Clean up deprecation warnings (#19654)

* Clean up deprecation warnings

Notes:
Changed some strings in tests to raw strings, which will change the literal content of the strings as they are fed into whatever machine handles them.
Test cases for past in the past/past_key_values switch changed/removed due to warning of impending removal

* Add PILImageResampling abstraction for PIL.Image.Resampling

src/transformers/models/gptj/modeling_tf_gptj.py

@@ -761,7 +761,7 @@ class TFGPTJForCausalLM(TFGPTJPreTrainedModel, TFCausalLanguageModelingLoss):
             "input_ids": inputs,
             "attention_mask": attention_mask,
             "position_ids": position_ids,
-            "past": past,
+            "past_key_values": past,
             "use_cache": use_cache,
             "token_type_ids": token_type_ids,
         }

src/transformers/models/hubert/modeling_hubert.py

@@ -133,7 +133,7 @@ def _compute_mask_indices(
     )
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
     spec_aug_mask_idxs = []
 
     max_num_masked_span = compute_num_masked_span(sequence_length)

src/transformers/models/imagegpt/feature_extraction_imagegpt.py

@@ -19,6 +19,8 @@ from typing import List, Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import ImageFeatureExtractionMixin, is_torch_tensor
 from ...utils import TensorType, logging
@@ -60,17 +62,20 @@ class ImageGPTFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMix
             Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then the input will be resized to (size, size). Only has an effect if `do_resize` is
             set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BILINEAR`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            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_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to normalize the input to the range between -1 and +1.
     """
 
     model_input_names = ["input_ids"]
 
-    def __init__(self, clusters, do_resize=True, size=32, resample=Image.BILINEAR, do_normalize=True, **kwargs):
+    def __init__(
+        self, clusters, do_resize=True, size=32, resample=PILImageResampling.BILINEAR, do_normalize=True, **kwargs
+    ):
         super().__init__(**kwargs)
         self.clusters = np.asarray(clusters)
         self.do_resize = do_resize

src/transformers/models/layoutlmv2/feature_extraction_layoutlmv2.py

@@ -21,6 +21,8 @@ from typing import List, Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import ImageFeatureExtractionMixin, is_torch_tensor
 from ...utils import TensorType, is_pytesseract_available, logging, requires_backends
@@ -94,10 +96,11 @@ class LayoutLMv2FeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
             Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then the input will be resized to (size, size). Only has an effect if `do_resize` is
             set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BILINEAR`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            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`.
         apply_ocr (`bool`, *optional*, defaults to `True`):
             Whether to apply the Tesseract OCR engine to get words + normalized bounding boxes.
         ocr_lang (`str`, *optional*):
@@ -119,7 +122,7 @@ class LayoutLMv2FeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
         self,
         do_resize=True,
         size=224,
-        resample=Image.BILINEAR,
+        resample=PILImageResampling.BILINEAR,
         apply_ocr=True,
         ocr_lang=None,
         tesseract_config="",

src/transformers/models/layoutlmv3/feature_extraction_layoutlmv3.py

@@ -21,6 +21,8 @@ from typing import List, Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import IMAGENET_STANDARD_MEAN, IMAGENET_STANDARD_STD, ImageFeatureExtractionMixin, is_torch_tensor
 from ...utils import TensorType, is_pytesseract_available, logging, requires_backends
@@ -93,10 +95,11 @@ class LayoutLMv3FeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
             Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then the input will be resized to (size, size). Only has an effect if `do_resize` is
             set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BILINEAR`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            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_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to normalize the input with mean and standard deviation.
         image_mean (`List[int]`, defaults to `[0.5, 0.5, 0.5]`):
@@ -124,7 +127,7 @@ class LayoutLMv3FeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
         self,
         do_resize=True,
         size=224,
-        resample=Image.BILINEAR,
+        resample=PILImageResampling.BILINEAR,
         do_normalize=True,
         image_mean=None,
         image_std=None,

src/transformers/models/levit/feature_extraction_levit.py

@@ -19,6 +19,8 @@ from typing import Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import (
     IMAGENET_DEFAULT_MEAN,
@@ -46,10 +48,11 @@ class LevitFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin)
         size (`int` or `Tuple(int)`, *optional*, defaults to 224):
             Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then shorter side of input will be resized to 'size'.
-        resample (`int`, *optional*, defaults to `PIL.Image.BICUBIC`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.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 or not to center crop the input to `size`.
         do_normalize (`bool`, *optional*, defaults to `True`):
@@ -66,7 +69,7 @@ class LevitFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin)
         self,
         do_resize=True,
         size=224,
-        resample=Image.BICUBIC,
+        resample=PILImageResampling.BICUBIC,
         do_center_crop=True,
         do_normalize=True,
         image_mean=IMAGENET_DEFAULT_MEAN,

src/transformers/models/maskformer/feature_extraction_maskformer.py

@@ -19,6 +19,8 @@ from typing import TYPE_CHECKING, Dict, List, Optional, Set, Tuple, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import ImageFeatureExtractionMixin, ImageInput, is_torch_tensor
 from ...utils import TensorType, is_torch_available, logging
@@ -201,10 +203,11 @@ class MaskFormerFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
         max_size (`int`, *optional*, defaults to 1333):
             The largest size an image dimension can have (otherwise it's capped). Only has an effect if `do_resize` is
             set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BILINEAR`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            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`.
         size_divisibility (`int`, *optional*, defaults to 32):
             Some backbones need images divisible by a certain number. If not passed, it defaults to the value used in
             Swin Transformer.
@@ -232,7 +235,7 @@ class MaskFormerFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
         do_resize=True,
         size=800,
         max_size=1333,
-        resample=Image.BILINEAR,
+        resample=PILImageResampling.BILINEAR,
         size_divisibility=32,
         do_normalize=True,
         image_mean=None,

src/transformers/models/mobilevit/feature_extraction_mobilevit.py

@@ -19,6 +19,8 @@ from typing import List, Optional, Tuple, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import ImageFeatureExtractionMixin, ImageInput, is_torch_tensor
 from ...utils import TensorType, is_torch_available, logging
@@ -44,10 +46,11 @@ class MobileViTFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMi
             Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then the input will be resized to match the shorter side. Only has an effect if
             `do_resize` is set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BILINEAR`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            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.
@@ -63,7 +66,7 @@ class MobileViTFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMi
         self,
         do_resize=True,
         size=288,
-        resample=Image.BILINEAR,
+        resample=PILImageResampling.BILINEAR,
         do_center_crop=True,
         crop_size=256,
         do_flip_channel_order=True,

src/transformers/models/owlvit/feature_extraction_owlvit.py

@@ -19,6 +19,8 @@ from typing import List, Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import ImageFeatureExtractionMixin, is_torch_tensor
 from ...utils import TensorType, is_torch_available, logging
@@ -54,10 +56,11 @@ class OwlViTFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin
             The size to use for resizing the image. Only has an effect if `do_resize` is set to `True`. If `size` is a
             sequence like (h, w), output size will be matched to this. If `size` is an int, then image will be resized
             to (size, size).
-        resample (`int`, *optional*, defaults to `PIL.Image.BICUBIC`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.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 `False`):
             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.
@@ -77,7 +80,7 @@ class OwlViTFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin
         self,
         do_resize=True,
         size=(768, 768),
-        resample=Image.BICUBIC,
+        resample=PILImageResampling.BICUBIC,
         crop_size=768,
         do_center_crop=False,
         do_normalize=True,

src/transformers/models/perceiver/feature_extraction_perceiver.py

@@ -19,6 +19,8 @@ from typing import Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import (
     IMAGENET_DEFAULT_MEAN,
@@ -52,10 +54,11 @@ class PerceiverFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMi
             Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then the input will be resized to (size, size). Only has an effect if `do_resize` is
             set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BICUBIC`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.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_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to normalize the input with `image_mean` and `image_std`.
         image_mean (`List[int]`, defaults to `[0.485, 0.456, 0.406]`):
@@ -72,7 +75,7 @@ class PerceiverFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMi
         crop_size=256,
         do_resize=True,
         size=224,
-        resample=Image.BICUBIC,
+        resample=PILImageResampling.BICUBIC,
         do_normalize=True,
         image_mean=None,
         image_std=None,

src/transformers/models/poolformer/feature_extraction_poolformer.py

@@ -20,6 +20,8 @@ from typing import Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import (
     IMAGENET_DEFAULT_MEAN,
@@ -48,10 +50,11 @@ class PoolFormerFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
             Center crop the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then the input will be center cropped to (size, size). Only has an effect if
             `do_resize_and_center_crop` is set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BICUBIC`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize_and_center_crop` 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`.
         crop_pct (`float`, *optional*, defaults to `0.9`):
             The percentage of the image to crop from the center. Only has an effect if `do_resize_and_center_crop` is
             set to `True`.
@@ -69,7 +72,7 @@ class PoolFormerFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionM
         self,
         do_resize_and_center_crop=True,
         size=224,
-        resample=Image.BICUBIC,
+        resample=PILImageResampling.BICUBIC,
         crop_pct=0.9,
         do_normalize=True,
         image_mean=None,

src/transformers/models/segformer/feature_extraction_segformer.py

@@ -19,6 +19,8 @@ from typing import List, Optional, Tuple, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import (
     IMAGENET_DEFAULT_MEAN,
@@ -50,10 +52,11 @@ class SegformerFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMi
             Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then the input will be resized to (size, size). Only has an effect if `do_resize` is
             set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BILINEAR`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            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_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to normalize the input with mean and standard deviation.
         image_mean (`int`, *optional*, defaults to `[0.485, 0.456, 0.406]`):
@@ -73,7 +76,7 @@ class SegformerFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMi
         self,
         do_resize=True,
         size=512,
-        resample=Image.BILINEAR,
+        resample=PILImageResampling.BILINEAR,
         do_normalize=True,
         image_mean=None,
         image_std=None,

src/transformers/models/sew/modeling_sew.py

@@ -133,7 +133,7 @@ def _compute_mask_indices(
     )
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
     spec_aug_mask_idxs = []
 
     max_num_masked_span = compute_num_masked_span(sequence_length)

src/transformers/models/sew_d/modeling_sew_d.py

@@ -134,7 +134,7 @@ def _compute_mask_indices(
     )
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
     spec_aug_mask_idxs = []
 
     max_num_masked_span = compute_num_masked_span(sequence_length)

src/transformers/models/unispeech/modeling_unispeech.py

@@ -169,7 +169,7 @@ def _compute_mask_indices(
     )
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
     spec_aug_mask_idxs = []
 
     max_num_masked_span = compute_num_masked_span(sequence_length)

src/transformers/models/unispeech_sat/modeling_unispeech_sat.py

@@ -183,7 +183,7 @@ def _compute_mask_indices(
     )
 
     # SpecAugment mask to fill
-    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=np.bool)
+    spec_aug_mask = np.zeros((batch_size, sequence_length), dtype=bool)
     spec_aug_mask_idxs = []
 
     max_num_masked_span = compute_num_masked_span(sequence_length)

src/transformers/models/videomae/feature_extraction_videomae.py

@@ -19,6 +19,8 @@ from typing import Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import ImageFeatureExtractionMixin, ImageInput, is_torch_tensor
 from ...utils import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD, TensorType, logging
@@ -39,10 +41,11 @@ class VideoMAEFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMix
             Whether to resize the shorter edge of the input to a certain `size`.
         size (`int`, *optional*, defaults to 224):
             Resize the shorter edge of the input to the given size. Only has an effect if `do_resize` is set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BILINEAR`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            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 center crop the input to a certain `size`.
         do_normalize (`bool`, *optional*, defaults to `True`):
@@ -59,7 +62,7 @@ class VideoMAEFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMix
         self,
         do_resize=True,
         size=224,
-        resample=Image.BILINEAR,
+        resample=PILImageResampling.BILINEAR,
         do_center_crop=True,
         do_normalize=True,
         image_mean=None,

src/transformers/models/vilt/feature_extraction_vilt.py

@@ -19,6 +19,8 @@ from typing import List, Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import (
     IMAGENET_STANDARD_MEAN,
@@ -53,10 +55,11 @@ class ViltFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
             `do_resize` is set to `True`.
         size_divisor (`int`, *optional*, defaults to 32):
             The size by which to make sure both the height and width can be divided.
-        resample (`int`, *optional*, defaults to `PIL.Image.BICUBIC`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.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_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to normalize the input with mean and standard deviation.
         image_mean (`List[int]`, defaults to `[0.5, 0.5, 0.5]`):
@@ -72,7 +75,7 @@ class ViltFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
         do_resize=True,
         size=384,
         size_divisor=32,
-        resample=Image.BICUBIC,
+        resample=PILImageResampling.BICUBIC,
         do_normalize=True,
         image_mean=None,
         image_std=None,
@@ -87,7 +90,7 @@ class ViltFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
         self.image_mean = image_mean if image_mean is not None else IMAGENET_STANDARD_MEAN
         self.image_std = image_std if image_std is not None else IMAGENET_STANDARD_STD
 
-    def _resize(self, image, shorter=800, longer=1333, size_divisor=32, resample=Image.BICUBIC):
+    def _resize(self, image, shorter=800, longer=1333, size_divisor=32, resample=PILImageResampling.BICUBIC):
         """
         Resizes the shorter edge of `image` to `shorter` and limits the longer edge to under `longer`, while preserving
         the aspect ratio. Also makes sure that both the height and width can be divided by `size_divisor`.
@@ -104,7 +107,7 @@ class ViltFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
                 The size by which to limit the longer side of the image, while preserving the aspect ratio.
             size_divisor (`int`, *optional*, defaults to `32`):
                 The size by which both the height and the width must be divisible.
-            resample (`int`, *optional*, defaults to `PIL.Image.BICUBIC`):
+            resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BICUBIC`):
                 An optional resampling filter.
         """
         if not isinstance(image, Image.Image):

src/transformers/models/vit/feature_extraction_vit.py

@@ -19,6 +19,8 @@ from typing import Optional, Union
 import numpy as np
 from PIL import Image
 
+from transformers.image_utils import PILImageResampling
+
 from ...feature_extraction_utils import BatchFeature, FeatureExtractionMixin
 from ...image_utils import (
     IMAGENET_STANDARD_MEAN,
@@ -47,10 +49,11 @@ class ViTFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
             Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an
             integer is provided, then the input will be resized to (size, size). Only has an effect if `do_resize` is
             set to `True`.
-        resample (`int`, *optional*, defaults to `PIL.Image.BILINEAR`):
-            An optional resampling filter. This can be one of `PIL.Image.NEAREST`, `PIL.Image.BOX`,
-            `PIL.Image.BILINEAR`, `PIL.Image.HAMMING`, `PIL.Image.BICUBIC` or `PIL.Image.LANCZOS`. Only has an effect
-            if `do_resize` is set to `True`.
+        resample (`int`, *optional*, defaults to `PIL.Image.Resampling.BILINEAR`):
+            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_normalize (`bool`, *optional*, defaults to `True`):
             Whether or not to normalize the input with mean and standard deviation.
         image_mean (`List[int]`, defaults to `[0.5, 0.5, 0.5]`):
@@ -65,7 +68,7 @@ class ViTFeatureExtractor(FeatureExtractionMixin, ImageFeatureExtractionMixin):
         self,
         do_resize=True,
         size=224,
-        resample=Image.BILINEAR,
+        resample=PILImageResampling.BILINEAR,
         do_normalize=True,
         image_mean=None,
         image_std=None,

src/transformers/models/vit_mae/modeling_vit_mae.py

@@ -182,7 +182,7 @@ def get_1d_sincos_pos_embed_from_grid(embed_dim, pos):
     if embed_dim % 2 != 0:
         raise ValueError("embed_dim must be even")
 
-    omega = np.arange(embed_dim // 2, dtype=np.float)
+    omega = np.arange(embed_dim // 2, dtype=float)
     omega /= embed_dim / 2.0
     omega = 1.0 / 10000**omega  # (D/2,)