keras-hub-nightly 0.16.1.dev202409290341__py3-none-any.whl → 0.16.1.dev202410010346__py3-none-any.whl

keras_hub/api/layers/__init__.py

@@ -46,6 +46,7 @@ from keras_hub.src.models.pali_gemma.pali_gemma_image_converter import (
 from keras_hub.src.models.resnet.resnet_image_converter import (
     ResNetImageConverter,
 )
+from keras_hub.src.models.sam.sam_image_converter import SAMImageConverter
 from keras_hub.src.models.sam.sam_mask_decoder import SAMMaskDecoder
 from keras_hub.src.models.sam.sam_prompt_encoder import SAMPromptEncoder
 from keras_hub.src.models.whisper.whisper_audio_converter import (

keras_hub/api/models/__init__.py

@@ -168,6 +168,9 @@ from keras_hub.src.models.image_classifier_preprocessor import (
     ImageClassifierPreprocessor,
 )
 from keras_hub.src.models.image_segmenter import ImageSegmenter
+from keras_hub.src.models.image_segmenter_preprocessor import (
+    ImageSegmenterPreprocessor,
+)
 from keras_hub.src.models.llama3.llama3_backbone import Llama3Backbone
 from keras_hub.src.models.llama3.llama3_causal_lm import Llama3CausalLM
 from keras_hub.src.models.llama3.llama3_causal_lm_preprocessor import (
@@ -250,6 +253,9 @@ from keras_hub.src.models.roberta.roberta_text_classifier_preprocessor import (
 from keras_hub.src.models.roberta.roberta_tokenizer import RobertaTokenizer
 from keras_hub.src.models.sam.sam_backbone import SAMBackbone
 from keras_hub.src.models.sam.sam_image_segmenter import SAMImageSegmenter
+from keras_hub.src.models.sam.sam_image_segmenter_preprocessor import (
+    SAMImageSegmenterPreprocessor as SamImageSegmenterPreprocessor,
+)
 from keras_hub.src.models.seq_2_seq_lm import Seq2SeqLM
 from keras_hub.src.models.seq_2_seq_lm_preprocessor import Seq2SeqLMPreprocessor
 from keras_hub.src.models.stable_diffusion_3.stable_diffusion_3_backbone import (

keras_hub/src/models/image_segmenter_preprocessor.py

@@ -0,0 +1,73 @@
+import keras
+
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.models.preprocessor import Preprocessor
+from keras_hub.src.utils.tensor_utils import preprocessing_function
+
+
+@keras_hub_export("keras_hub.models.ImageSegmenterPreprocessor")
+class ImageSegmenterPreprocessor(Preprocessor):
+    """Base class for image segmentation preprocessing layers.
+
+    `ImageSegmenterPreprocessor` wraps a
+    `keras_hub.layers.ImageConverter` to create a preprocessing layer for
+    image segmentation tasks. It is intended to be paired with a
+    `keras_hub.models.ImageSegmenter` task.
+
+    All `ImageSegmenterPreprocessor` instances take three inputs: `x`, `y`, and
+    `sample_weight`.
+
+    - `x`: The first input, should always be included. It can be an image or
+      a batch of images.
+    - `y`: (Optional) Usually the segmentation mask(s), will be passed through
+      unaltered.
+    - `sample_weight`: (Optional) Will be passed through unaltered.
+
+    The layer will output either `x`, an `(x, y)` tuple if labels were provided,
+    or an `(x, y, sample_weight)` tuple if labels and sample weight were
+    provided. `x` will be the input images after all model preprocessing has
+    been applied.
+
+    All `ImageSegmenterPreprocessor` tasks include a `from_preset()`
+    constructor which can be used to load a pre-trained config and vocabularies.
+    You can call the `from_preset()` constructor directly on this base class, in
+    which case the correct class for your model will be automatically
+    instantiated.
+
+    Examples.
+    ```python
+    preprocessor = keras_hub.models.ImageSegmenterPreprocessor.from_preset(
+        "deeplabv3_resnet50",
+    )
+
+    # Resize a single image for the model.
+    x = np.ones((512, 512, 3))
+    x = preprocessor(x)
+
+    # Resize an image and its mask.
+    x, y = np.ones((512, 512, 3)), np.zeros((512, 512, 1))
+    x, y = preprocessor(x, y)
+
+    # Resize a batch of images and masks.
+    x, y = [np.ones((512, 512, 3)), np.zeros((512, 512, 3))], [np.ones((512, 512, 1)), np.zeros((512, 512, 1))]
+    x, y = preprocessor(x, y)
+
+    # Use a `tf.data.Dataset`.
+    ds = tf.data.Dataset.from_tensor_slices((x, y)).batch(2)
+    ds = ds.map(preprocessor, num_parallel_calls=tf.data.AUTOTUNE)
+    ```
+    """
+
+    def __init__(
+        self,
+        image_converter=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.image_converter = image_converter
+
+    @preprocessing_function
+    def call(self, x, y=None, sample_weight=None):
+        if self.image_converter:
+            x = self.image_converter(x)
+        return keras.utils.pack_x_y_sample_weight(x, y, sample_weight)

keras_hub/src/models/llama/llama_backbone.py

@@ -90,13 +90,14 @@ class LlamaBackbone(Backbone):
         layer_norm_epsilon=1e-6,
         dropout=0,
         dtype=None,
+        tie_word_embeddings=False,
         **kwargs,
     ):
         # === Layers ===
         self.token_embedding = ReversibleEmbedding(
             input_dim=vocabulary_size,
             output_dim=hidden_dim,
-            tie_weights=False,
+            tie_weights=tie_word_embeddings,
             embeddings_initializer=_llama_kernel_initializer(stddev=0.01),
             dtype=dtype,
             name="token_embedding",
@@ -155,6 +156,7 @@ class LlamaBackbone(Backbone):
         self.rope_scaling_factor = rope_scaling_factor
         self.layer_norm_epsilon = layer_norm_epsilon
         self.dropout = dropout
+        self.tie_word_embeddings = tie_word_embeddings
 
     def get_config(self):
         config = super().get_config()

keras_hub/src/models/mix_transformer/mix_transformer_backbone.py

@@ -20,7 +20,7 @@ class MiTBackbone(FeaturePyramidBackbone):
         num_layers,
         blockwise_num_heads,
         blockwise_sr_ratios,
-        end_value,
+        max_drop_path_rate,
         patch_sizes,
         strides,
         image_shape=(None, None, 3),
@@ -45,7 +45,9 @@ class MiTBackbone(FeaturePyramidBackbone):
                 ratio to perform for each layer on the sequence before key and
                 value projections. If set to > 1, a `Conv2D` layer is used to
                 reduce the length of the sequence.
-            end_value: The end value of the sequence.
+            max_drop_path_rate: The final value of the `linspace()` that
+                defines the drop path rates for the `DropPath` layers of
+                the `HierarchicalTransformerEncoder` layers.
             image_shape: optional shape tuple, defaults to (None, None, 3).
             hidden_dims: the embedding dims per hierarchical layer, used as
                 the levels of the feature pyramid.
@@ -73,7 +75,7 @@ class MiTBackbone(FeaturePyramidBackbone):
         model.fit(images, labels, epochs=3)
         ```
         """
-        dpr = [x for x in np.linspace(0.0, end_value, sum(depths))]
+        dpr = [x for x in np.linspace(0.0, max_drop_path_rate, sum(depths))]
 
         # === Layers ===
         cur = 0
@@ -136,7 +138,7 @@ class MiTBackbone(FeaturePyramidBackbone):
         self.num_layers = num_layers
         self.blockwise_num_heads = blockwise_num_heads
         self.blockwise_sr_ratios = blockwise_sr_ratios
-        self.end_value = end_value
+        self.max_drop_path_rate = max_drop_path_rate
         self.patch_sizes = patch_sizes
         self.strides = strides
 
@@ -150,7 +152,7 @@ class MiTBackbone(FeaturePyramidBackbone):
                 "num_layers": self.num_layers,
                 "blockwise_num_heads": self.blockwise_num_heads,
                 "blockwise_sr_ratios": self.blockwise_sr_ratios,
-                "end_value": self.end_value,
+                "max_drop_path_rate": self.max_drop_path_rate,
                 "patch_sizes": self.patch_sizes,
                 "strides": self.strides,
             }

keras_hub/src/models/sam/sam_image_converter.py

@@ -0,0 +1,10 @@
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.layers.preprocessing.resizing_image_converter import (
+    ResizingImageConverter,
+)
+from keras_hub.src.models.sam.sam_backbone import SAMBackbone
+
+
+@keras_hub_export("keras_hub.layers.SAMImageConverter")
+class SAMImageConverter(ResizingImageConverter):
+    backbone_cls = SAMBackbone

keras_hub/src/models/sam/sam_image_segmenter.py

@@ -4,6 +4,9 @@ from keras import ops
 from keras_hub.src.api_export import keras_hub_export
 from keras_hub.src.models.image_segmenter import ImageSegmenter
 from keras_hub.src.models.sam.sam_backbone import SAMBackbone
+from keras_hub.src.models.sam.sam_image_segmenter_preprocessor import (
+    SAMImageSegmenterPreprocessor,
+)
 
 
 @keras_hub_export("keras_hub.models.SAMImageSegmenter")
@@ -165,7 +168,7 @@ class SAMImageSegmenter(ImageSegmenter):
     """
 
     backbone_cls = SAMBackbone
-    preprocessor_cls = None
+    preprocessor_cls = SAMImageSegmenterPreprocessor
 
     def __init__(self, backbone, preprocessor=None, **kwargs):
         # The implementation has been adapted form [Segment Anything
@@ -174,6 +177,7 @@ class SAMImageSegmenter(ImageSegmenter):
         # [Detectron2](https://github.com/facebookresearch/detectron2).
         # === Layers ===
         self.backbone = backbone
+        self.preprocessor = preprocessor
         # === Functional Model ===
         inputs = self.backbone.input
         x = self.backbone(inputs)

keras_hub/src/models/sam/sam_image_segmenter_preprocessor.py

@@ -0,0 +1,12 @@
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.models.image_segmenter_preprocessor import (
+    ImageSegmenterPreprocessor,
+)
+from keras_hub.src.models.sam.sam_backbone import SAMBackbone
+from keras_hub.src.models.sam.sam_image_converter import SAMImageConverter
+
+
+@keras_hub_export("keras_hub.models.SamImageSegmenterPreprocessor")
+class SAMImageSegmenterPreprocessor(ImageSegmenterPreprocessor):
+    backbone_cls = SAMBackbone
+    image_converter_cls = SAMImageConverter

keras_hub/src/models/sam/sam_presets.py

@@ -0,0 +1,34 @@
+"""SAM preset configurations."""
+
+backbone_presets = {
+    "sam_base_sa1b": {
+        "metadata": {
+            "description": ("The base SAM model trained on the SA1B dataset."),
+            "params": 93735728,
+            "official_name": "SAMImageSegmenter",
+            "path": "sam",
+            "model_card": "https://arxiv.org/abs/2304.02643",
+        },
+        "kaggle_handle": "kaggle://kerashub/sam/keras/sam_base_sa1b/1",
+    },
+    "sam_large_sa1b": {
+        "metadata": {
+            "description": ("The large SAM model trained on the SA1B dataset."),
+            "params": 641090864,
+            "official_name": "SAMImageSegmenter",
+            "path": "sam",
+            "model_card": "https://arxiv.org/abs/2304.02643",
+        },
+        "kaggle_handle": "kaggle://kerashub/sam/keras/sam_large_sa1b/1",
+    },
+    "sam_huge_sa1b": {
+        "metadata": {
+            "description": ("The huge SAM model trained on the SA1B dataset."),
+            "params": 312343088,
+            "official_name": "SAMImageSegmenter",
+            "path": "sam",
+            "model_card": "https://arxiv.org/abs/2304.02643",
+        },
+        "kaggle_handle": "kaggle://kerashub/sam/keras/sam_huge_sa1b/1",
+    },
+}

keras_hub/src/models/vit_det/vit_layers.py

@@ -212,7 +212,7 @@ class MultiHeadAttentionWithRelativePE(keras.layers.Layer):
                     "Input size must be provided if using relative "
                     "positional encoding."
                 )
-            self.add_decomposed_reative_pe = AddRelativePositionalEmbedding(
+            self.add_decomposed_relative_pe = AddRelativePositionalEmbedding(
                 self.input_size, self.key_dim
             )
 
@@ -241,7 +241,7 @@ class MultiHeadAttentionWithRelativePE(keras.layers.Layer):
             keys, axes=(0, 2, 1)
         )
         if self.use_rel_pos:
-            attention_map = self.add_decomposed_reative_pe(
+            attention_map = self.add_decomposed_relative_pe(
                 attention_map,
                 queries=queries,
                 query_size=(height, width),

keras_hub/src/utils/transformers/convert_llama3.py

@@ -14,6 +14,7 @@ def convert_backbone_config(transformers_config):
         "hidden_dim": transformers_config["hidden_size"],
         "intermediate_dim": transformers_config["intermediate_size"],
         "num_key_value_heads": transformers_config["num_key_value_heads"],
+        "tie_word_embeddings": transformers_config["tie_word_embeddings"],
     }
 
 
@@ -22,12 +23,15 @@ def convert_weights(backbone, loader, transformers_config):
         keras_variable=backbone.get_layer("token_embedding").embeddings,
         hf_weight_key="model.embed_tokens.weight",
     )
-    loader.port_weight(
-        keras_variable=backbone.get_layer("token_embedding").reverse_embeddings,
-        hf_weight_key="lm_head.weight",
-        # rearrange_pattern="b a -> a b",
-        hook_fn=lambda hf_tensor, _: np.transpose(hf_tensor, axes=(1, 0)),
-    )
+    if not backbone.tie_word_embeddings:
+        loader.port_weight(
+            keras_variable=backbone.get_layer(
+                "token_embedding"
+            ).reverse_embeddings,
+            hf_weight_key="lm_head.weight",
+            # rearrange_pattern="b a -> a b",
+            hook_fn=lambda hf_tensor, _: np.transpose(hf_tensor, axes=(1, 0)),
+        )
 
     def transpose_and_reshape(x, shape):
         return np.reshape(np.transpose(x), shape)

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__ = "0.16.1.dev202409290341"
+__version__ = "0.16.1.dev202410010346"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub_nightly-0.16.1.dev202409290341.dist-info → keras_hub_nightly-0.16.1.dev202410010346.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: keras-hub-nightly
-Version: 0.16.1.dev202409290341
+Version: 0.16.1.dev202410010346
 Summary: Industry-strength Natural Language Processing extensions for Keras.
 Home-page: https://github.com/keras-team/keras-hub
 Author: Keras team
@@ -83,13 +83,13 @@ We welcome contributions.
 
 ## Quickstart
 
-Fine-tune BERT on IMDb movie reviews:
+Fine-tune a BERT classifier on IMDb movie reviews:
 
 ```python
 import os
 os.environ["KERAS_BACKEND"] = "jax"  # Or "tensorflow" or "torch"!
 
-import keras_hub
+import keras_nlp
 import tensorflow_datasets as tfds
 
 imdb_train, imdb_test = tfds.load(
@@ -98,12 +98,14 @@ imdb_train, imdb_test = tfds.load(
     as_supervised=True,
     batch_size=16,
 )
+
 # Load a BERT model.
-classifier = keras_hub.models.Classifier.from_preset(
+classifier = keras_nlp.models.Classifier.from_preset(
     "bert_base_en",
     num_classes=2,
     activation="softmax",
 )
+
 # Fine-tune on IMDb movie reviews.
 classifier.fit(imdb_train, validation_data=imdb_test)
 # Predict two new examples.
@@ -116,21 +118,23 @@ For more in depth guides and examples, visit
 
 ## Installation
 
-To install the latest KerasHub release with Keras 3, simply run:
+KerasHub is currently in pre-release. Note that pre-release versions may
+introduce breaking changes to the API in future versions. For a stable and
+supported experience, we recommend installing `keras-nlp` version 0.15.1:
 
-```
-pip install --upgrade keras-hub
+```bash
+pip install keras-nlp==0.15.1
 ```
 
-To install the latest nightly changes for both KerasHub and Keras, you can use
-our nightly package.
+To try out the latest pre-release version of KerasHub, you can use
+our nightly package:
 
-```
-pip install --upgrade keras-hub-nightly
+```bash
+pip install keras-hub-nightly
 ```
 
-Note that currently, installing KerasHub will always pull in TensorFlow for use
-of the `tf.data` API for preprocessing. Even when pre-processing with `tf.data`,
+KerasHub currently requires TensorFlow to be installed for use of the
+`tf.data` API for preprocessing. Even when pre-processing with `tf.data`,
 training can still happen on any backend.
 
 Read [Getting started with Keras](https://keras.io/getting_started/) for more
@@ -160,15 +164,15 @@ import keras_hub
 ```
 
 > [!IMPORTANT]
-> Make sure to set the `KERAS_BACKEND` before import any Keras libraries, it
-> will be used to set up Keras when it is first imported.
+> Make sure to set the `KERAS_BACKEND` **before** importing any Keras libraries;
+> it will be used to set up Keras when it is first imported.
 
 ## Compatibility
 
 We follow [Semantic Versioning](https://semver.org/), and plan to
 provide backwards compatibility guarantees both for code and saved models built
 with our components. While we continue with pre-release `0.y.z` development, we
-may break compatibility at any time and APIs should not be consider stable.
+may break compatibility at any time and APIs should not be considered stable.
 
 ## Disclaimer
 

{keras_hub_nightly-0.16.1.dev202409290341.dist-info → keras_hub_nightly-0.16.1.dev202410010346.dist-info}/RECORD

@@ -1,15 +1,15 @@
 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=W42ptsnGJZ9x6I6jfaspKcrv4SSFLokschJDW9CofAM,2256
+keras_hub/api/layers/__init__.py,sha256=jX6K16_pDvfm8ScLsRnO5OoF91WpHda0SiOLGkoIGp4,2331
 keras_hub/api/metrics/__init__.py,sha256=So8Ec-lOcTzn_UUMmAdzDm8RKkPu2dbRUm2px8gpUEI,381
-keras_hub/api/models/__init__.py,sha256=71LtPajJXixbdH2BpslAoBoO0S8j64uZWnzZSXUP_0Q,13787
+keras_hub/api/models/__init__.py,sha256=mPLLdpHJ6AIOei9dFKImcIrHjXOm3-pHYiUZVA_ry0g,14027
 keras_hub/api/samplers/__init__.py,sha256=n-_SEXxr2LNUzK2FqVFN7alsrkx1P_HOVTeLZKeGCdE,730
 keras_hub/api/tokenizers/__init__.py,sha256=_f-r_cyUM2fjBB7iO84ThOdqqsAxHNIewJ2EBDlM0cA,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=GxYmS5YH-wnfPE281Ma_mqC_6TDvSlrBelngquLu2LQ,222
+keras_hub/src/version_utils.py,sha256=NH7d2eE6DNxa_SHZWLz69EGvzOJOo6uXftLERho96ps,222
 keras_hub/src/bounding_box/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/bounding_box/converters.py,sha256=a5po8DBm87oz2EXfi-0uEZHCMlCJPIb4-MaZIdYx3Dg,17865
 keras_hub/src/bounding_box/formats.py,sha256=YmskOz2BOSat7NaE__J9VfpSNGPJJR0znSzA4lp8MMI,3868
@@ -57,6 +57,7 @@ keras_hub/src/models/feature_pyramid_backbone.py,sha256=2Mh0G5y3CYjSyWqyw5X-NvtJ
 keras_hub/src/models/image_classifier.py,sha256=PFbuXXYDzryfvftsCJs2eLJ8IoSAwIbsMSiAW-zn-8M,3169
 keras_hub/src/models/image_classifier_preprocessor.py,sha256=BRAdFfK4oQ0TsvGDM-Dpjj38eV0xmpKdQwdnGZOvt_c,2614
 keras_hub/src/models/image_segmenter.py,sha256=OngkYiqvgs49Q-bNQ86TE1w_HYTorcgSg_mkmwbhO00,3014
+keras_hub/src/models/image_segmenter_preprocessor.py,sha256=vJoZc1OebQWlqUP_ygCS7P1Pyq1KmmUc-0V_-maDzX4,2658
 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/preprocessor.py,sha256=_hNy2qWRK_vcycS1eDB_Dz9r33T3eZ7dUwB85f7FzOs,8133
@@ -178,7 +179,7 @@ keras_hub/src/models/gpt_neo_x/gpt_neo_x_decoder.py,sha256=xSLDgavOhhm3SZc18VN60
 keras_hub/src/models/gpt_neo_x/gpt_neo_x_tokenizer.py,sha256=aKso-8yGrynn3tZ5xm2egcXIBQo3__sWZDBtjmS3ZgU,1991
 keras_hub/src/models/llama/__init__.py,sha256=svVZjGi71R3lVbq0AdbqlXj909mr3Rp9EPXdiO0w0G0,251
 keras_hub/src/models/llama/llama_attention.py,sha256=HzTWtvTjfN_j0vA9-ComstHpI81tzUrJU3RSSvSCaI4,7194
-keras_hub/src/models/llama/llama_backbone.py,sha256=cpBJD7dnCnfeBSAYPMGwR3gwewMr0oBNSQseUU6Pgao,6599
+keras_hub/src/models/llama/llama_backbone.py,sha256=6tkTvAwhFZjnHFIzQbUYlgByMt2qQE2F3sfBluVhON0,6703
 keras_hub/src/models/llama/llama_causal_lm.py,sha256=JyTiCt1mxvf6QNxhjCjAW-aopTL4teS1EHTb_K-RGrs,13109
 keras_hub/src/models/llama/llama_causal_lm_preprocessor.py,sha256=VTboOMiRBoxHrwP343upLUTsv3AG65r2H8h_PNPVphE,3047
 keras_hub/src/models/llama/llama_decoder.py,sha256=6iERIblED0ZB5w_EUlHks4UvMnsrWONdO_Xdz2OzhWM,8623
@@ -201,7 +202,7 @@ keras_hub/src/models/mistral/mistral_presets.py,sha256=gucgdaFAiU-vRDS1g9zWGHjbD
 keras_hub/src/models/mistral/mistral_tokenizer.py,sha256=wyzR_Y2XwrDiBV3jIeBChSPiaOkVVaxFuLxMH2F6EYA,2005
 keras_hub/src/models/mistral/mistral_transformer_decoder.py,sha256=RDIIB3FhneHZP11tNUFQT9DcWawCMnrtVxtSvtnP3ts,9542
 keras_hub/src/models/mix_transformer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-keras_hub/src/models/mix_transformer/mix_transformer_backbone.py,sha256=Uuuz7G9pwHIEVaJwpUJmRieFak8LvIg275hyvn34lh0,5841
+keras_hub/src/models/mix_transformer/mix_transformer_backbone.py,sha256=B4hdhWHZ93lS937BGSSxovDKVXQZVuWrMbFwECFoWrg,6048
 keras_hub/src/models/mix_transformer/mix_transformer_classifier.py,sha256=XF0RvdocC4CPOrIEStw1V9KQ8IKs09Ti3Dd4dbZteac,3692
 keras_hub/src/models/mix_transformer/mix_transformer_layers.py,sha256=SzyJJhuyESlsCgndmZNYuuF0Ogb1FKoYkSfDJnThgT0,9538
 keras_hub/src/models/mobilenet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -254,9 +255,12 @@ keras_hub/src/models/roberta/roberta_text_classifier_preprocessor.py,sha256=gAJa
 keras_hub/src/models/roberta/roberta_tokenizer.py,sha256=VKPrgXVT9aMKP7et2DIWKlTN8g4tIzjya0MHqNz9BwQ,2712
 keras_hub/src/models/sam/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/models/sam/sam_backbone.py,sha256=fbvtGG6du7tnkcGtEsRyT9TRwPBUJ99GBolGkWR5pkc,4351
-keras_hub/src/models/sam/sam_image_segmenter.py,sha256=Lt_RAC7tBxH85dnuSPJoavrvxes_kxXQiCyCOaQKApo,7505
+keras_hub/src/models/sam/sam_image_converter.py,sha256=Gr6OB-R3jXKjnWk_ndKEQLveIUj8NGKQ3vMG3tpBy9Y,358
+keras_hub/src/models/sam/sam_image_segmenter.py,sha256=gJ-O7XaSvn9KTI-QPguhAiGfvxLUBar-KVQ-EEH5kko,7680
+keras_hub/src/models/sam/sam_image_segmenter_preprocessor.py,sha256=lZynaWAAdHer3NZZ6YLymZ9h5x1D6dIMQDwmPp-JSc4,499
 keras_hub/src/models/sam/sam_layers.py,sha256=SE5e6tYc-lsIVfMp9khewvuA1jY-dEHQmLT00YUok4M,13862
 keras_hub/src/models/sam/sam_mask_decoder.py,sha256=9RfjoNL7GSY6I9LZ3ulUa5cIoYSPJNP4KnHvq16lnM4,9549
+keras_hub/src/models/sam/sam_presets.py,sha256=PYQrmhsNApgLO6CAOYPnd24IbFqztyJwrhkLT5bx1wk,1220
 keras_hub/src/models/sam/sam_prompt_encoder.py,sha256=2foB7900QbzQfZjBo335XYsdjmhOnVT8fKD1CubJNVE,11801
 keras_hub/src/models/sam/sam_transformer.py,sha256=L2bdxdc2RUF1juRZ0F0Z6r0gTva1sUwEdjItJmKKf6w,5730
 keras_hub/src/models/stable_diffusion_3/__init__.py,sha256=ZKYQuaRObyhKq8GVAHmoRvlXp6FpU8ChvutVCHyXKuc,343
@@ -281,7 +285,7 @@ keras_hub/src/models/vgg/vgg_backbone.py,sha256=rI8pAscWJlda9P9L6gcfROpAo461l3v3
 keras_hub/src/models/vgg/vgg_image_classifier.py,sha256=eRJiisvXhO6SK3FPO6aOdI8ipxabktyT9Dt03l-_uxw,3486
 keras_hub/src/models/vit_det/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/models/vit_det/vit_det_backbone.py,sha256=GzwHXAfttExqDaGU4R2LAvng1gzjuvO3HMqUPwNUy9g,7656
-keras_hub/src/models/vit_det/vit_layers.py,sha256=0DWLSHgEoz3lLPveOEIJ7cNmTCLfSE7p1W_JL2GxDDI,19850
+keras_hub/src/models/vit_det/vit_layers.py,sha256=oCKeUw5ckyUAGvmFPuxIiIAqgmC3uqh85LfZcgyh964,19852
 keras_hub/src/models/whisper/__init__.py,sha256=45vTF01_e-7VzD-zvXPw1NiA9SCgDE8w0cI-6peG9cA,263
 keras_hub/src/models/whisper/whisper_audio_converter.py,sha256=aXqQ6uPI9fBSjuYbo7bMr4C0avPh3iDwrVXHEJ7W_zo,8386
 keras_hub/src/models/whisper/whisper_backbone.py,sha256=5AwhulDC-ius9zJQNqWmOISXRv3hLMurRfnaaj_EXVQ,11514
@@ -342,12 +346,12 @@ keras_hub/src/utils/transformers/convert_bert.py,sha256=4gQqXCJzC9QWdLPDUAq741K8
 keras_hub/src/utils/transformers/convert_distilbert.py,sha256=SlfIRhSRk5c1ir2HGiDPiXa5XdOId_DbcnZO9lbwyZ8,6498
 keras_hub/src/utils/transformers/convert_gemma.py,sha256=ElCgwBpSN5Q7rV5PJawTsoytPzs5ZjuwoY60YAe8y_A,6533
 keras_hub/src/utils/transformers/convert_gpt2.py,sha256=HCeHN_-GiQJRxLCM9OCJJ1watPVpIBF8ujS8pGbBOWc,5703
-keras_hub/src/utils/transformers/convert_llama3.py,sha256=yy7dDtgNESP_W34JgIm5fdlbpybrCqmvB7vtwF_dy6c,4450
+keras_hub/src/utils/transformers/convert_llama3.py,sha256=QqsGS2rkQ5EBJUzhq06tJNU07BI7k7wAlUNzUgFEYhs,4620
 keras_hub/src/utils/transformers/convert_mistral.py,sha256=kVhN9h1ZFVhwkNW8p3wnS7eANJUXIsNy1RxWXy20Gqw,4760
 keras_hub/src/utils/transformers/convert_pali_gemma.py,sha256=B1leeDw96Yvu81hYumf66hIid07k5NLqoeWAJgPnaLs,10649
 keras_hub/src/utils/transformers/preset_loader.py,sha256=GS44hZUuGQCtzsyn8z44ZpHdftd3DFemwV2hx2bQa-U,2738
 keras_hub/src/utils/transformers/safetensor_utils.py,sha256=rPK-Uw1CG0DX0d_UAD-r2cG9fw8GI8bvAlrcXfQ9g4c,3323
-keras_hub_nightly-0.16.1.dev202409290341.dist-info/METADATA,sha256=x4KCDdTpn0-dCiiXij4SGFDFTt_e2WIBa0z3_8cUcnY,7310
-keras_hub_nightly-0.16.1.dev202409290341.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-keras_hub_nightly-0.16.1.dev202409290341.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub_nightly-0.16.1.dev202409290341.dist-info/RECORD,,
+keras_hub_nightly-0.16.1.dev202410010346.dist-info/METADATA,sha256=q_YCWBdg95yQvhaaHRaaLHxjh_zSBItI4TrdnUn0fvI,7458
+keras_hub_nightly-0.16.1.dev202410010346.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+keras_hub_nightly-0.16.1.dev202410010346.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
+keras_hub_nightly-0.16.1.dev202410010346.dist-info/RECORD,,