[ViTDet] Remove hardcoded image preprocessing and add ViTDet ImageConverter

keras_hub/api/layers/__init__.py

@@ -147,6 +147,9 @@
 from keras_hub.src.models.vit.vit_image_converter import (
     ViTImageConverter as ViTImageConverter,
 )
+from keras_hub.src.models.vit_det.vit_det_image_converter import (
+    ViTDetImageConverter as ViTDetImageConverter,
+)
 from keras_hub.src.models.whisper.whisper_audio_converter import (
     WhisperAudioConverter as WhisperAudioConverter,
 )

keras_hub/src/models/vit_det/vit_det_backbone.py

@@ -1,5 +1,4 @@
 import keras
-from keras import ops
 
 from keras_hub.src.api_export import keras_hub_export
 from keras_hub.src.models.backbone import Backbone
@@ -105,10 +104,6 @@ def __init__(
             )
         img_size = img_input.shape[-3]
         x = img_input
-        # VITDet scales inputs based on the standard ImageNet mean/stddev.
-        x = (x - ops.array([0.485, 0.456, 0.406], dtype=x.dtype)) / (
-            ops.array([0.229, 0.224, 0.225], dtype=x.dtype)
-        )
         x = ViTDetPatchingAndEmbedding(
             kernel_size=(patch_size, patch_size),
             strides=(patch_size, patch_size),

keras_hub/src/models/vit_det/vit_det_image_converter.py

@@ -0,0 +1,40 @@
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.layers.preprocessing.image_converter import ImageConverter
+from keras_hub.src.models.vit_det.vit_det_backbone import ViTDetBackbone
+
+
+@keras_hub_export("keras_hub.layers.ViTDetImageConverter")
+class ViTDetImageConverter(ImageConverter):
+    """Image converter for ViTDet models.
+
+    This layer applies ImageNet normalization (mean=[0.485, 0.456, 0.406],
+    std=[0.229, 0.224, 0.225]) to input images for ViTDet models.
+
+    Args:
+        image_size: int or tuple of (height, width). The output size of the
+            image. Defaults to `(1024, 1024)`.
+
+    Example:
+    ```python
+    converter = keras_hub.layers.ViTDetImageConverter(image_size=(1024, 1024))
+    converter(np.random.rand(1, 512, 512, 3))  # Resizes and normalizes
+    ```
+    """
+
+    backbone_cls = ViTDetBackbone
+
+    def __init__(
+        self,
+        image_size=(1024, 1024),
+        **kwargs,
+    ):
+        mean = [0.485, 0.456, 0.406]
+        std = [0.229, 0.224, 0.225]
+        variance = [x**2 for x in std]
+        super().__init__(
+            image_size=image_size,
+            scale=1.0 / 255.0,  # Scale to [0, 1]
+            mean=mean,
+            variance=variance,
+            **kwargs,
+        )