Add Fast PVT Processor (#37204)

* Add Fast PVT Processor

* Update image_processing_pvt_fast.py

* Update image_processing_pvt_fast.py

* remove kwargs

---------

Co-authored-by: Yoni Gozlan <74535834+yonigozlan@users.noreply.github.com>

docs/source/en/model_doc/pvt.md

@@ -64,6 +64,11 @@ This model was contributed by [Xrenya](https://huggingface.co/Xrenya). The origi
 [[autodoc]] PvtImageProcessor
     - preprocess
 
+## PvtImageProcessorFast
+
+[[autodoc]] PvtImageProcessorFast
+    - preprocess
+
 ## PvtForImageClassification
 
 [[autodoc]] PvtForImageClassification

src/transformers/models/auto/image_processing_auto.py

@@ -133,8 +133,8 @@ else:
             ("pixtral", ("PixtralImageProcessor", "PixtralImageProcessorFast")),
             ("poolformer", ("PoolFormerImageProcessor",)),
             ("prompt_depth_anything", ("PromptDepthAnythingImageProcessor",)),
-            ("pvt", ("PvtImageProcessor",)),
-            ("pvt_v2", ("PvtImageProcessor",)),
+            ("pvt", ("PvtImageProcessor", "PvtImageProcessorFast")),
+            ("pvt_v2", ("PvtImageProcessor", "PvtImageProcessorFast")),
             ("qwen2_5_vl", ("Qwen2VLImageProcessor", "Qwen2VLImageProcessorFast")),
             ("qwen2_vl", ("Qwen2VLImageProcessor", "Qwen2VLImageProcessorFast")),
             ("regnet", ("ConvNextImageProcessor", "ConvNextImageProcessorFast")),

src/transformers/models/pvt/__init__.py

@@ -20,6 +20,7 @@ from ...utils.import_utils import define_import_structure
 if TYPE_CHECKING:
     from .configuration_pvt import *
     from .image_processing_pvt import *
+    from .image_processing_pvt_fast import *
     from .modeling_pvt import *
 else:
     import sys

src/transformers/models/pvt/image_processing_pvt_fast.py

@@ -0,0 +1,44 @@
+# coding=utf-8
+# Copyright 2025 The HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Fast Image processor class for Pvt."""
+
+from ...image_processing_utils_fast import (
+    BASE_IMAGE_PROCESSOR_FAST_DOCSTRING,
+    BaseImageProcessorFast,
+)
+from ...image_utils import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD, PILImageResampling
+from ...utils import add_start_docstrings
+
+
+@add_start_docstrings(
+    "Constructs a fast Pvt image processor.",
+    BASE_IMAGE_PROCESSOR_FAST_DOCSTRING,
+)
+class PvtImageProcessorFast(BaseImageProcessorFast):
+    resample = PILImageResampling.BILINEAR
+    image_mean = IMAGENET_DEFAULT_MEAN
+    image_std = IMAGENET_DEFAULT_STD
+    size = {"height": 224, "width": 224}
+    default_to_square = True
+    crop_size = None
+    do_resize = True
+    do_center_crop = None
+    do_rescale = True
+    do_normalize = True
+    do_convert_rgb = None
+    model_input_names = ["pixel_values"]
+
+
+__all__ = ["PvtImageProcessorFast"]

tests/models/pvt/test_image_processing_pvt.py

@@ -16,7 +16,7 @@
 import unittest
 
 from transformers.testing_utils import require_torch, require_vision
-from transformers.utils import is_vision_available
+from transformers.utils import is_torchvision_available, is_vision_available
 
 from ...test_image_processing_common import ImageProcessingTestMixin, prepare_image_inputs
 
@@ -24,6 +24,9 @@ from ...test_image_processing_common import ImageProcessingTestMixin, prepare_im
 if is_vision_available():
     from transformers import PvtImageProcessor
 
+    if is_torchvision_available():
+        from transformers import PvtImageProcessorFast
+
 
 class PvtImageProcessingTester:
     def __init__(
@@ -81,6 +84,7 @@ class PvtImageProcessingTester:
 @require_vision
 class PvtImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
     image_processing_class = PvtImageProcessor if is_vision_available() else None
+    fast_image_processing_class = PvtImageProcessorFast if is_torchvision_available() else None
 
     def setUp(self):
         super().setUp()
@@ -91,7 +95,8 @@ class PvtImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
         return self.image_processor_tester.prepare_image_processor_dict()
 
     def test_image_processor_properties(self):
-        image_processing = self.image_processing_class(**self.image_processor_dict)
+        for image_processing_class in self.image_processor_list:
+            image_processing = image_processing_class(**self.image_processor_dict)
             self.assertTrue(hasattr(image_processing, "image_mean"))
             self.assertTrue(hasattr(image_processing, "image_std"))
             self.assertTrue(hasattr(image_processing, "do_normalize"))
@@ -99,8 +104,9 @@ class PvtImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
             self.assertTrue(hasattr(image_processing, "size"))
 
     def test_image_processor_from_dict_with_kwargs(self):
-        image_processor = self.image_processing_class.from_dict(self.image_processor_dict)
+        for image_processing_class in self.image_processor_list:
+            image_processor = image_processing_class.from_dict(self.image_processor_dict)
             self.assertEqual(image_processor.size, {"height": 18, "width": 18})
 
-        image_processor = self.image_processing_class.from_dict(self.image_processor_dict, size=42)
+            image_processor = image_processing_class.from_dict(self.image_processor_dict, size=42)
             self.assertEqual(image_processor.size, {"height": 42, "width": 42})