size` is an int and `default_to_square` is `True`, then image will be resized to (size, size). If
                 `size` is an int and `default_to_square` is `False`, then smaller edge of the image will be matched to
                 this number. i.e, if height > width, then image will be rescaled to (size * height / width, size).
-            resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            resample (`int`, *optional*, defaults to `PIL.Image.[Resampling.]BILINEAR`):
                 The filter to user for resampling.
             default_to_square (`bool`, *optional*, defaults to `True`):
                 How to convert `size` when it is a single int. If set to `True`, the `size` will be converted to a