keras-hub-nightly 0.19.0.dev202502060348__py3-none-any.whl → 0.19.0.dev202502080344__py3-none-any.whl

keras_hub/src/models/retinanet/retinanet_label_encoder.py

@@ -3,11 +3,7 @@ import math
 import keras
 from keras import ops
 
-# TODO: https://github.com/keras-team/keras-hub/issues/1965
-from keras_hub.src.bounding_box.converters import convert_format
-from keras_hub.src.bounding_box.converters import encode_box_to_deltas
-from keras_hub.src.bounding_box.iou import compute_iou
-from keras_hub.src.models.retinanet.box_matcher import BoxMatcher
+from keras_hub.src.layers.modeling.box_matcher import BoxMatcher
 from keras_hub.src.utils import tensor_utils
 
 
@@ -30,7 +26,8 @@ class RetinaNetLabelEncoder(keras.layers.Layer):
         anchor_generator:  A `keras_hub.layers.AnchorGenerator`.
         bounding_box_format: str. Ground truth format of bounding boxes.
         encoding_format: str. The desired target encoding format for the boxes.
-            TODO: https://github.com/keras-team/keras-hub/issues/1907
+            Refer: `keras.utils.bounding_boxes.convert_format` for supported
+            formats.
         positive_threshold:  float. the threshold to set an anchor to positive
             match to gt box. Values above it are positive matches.
             Defaults to `0.5`
@@ -113,7 +110,7 @@ class RetinaNetLabelEncoder(keras.layers.Layer):
                 "support  unbatched inputs for the `images` argument. "
                 f"Received `shape(images)={images_shape}`."
             )
-        image_shape = images_shape[1:]
+        height, width, channels = images_shape[1:]
 
         if len(ops.shape(gt_classes)) == 2:
             gt_classes = ops.expand_dims(gt_classes, axis=-1)
@@ -122,14 +119,16 @@ class RetinaNetLabelEncoder(keras.layers.Layer):
         anchor_boxes = ops.concatenate(list(anchor_boxes.values()), axis=0)
 
         box_targets, class_targets = self._encode_sample(
-            gt_boxes, gt_classes, anchor_boxes, image_shape
+            gt_boxes, gt_classes, anchor_boxes, height, width, channels
         )
         box_targets = ops.reshape(
             box_targets, (-1, ops.shape(box_targets)[1], 4)
         )
         return box_targets, class_targets
 
-    def _encode_sample(self, gt_boxes, gt_classes, anchor_boxes, image_shape):
+    def _encode_sample(
+        self, gt_boxes, gt_classes, anchor_boxes, height, width, channels
+    ):
         """Creates box and classification targets for a batched sample.
 
         Matches ground truth boxes to anchor boxes based on IOU.
@@ -149,23 +148,26 @@ class RetinaNetLabelEncoder(keras.layers.Layer):
             anchor_boxes: A Tensor with the shape `[total_anchors, 4]`
                 representing all the anchor boxes for a given input image shape,
                 where each anchor box is of the format `[x, y, width, height]`.
-            image_shape: Tuple indicating the image shape `[H, W, C]`.
+            height: int. Height of the inputs.
+            width: int. Width of the inputs.
+            channels: int. Number of channesl in the inputs.
 
         Returns:
             Encoded bounding boxes in the format of `center_yxwh` and
             corresponding labels for each encoded bounding box.
         """
-        anchor_boxes = convert_format(
+        anchor_boxes = keras.utils.bounding_boxes.convert_format(
             anchor_boxes,
             source=self.anchor_generator.bounding_box_format,
             target=self.bounding_box_format,
-            image_shape=image_shape,
+            height=height,
+            width=width,
         )
-        iou_matrix = compute_iou(
+        iou_matrix = keras.utils.bounding_boxes.compute_iou(
             anchor_boxes,
             gt_boxes,
             bounding_box_format=self.bounding_box_format,
-            image_shape=image_shape,
+            image_shape=(height, width, channels),
         )
 
         matched_gt_idx, matched_vals = self.box_matcher(iou_matrix)
@@ -179,14 +181,14 @@ class RetinaNetLabelEncoder(keras.layers.Layer):
             matched_gt_boxes, (-1, ops.shape(matched_gt_boxes)[1], 4)
         )
 
-        box_targets = encode_box_to_deltas(
+        box_targets = keras.utils.bounding_boxes.encode_box_to_deltas(
             anchors=anchor_boxes,
             boxes=matched_gt_boxes,
             anchor_format=self.bounding_box_format,
             box_format=self.bounding_box_format,
             encoding_format=self.encoding_format,
             variance=self.box_variance,
-            image_shape=image_shape,
+            image_shape=(height, width, channels),
         )
 
         matched_gt_cls_ids = tensor_utils.target_gather(

keras_hub/src/models/retinanet/retinanet_object_detector.py

@@ -2,13 +2,9 @@ import keras
 from keras import ops
 
 from keras_hub.src.api_export import keras_hub_export
-
-# TODO: https://github.com/keras-team/keras-hub/issues/1965
-from keras_hub.src.bounding_box.converters import convert_format
-from keras_hub.src.bounding_box.converters import decode_deltas_to_boxes
-from keras_hub.src.models.image_object_detector import ImageObjectDetector
-from keras_hub.src.models.retinanet.anchor_generator import AnchorGenerator
-from keras_hub.src.models.retinanet.non_max_supression import NonMaxSuppression
+from keras_hub.src.layers.modeling.anchor_generator import AnchorGenerator
+from keras_hub.src.layers.modeling.non_max_supression import NonMaxSuppression
+from keras_hub.src.models.object_detector import ObjectDetector
 from keras_hub.src.models.retinanet.prediction_head import PredictionHead
 from keras_hub.src.models.retinanet.retinanet_backbone import RetinaNetBackbone
 from keras_hub.src.models.retinanet.retinanet_label_encoder import (
@@ -17,10 +13,11 @@ from keras_hub.src.models.retinanet.retinanet_label_encoder import (
 from keras_hub.src.models.retinanet.retinanet_object_detector_preprocessor import (  # noqa: E501
     RetinaNetObjectDetectorPreprocessor,
 )
+from keras_hub.src.utils.tensor_utils import assert_bounding_box_support
 
 
 @keras_hub_export("keras_hub.models.RetinaNetObjectDetector")
-class RetinaNetObjectDetector(ImageObjectDetector):
+class RetinaNetObjectDetector(ObjectDetector):
     """RetinaNet object detector model.
 
     This class implements the RetinaNet object detection architecture.
@@ -47,9 +44,7 @@ class RetinaNetObjectDetector(ImageObjectDetector):
             arguments.
         num_classes: int. The number of object classes to be detected.
         bounding_box_format: str. Dataset bounding box format (e.g., "xyxy",
-            "yxyx"). The supported formats are
-            refer TODO: https://github.com/keras-team/keras-hub/issues/1907.
-            Defaults to `yxyx`.
+            "yxyx"). Defaults to `yxyx`.
         label_encoder: Optional. A `RetinaNetLabelEncoder` instance.  Encodes
             ground truth boxes and classes into training targets. It matches
             ground truth boxes to anchors based on IoU and encodes box
@@ -107,6 +102,9 @@ class RetinaNetObjectDetector(ImageObjectDetector):
         prediction_decoder=None,
         **kwargs,
     ):
+        # Check whether current version of keras support bounding box utils
+        assert_bounding_box_support(self.__class__.__name__)
+
         # === Layers ===
         image_input = keras.layers.Input(backbone.image_shape, name="images")
         head_dtype = dtype or backbone.dtype_policy
@@ -204,17 +202,19 @@ class RetinaNetObjectDetector(ImageObjectDetector):
         )
 
     def compute_loss(self, x, y, y_pred, sample_weight, **kwargs):
-        y_for_label_encoder = convert_format(
+        _, height, width, _ = keras.ops.shape(x)
+        y_for_label_encoder = keras.utils.bounding_boxes.convert_format(
             y,
             source=self.bounding_box_format,
             target=self.label_encoder.bounding_box_format,
-            images=x,
+            height=height,
+            width=width,
         )
 
-        boxes, classes = self.label_encoder(
+        boxes, labels = self.label_encoder(
             images=x,
             gt_boxes=y_for_label_encoder["boxes"],
-            gt_classes=y_for_label_encoder["classes"],
+            gt_classes=y_for_label_encoder["labels"],
         )
 
         box_pred = y_pred["bbox_regression"]
@@ -242,11 +242,11 @@ class RetinaNetObjectDetector(ImageObjectDetector):
             )
 
         cls_labels = ops.one_hot(
-            ops.cast(classes, "int32"), self.num_classes, dtype="float32"
+            ops.cast(labels, "int32"), self.num_classes, dtype="float32"
         )
-        positive_mask = ops.cast(ops.greater(classes, -1.0), dtype="float32")
+        positive_mask = ops.cast(ops.greater(labels, -1.0), dtype="float32")
         normalizer = ops.sum(positive_mask)
-        cls_weights = ops.cast(ops.not_equal(classes, -2.0), dtype="float32")
+        cls_weights = ops.cast(ops.not_equal(labels, -2.0), dtype="float32")
         cls_weights /= normalizer
         box_weights = positive_mask / normalizer
 
@@ -306,32 +306,32 @@ class RetinaNetObjectDetector(ImageObjectDetector):
             images, _ = data
         else:
             images = data
-        image_shape = ops.shape(images)[1:]
+        height, width, channels = ops.shape(images)[1:]
         anchor_boxes = self.anchor_generator(images)
         anchor_boxes = ops.concatenate(list(anchor_boxes.values()), axis=0)
-        box_pred = decode_deltas_to_boxes(
+        box_pred = keras.utils.bounding_boxes.decode_deltas_to_boxes(
             anchors=anchor_boxes,
             boxes_delta=box_pred,
             encoded_format="center_xywh",
             anchor_format=self.anchor_generator.bounding_box_format,
             box_format=self.bounding_box_format,
-            image_shape=image_shape,
+            image_shape=(height, width, channels),
         )
         # box_pred is now in "self.bounding_box_format" format
-        box_pred = convert_format(
+        box_pred = keras.utils.bounding_boxes.convert_format(
             box_pred,
             source=self.bounding_box_format,
             target=self.prediction_decoder.bounding_box_format,
-            image_shape=image_shape,
-        )
-        y_pred = self.prediction_decoder(
-            box_pred, cls_pred, image_shape=image_shape
+            height=height,
+            width=width,
         )
-        y_pred["boxes"] = convert_format(
+        y_pred = self.prediction_decoder(box_pred, cls_pred, images=images)
+        y_pred["boxes"] = keras.utils.bounding_boxes.convert_format(
             y_pred["boxes"],
             source=self.prediction_decoder.bounding_box_format,
             target=self.bounding_box_format,
-            image_shape=image_shape,
+            height=height,
+            width=width,
         )
         return y_pred
 

keras_hub/src/models/retinanet/retinanet_object_detector_preprocessor.py

@@ -1,6 +1,6 @@
 from keras_hub.src.api_export import keras_hub_export
-from keras_hub.src.models.image_object_detector_preprocessor import (
-    ImageObjectDetectorPreprocessor,
+from keras_hub.src.models.object_detector_preprocessor import (
+    ObjectDetectorPreprocessor,
 )
 from keras_hub.src.models.retinanet.retinanet_backbone import RetinaNetBackbone
 from keras_hub.src.models.retinanet.retinanet_image_converter import (
@@ -9,6 +9,6 @@ from keras_hub.src.models.retinanet.retinanet_image_converter import (
 
 
 @keras_hub_export("keras_hub.models.RetinaNetObjectDetectorPreprocessor")
-class RetinaNetObjectDetectorPreprocessor(ImageObjectDetectorPreprocessor):
+class RetinaNetObjectDetectorPreprocessor(ObjectDetectorPreprocessor):
     backbone_cls = RetinaNetBackbone
     image_converter_cls = RetinaNetImageConverter

keras_hub/src/utils/tensor_utils.py

@@ -6,6 +6,7 @@ import threading
 import keras
 import numpy as np
 from keras import ops
+from packaging import version
 
 try:
     import tensorflow as tf
@@ -262,6 +263,18 @@ def assert_tf_libs_installed(symbol_name):
         )
 
 
+def check_bounding_box_support():
+    return version.parse(keras.__version__) >= version.parse("3.8.0")
+
+
+def assert_bounding_box_support(symbol_name):
+    if not check_bounding_box_support():
+        raise ImportError(
+            f"{symbol_name} requires Keras version to be 3.8.0 or higher. "
+            f"Current keras version: {keras.__version__}"
+        )
+
+
 def assert_tf_backend(symbol_name):
     if keras.config.backend() != "tensorflow":
         raise RuntimeError(

keras_hub/src/version_utils.py

@@ -1,7 +1,7 @@
 from keras_hub.src.api_export import keras_hub_export
 
 # Unique source of truth for the version number.
-__version__ = "0.19.0.dev202502060348"
+__version__ = "0.19.0.dev202502080344"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub_nightly-0.19.0.dev202502060348.dist-info → keras_hub_nightly-0.19.0.dev202502080344.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: keras-hub-nightly
-Version: 0.19.0.dev202502060348
+Version: 0.19.0.dev202502080344
 Summary: Industry-strength Natural Language Processing extensions for Keras.
 Home-page: https://github.com/keras-team/keras-hub
 Author: Keras team

{keras_hub_nightly-0.19.0.dev202502060348.dist-info → keras_hub_nightly-0.19.0.dev202502080344.dist-info}/RECORD

@@ -1,29 +1,23 @@
 keras_hub/__init__.py,sha256=QGdXyHgYt6cMUAP1ebxwc6oR86dE0dkMxNy2eOCQtFo,855
-keras_hub/api/__init__.py,sha256=spMxsgqzjpeuC8rY4WP-2kAZ2qwwKRSbFwddXgUjqQE,524
-keras_hub/api/bounding_box/__init__.py,sha256=T8R_X7BPm0et1xaZq8565uJmid7dylsSFSj4V-rGuFQ,1097
-keras_hub/api/layers/__init__.py,sha256=YO_YLbcxMEboFEgmFkzRf_JfQciQukX2AseOGpWEbDo,3195
+keras_hub/api/__init__.py,sha256=EzR6D-XWsm_gDrX5LDwKEmrah_gu3ffpj8GKBudE0yI,485
+keras_hub/api/layers/__init__.py,sha256=oHP3UTIAom7bK1E3nCZzK8wQ-TdYKtgF-wL9_-xzyhQ,3338
 keras_hub/api/metrics/__init__.py,sha256=So8Ec-lOcTzn_UUMmAdzDm8RKkPu2dbRUm2px8gpUEI,381
-keras_hub/api/models/__init__.py,sha256=suTcar7FqO5w9nNtalqmfYn7Fs6XmNEGpbojK-gaMEY,16795
+keras_hub/api/models/__init__.py,sha256=YqsLw0u69F93OpS6E677hIeka_hIgjIleSt-xjVqqrk,17002
 keras_hub/api/samplers/__init__.py,sha256=n-_SEXxr2LNUzK2FqVFN7alsrkx1P_HOVTeLZKeGCdE,730
 keras_hub/api/tokenizers/__init__.py,sha256=mtJgQy1spfQnPAkeLoeinsT_W9iCWHlJXwzcol5W1aU,2524
 keras_hub/api/utils/__init__.py,sha256=Gp1E6gG-RtKQS3PBEQEOz9PQvXkXaJ0ySGMqZ7myN7A,215
 keras_hub/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/api_export.py,sha256=9pQZK27JObxWZ96QPLBp1OBsjWigh1iuV6RglPGMRk0,1499
-keras_hub/src/version_utils.py,sha256=9jSO2EIm-H2g7HB6xeztJp-sIsCQm3uK5Cmu0f4CqFU,222
-keras_hub/src/bounding_box/__init__.py,sha256=7i6KnGupN4AVivR_dFjQyuuTbI0GkHy8d-aMXeqZdU8,95
-keras_hub/src/bounding_box/converters.py,sha256=UUp1hwegpDZyIo8sh9TLNy1v6JjwmvwzL6wmHFMAtbk,21916
-keras_hub/src/bounding_box/formats.py,sha256=YmskOz2BOSat7NaE__J9VfpSNGPJJR0znSzA4lp8MMI,3868
-keras_hub/src/bounding_box/iou.py,sha256=wmBKEUwu7Q-dJMoTO9I493NQAwpU7lF4oWLpccpkQ0I,9116
-keras_hub/src/bounding_box/to_dense.py,sha256=usSkar5PfEoW-ZasacBXNHpJ-XaRHLUTnSagef2sZxo,2775
-keras_hub/src/bounding_box/to_ragged.py,sha256=Z7lZN-wlMIF0FLRknewgqrRlIDhmhvWh8QwLAcNxoek,2874
-keras_hub/src/bounding_box/utils.py,sha256=ejWDLDTsZd_k3cfBqxhKWlYV2vwd0RInLmPNTPYpsLA,6441
-keras_hub/src/bounding_box/validate_format.py,sha256=05hdCs7ICavuEPog2syCuNe8i8r0xPZQSnkQA7ncr2c,3054
+keras_hub/src/version_utils.py,sha256=xerud-Qd3XquCvXGjsryhnIuIA6bgqbnKrFjbxL91i0,222
 keras_hub/src/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/layers/modeling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/layers/modeling/alibi_bias.py,sha256=1XBTHI52L_iJDhN_w5ydu_iMhCuTgQAxEPwcLA6BPuk,4411
+keras_hub/src/layers/modeling/anchor_generator.py,sha256=gmT-RCtXpLzNoS4wf5xPgZZMjHnj9zp3VnEXRyxLE5c,6671
+keras_hub/src/layers/modeling/box_matcher.py,sha256=lp1aQpTZtrGWScWM2iFnkIlXkzYO-Id6QvKnOPfXKWM,11242
 keras_hub/src/layers/modeling/cached_multi_head_attention.py,sha256=8IDyP3JMeALV1K7Ot04o6MehyS7zDVpci4uvlTZY1oc,5600
 keras_hub/src/layers/modeling/f_net_encoder.py,sha256=zkVeO5Nk_kBZCUGq2LeDGmPEIM_cr-aGqCKtQGOHKTY,6842
 keras_hub/src/layers/modeling/masked_lm_head.py,sha256=no6XQb76KB2cUiksYC0MSdyeDOK7pn8MY6cmdCDxpKs,9015
+keras_hub/src/layers/modeling/non_max_supression.py,sha256=yAkAH1CCj_tYXgQTav39IRr_Uxn8hmzJgIxqbYQyZY8,22565
 keras_hub/src/layers/modeling/position_embedding.py,sha256=FfTS6JGMhnOIzo9bHzvoxBbdQNctc32iRLI7ZjdxoTY,3850
 keras_hub/src/layers/modeling/reversible_embedding.py,sha256=sfm5giI-bHu2J9xm9Tkydx8XM-I_m8Oe0wbW1gzrYjk,11141
 keras_hub/src/layers/modeling/rms_normalization.py,sha256=Ylnc9vkDw1A_ZqiKpQ09jVTAGumS5rspjdQOkH-mxf4,1084
@@ -35,7 +29,7 @@ keras_hub/src/layers/modeling/transformer_encoder.py,sha256=Qe19_aR6w4PTFbzvBmSP
 keras_hub/src/layers/modeling/transformer_layer_utils.py,sha256=FuznrW33iG50B-VDN8R1RjuA5JG72yNMJ1TBgWLxR0E,3487
 keras_hub/src/layers/preprocessing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/layers/preprocessing/audio_converter.py,sha256=YGh_kQw65a1Z6S5zzSNVP-ChyLYHq3-eOYpOS53xIN8,4156
-keras_hub/src/layers/preprocessing/image_converter.py,sha256=XwqgHYWj0Z14UMGQw5E4pOm3MmgbuvQpBcKl36e-nvo,10962
+keras_hub/src/layers/preprocessing/image_converter.py,sha256=z0lLTbAxNixecQcfxvugWaidRmjvlEUZSlPhv8DdS1k,12082
 keras_hub/src/layers/preprocessing/masked_lm_mask_generator.py,sha256=itxWq3FHYlR0I7jKarQlSKbSmRLl9ut_UTSP3ZDwP0A,8162
 keras_hub/src/layers/preprocessing/multi_segment_packer.py,sha256=ZNqnUFnc9Af122Q7T6YyUoXgIdU9AgIJfsvR1UrCjFU,12068
 keras_hub/src/layers/preprocessing/preprocessing_layer.py,sha256=WyX41b9Ev_YJ5uVQVOAqD0PQasMOPDoyDjl_PkzkAkE,687
@@ -56,14 +50,14 @@ keras_hub/src/models/causal_lm_preprocessor.py,sha256=YY7VJZicdmnjDSWi9g4_pEpd5b
 keras_hub/src/models/feature_pyramid_backbone.py,sha256=clEW-TTQSVJ_5qFNdDF0iABkin1p_xlBUFjJrC7T0IA,2247
 keras_hub/src/models/image_classifier.py,sha256=yt6cjhPfqs8A_eWXBsXdXFzn-aRgH2rVHUq7Zu7CyK8,7804
 keras_hub/src/models/image_classifier_preprocessor.py,sha256=Bf7jSqHB1hX2ZWoWQS4GcXNOY_EjeoJi-_vtzCAqw4o,2690
-keras_hub/src/models/image_object_detector.py,sha256=b4Gx6um7Li2-xNA6O2Nb_u0gGD4lmYGNbT3wVo5djho,3721
-keras_hub/src/models/image_object_detector_preprocessor.py,sha256=3g_Qfcu5Gi_HDzXai-QOAL7Td_NC-VsUr-7rJbXnQvk,2232
 keras_hub/src/models/image_segmenter.py,sha256=C1bzIO59pG58iist5GLn_qnlotDpcAVxPV_8a68BkAc,2876
 keras_hub/src/models/image_segmenter_preprocessor.py,sha256=d7I2Hk0SKWyKpjRS6WYccmh_CYQBpWoj0JF5RRrU6rw,3748
 keras_hub/src/models/image_to_image.py,sha256=IJLZ6svgvcQvypwF6oe4SbJj_Zuk2-CrgHFBQcsY7n8,16753
 keras_hub/src/models/inpaint.py,sha256=fxZZrheYIK1rI6BjqZsxt9G2U0afMZR62Z87ZzuSNrQ,20815
 keras_hub/src/models/masked_lm.py,sha256=uXO_dE_hILlOC9jNr6oK6IHi9IGUqLyNGvr6nMt8Rk0,3576
 keras_hub/src/models/masked_lm_preprocessor.py,sha256=g8vrnyYwqdnSw5xppROM1Gzo_jmMWKYZoQCsKdfrFKk,5656
+keras_hub/src/models/object_detector.py,sha256=oAK42fFBKuN0G_WM-DhygFkgQ0KsEwU_ZiU4umHywqc,3757
+keras_hub/src/models/object_detector_preprocessor.py,sha256=kOSVRNFAg-UjtrCEVBdHXUFyJy7kQtlVuGnZ1aLEfOk,2664
 keras_hub/src/models/preprocessor.py,sha256=kBlahgVST3L6vKeWDM4fXuDoXa6pwaJW2A5__L85wFU,8487
 keras_hub/src/models/seq_2_seq_lm.py,sha256=w0gX-5YZjatfvAJmFAgSHyqS_BLqc8FF8DPLGK8mrgI,1864
 keras_hub/src/models/seq_2_seq_lm_preprocessor.py,sha256=DJmm4VTt8AdLtq1k9YKl_VR31cKUHaYjfSbrk7-fJqA,9667
@@ -277,16 +271,13 @@ keras_hub/src/models/resnet/resnet_image_classifier_preprocessor.py,sha256=fM7gy
 keras_hub/src/models/resnet/resnet_image_converter.py,sha256=fgTxihJznGFss-y3Z-jp0JE3X1gaaB2y-f2KMwrT8Pk,342
 keras_hub/src/models/resnet/resnet_presets.py,sha256=cryfXlC_FSEN_jrexKIh5aVbzp87oYetoWeWpX0_lWQ,6947
 keras_hub/src/models/retinanet/__init__.py,sha256=veWIFvMN6151M69l7FvTcI-IIEe_8dLmNO5NLOszQ1c,275
-keras_hub/src/models/retinanet/anchor_generator.py,sha256=0OgKSW3OKmbc0cOPHF6FYTAzn7fcHklg665PGSwAaDM,6504
-keras_hub/src/models/retinanet/box_matcher.py,sha256=l820r1R-ByqiyVgmZ0YFjjz0njchDda-wItzLn1X84o,10834
 keras_hub/src/models/retinanet/feature_pyramid.py,sha256=hbdrj6X-D2SlwOp2h1WcBlTdSAlLmFK43X7OrkJRoMA,17614
-keras_hub/src/models/retinanet/non_max_supression.py,sha256=PMOLlRw-EnyEmhlUhJjEbHf1xXiplN95pUxQbiJQbN4,20996
 keras_hub/src/models/retinanet/prediction_head.py,sha256=xWHt21-SS2t7vCmTONlR1lSbJXhml5jx68V8MGbGybg,7863
 keras_hub/src/models/retinanet/retinanet_backbone.py,sha256=BJBPJLxpOCOU0Br7b4JsgCZBHQHLAhxLqo9BHNIsl1g,5659
-keras_hub/src/models/retinanet/retinanet_image_converter.py,sha256=jO2WSUVubjYc_lRV7A5unhkqQBvqzZN9GHy3dd2ie0U,1730
-keras_hub/src/models/retinanet/retinanet_label_encoder.py,sha256=K4Ffs5Gh052kIvStxQXM7jifMyJVAwAF3kZN-ofr9rQ,10935
-keras_hub/src/models/retinanet/retinanet_object_detector.py,sha256=ROVALhkKq5ImLnlDh4wcc1hVZCF9BD2piKwkpglApUE,15510
-keras_hub/src/models/retinanet/retinanet_object_detector_preprocessor.py,sha256=oKA-rSgX5kIOsCxKjo5Z3x2R5R15k_kUNQQXZ7VAR0c,584
+keras_hub/src/models/retinanet/retinanet_image_converter.py,sha256=Yr1ACzrPXzX1equjDqkrzRQv5nL5TARICc55Gnhwx7o,785
+keras_hub/src/models/retinanet/retinanet_label_encoder.py,sha256=Vowhs4uOZAevmVg1a19efIPfvjxkckXwsJDTX3VPDxs,10967
+keras_hub/src/models/retinanet/retinanet_object_detector.py,sha256=WJ3YLnnC4mcCLLoE7uUFA0cOSVuFgnx9Cr47If50Aig,15595
+keras_hub/src/models/retinanet/retinanet_object_detector_preprocessor.py,sha256=RnJkdqv4zYVcGx50sHoA7j9G1AKwEN-RNtyMQg-MMbo,568
 keras_hub/src/models/retinanet/retinanet_presets.py,sha256=ZOx4SM2c8BsqUQOikkWUhXLGq3Xut1hvjWt_gDXaJRM,510
 keras_hub/src/models/roberta/__init__.py,sha256=3ouSnKdLlMwoDDLVKD9cNtxam6f8XWgCyc0pwWJ0Zjo,263
 keras_hub/src/models/roberta/roberta_backbone.py,sha256=q16dylXbgWshT-elCA08lS_b_IZNphsBrrXiv3eJksM,6339
@@ -395,7 +386,7 @@ keras_hub/src/utils/keras_utils.py,sha256=ZULqIQylAQen-_pNC96htvLaxSJbfAenNoCo3Z
 keras_hub/src/utils/pipeline_model.py,sha256=jgzB6NQPSl0KOu08N-TazfOnXnUJbZjH2EXXhx25Ftg,9084
 keras_hub/src/utils/preset_utils.py,sha256=cRsviMUs-Xskg5KefJ-bQCL9y30yJFyVg3RtvmVCo8o,30504
 keras_hub/src/utils/python_utils.py,sha256=N8nWeO3san4YnGkffRXG3Ix7VEIMTKSN21FX5TuL7G8,202
-keras_hub/src/utils/tensor_utils.py,sha256=YVJesN91bk-OzJXY1mOKBppuY8noBU7zhPQNXPxZVGc,14646
+keras_hub/src/utils/tensor_utils.py,sha256=lczQWgPVJU09cLtNbo8MErVFNV9ne4gNlrzbNVQazg4,15042
 keras_hub/src/utils/imagenet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/utils/imagenet/imagenet_utils.py,sha256=MvIvv1WJo51ZXBxy4S7t_DsN3ZMtJWlC4cmRvKM2kIA,39304
 keras_hub/src/utils/timm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -417,7 +408,7 @@ keras_hub/src/utils/transformers/convert_pali_gemma.py,sha256=B1leeDw96Yvu81hYum
 keras_hub/src/utils/transformers/convert_vit.py,sha256=9SUZ9utNJhW_5cj3acMn9cRy47u2eIcDsrhmzj77o9k,5187
 keras_hub/src/utils/transformers/preset_loader.py,sha256=DgGJXbTSB9Na8FIR-YWWVqQPOFxHwWrGm41EwcS_EFs,3797
 keras_hub/src/utils/transformers/safetensor_utils.py,sha256=CYUHyA4y-B61r7NDnCsFb4t_UmSwZ1k9L-8gzEd6KRg,3339
-keras_hub_nightly-0.19.0.dev202502060348.dist-info/METADATA,sha256=qSqkL3rVgZubkSKyQioX5N7uoPjcnUIQK_Ecqa_jbSc,7498
-keras_hub_nightly-0.19.0.dev202502060348.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-keras_hub_nightly-0.19.0.dev202502060348.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub_nightly-0.19.0.dev202502060348.dist-info/RECORD,,
+keras_hub_nightly-0.19.0.dev202502080344.dist-info/METADATA,sha256=4-2tKEIq093C38m0YTkzJQIsqWpv-UxyR3o0wxGdrqc,7498
+keras_hub_nightly-0.19.0.dev202502080344.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+keras_hub_nightly-0.19.0.dev202502080344.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
+keras_hub_nightly-0.19.0.dev202502080344.dist-info/RECORD,,

keras_hub/api/bounding_box/__init__.py

@@ -1,23 +0,0 @@
-"""DO NOT EDIT.
-
-This file was autogenerated. Do not edit it by hand,
-since your modifications would be overwritten.
-"""
-
-from keras_hub.src.bounding_box.converters import convert_format
-from keras_hub.src.bounding_box.formats import CENTER_XYWH
-from keras_hub.src.bounding_box.formats import REL_XYWH
-from keras_hub.src.bounding_box.formats import REL_XYXY
-from keras_hub.src.bounding_box.formats import REL_YXYX
-from keras_hub.src.bounding_box.formats import XYWH
-from keras_hub.src.bounding_box.formats import XYXY
-from keras_hub.src.bounding_box.formats import YXYX
-from keras_hub.src.bounding_box.iou import compute_ciou
-from keras_hub.src.bounding_box.iou import compute_iou
-from keras_hub.src.bounding_box.to_dense import to_dense
-from keras_hub.src.bounding_box.to_ragged import to_ragged
-from keras_hub.src.bounding_box.utils import as_relative
-from keras_hub.src.bounding_box.utils import clip_boxes
-from keras_hub.src.bounding_box.utils import clip_to_image
-from keras_hub.src.bounding_box.utils import is_relative
-from keras_hub.src.bounding_box.validate_format import validate_format

keras_hub/src/bounding_box/__init__.py

@@ -1,2 +0,0 @@
-# TODO: Once all bounding boxes are moved to keras repostory remove the
-# bounding box folder.