keras-hub-nightly 0.21.0.dev202504050402__py3-none-any.whl → 0.21.0.dev202504052235__py3-none-any.whl

keras_hub/api/layers/__init__.py

@@ -84,3 +84,6 @@ from keras_hub.src.models.vit.vit_image_converter import ViTImageConverter
 from keras_hub.src.models.whisper.whisper_audio_converter import (
     WhisperAudioConverter,
 )
+from keras_hub.src.models.xception.xception_image_converter import (
+    XceptionImageConverter,
+)

keras_hub/api/models/__init__.py

@@ -388,6 +388,13 @@ from keras_hub.src.models.vit.vit_image_classifier_preprocessor import (
 from keras_hub.src.models.vit_det.vit_det_backbone import ViTDetBackbone
 from keras_hub.src.models.whisper.whisper_backbone import WhisperBackbone
 from keras_hub.src.models.whisper.whisper_tokenizer import WhisperTokenizer
+from keras_hub.src.models.xception.xception_backbone import XceptionBackbone
+from keras_hub.src.models.xception.xception_image_classifier import (
+    XceptionImageClassifier,
+)
+from keras_hub.src.models.xception.xception_image_classifier_preprocessor import (
+    XceptionImageClassifierPreprocessor,
+)
 from keras_hub.src.models.xlm_roberta.xlm_roberta_backbone import (
     XLMRobertaBackbone,
 )

keras_hub/src/models/xception/__init__.py

@@ -0,0 +1,5 @@
+from keras_hub.src.models.xception.xception_backbone import XceptionBackbone
+from keras_hub.src.models.xception.xception_presets import backbone_presets
+from keras_hub.src.utils.preset_utils import register_presets
+
+register_presets(backbone_presets, XceptionBackbone)

keras_hub/src/models/xception/xception_backbone.py

@@ -0,0 +1,188 @@
+import functools
+
+from keras import layers
+
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.models.backbone import Backbone
+from keras_hub.src.utils.keras_utils import standardize_data_format
+
+
+@keras_hub_export("keras_hub.models.XceptionBackbone")
+class XceptionBackbone(Backbone):
+    """Xception core network with hyperparameters.
+
+    This class implements a Xception backbone as described in
+    [Xception: Deep Learning with Depthwise Separable Convolutions](https://arxiv.org/abs/1610.02357).
+
+    Most users will want the pretrained presets available with this model. If
+    you are creating a custom backbone, this model provides customizability
+    through the `stackwise_conv_filters` and `stackwise_pooling` arguments. This
+    backbone assumes the same basic structure as the original Xception mode:
+    * Residuals and pre-activation everywhere but the first and last block.
+    * Conv layers for the first block only, separable conv layers elsewhere.
+
+    Args:
+        stackwise_conv_filters: list of list of ints. Each outermost list
+            entry represents a block, and each innermost list entry a conv
+            layer. The integer value specifies the number of filters for the
+            conv layer.
+        stackwise_pooling: list of bools. A list of booleans per block, where
+            each entry is true if the block should includes a max pooling layer
+            and false if it should not.
+        image_shape: tuple. The input shape without the batch size.
+            Defaults to `(None, None, 3)`.
+        data_format: `None` or str. If specified, either `"channels_last"` or
+            `"channels_first"`. If unspecified, the Keras default will be used.
+        dtype: `None` or str or `keras.mixed_precision.DTypePolicy`. The dtype
+            to use for the model's computations and weights.
+
+    Examples:
+    ```python
+    input_data = np.random.uniform(0, 1, size=(2, 224, 224, 3))
+
+    # Pretrained Xception backbone.
+    model = keras_hub.models.Backbone.from_preset("xception_41_imagenet")
+    model(input_data)
+
+    # Randomly initialized Xception backbone with a custom config.
+    model = keras_hub.models.XceptionBackbone(
+        stackwise_conv_filters=[[32, 64], [64, 128], [256, 256]],
+        stackwise_pooling=[True, True, False],
+    )
+    model(input_data)
+    ```
+    """
+
+    def __init__(
+        self,
+        stackwise_conv_filters,
+        stackwise_pooling,
+        image_shape=(None, None, 3),
+        data_format=None,
+        dtype=None,
+        **kwargs,
+    ):
+        if len(stackwise_conv_filters) != len(stackwise_pooling):
+            raise ValueError("All stackwise args should have the same length.")
+
+        data_format = standardize_data_format(data_format)
+        channel_axis = -1 if data_format == "channels_last" else 1
+        num_blocks = len(stackwise_conv_filters)
+
+        # Layer shorcuts with common args.
+        norm = functools.partial(
+            layers.BatchNormalization,
+            axis=channel_axis,
+            dtype=dtype,
+        )
+        act = functools.partial(
+            layers.Activation,
+            activation="relu",
+            dtype=dtype,
+        )
+        conv = functools.partial(
+            layers.Conv2D,
+            kernel_size=(3, 3),
+            use_bias=False,
+            data_format=data_format,
+            dtype=dtype,
+        )
+        sep_conv = functools.partial(
+            layers.SeparableConv2D,
+            kernel_size=(3, 3),
+            padding="same",
+            use_bias=False,
+            data_format=data_format,
+            dtype=dtype,
+        )
+        point_conv = functools.partial(
+            layers.Conv2D,
+            kernel_size=(1, 1),
+            strides=(2, 2),
+            padding="same",
+            use_bias=False,
+            data_format=data_format,
+            dtype=dtype,
+        )
+        pool = functools.partial(
+            layers.MaxPool2D,
+            pool_size=(3, 3),
+            strides=(2, 2),
+            padding="same",
+            data_format=data_format,
+            dtype=dtype,
+        )
+
+        # === Functional Model ===
+        image_input = layers.Input(shape=image_shape)
+        x = image_input  # Intermediate result.
+
+        # Iterate through the blocks.
+        for block_i in range(num_blocks):
+            first_block, last_block = block_i == 0, block_i == num_blocks - 1
+            block_filters = stackwise_conv_filters[block_i]
+            use_pooling = stackwise_pooling[block_i]
+
+            # Save the block input as a residual.
+            residual = x
+            for conv_i, filters in enumerate(block_filters):
+                # First block has post activation and strides on first conv.
+                if first_block:
+                    prefix = f"block{block_i + 1}_conv{conv_i + 1}"
+                    strides = (2, 2) if conv_i == 0 else (1, 1)
+                    x = conv(filters, strides=strides, name=prefix)(x)
+                    x = norm(name=f"{prefix}_bn")(x)
+                    x = act(name=f"{prefix}_act")(x)
+                # Last block has post activation.
+                elif last_block:
+                    prefix = f"block{block_i + 1}_sepconv{conv_i + 1}"
+                    x = sep_conv(filters, name=prefix)(x)
+                    x = norm(name=f"{prefix}_bn")(x)
+                    x = act(name=f"{prefix}_act")(x)
+                else:
+                    prefix = f"block{block_i + 1}_sepconv{conv_i + 1}"
+                    # The first conv in second block has no activation.
+                    if block_i != 1 or conv_i != 0:
+                        x = act(name=f"{prefix}_act")(x)
+                    x = sep_conv(filters, name=prefix)(x)
+                    x = norm(name=f"{prefix}_bn")(x)
+
+            # Optional block pooling.
+            if use_pooling:
+                x = pool(name=f"block{block_i + 1}_pool")(x)
+
+            # Sum residual, first and last block do not have a residual.
+            if not first_block and not last_block:
+                prefix = f"block{block_i + 1}_residual"
+                filters = x.shape[channel_axis]
+                # Match filters with a pointwise conv if needed.
+                if filters != residual.shape[channel_axis]:
+                    residual = point_conv(filters, name=f"{prefix}_conv")(
+                        residual
+                    )
+                    residual = norm(name=f"{prefix}_bn")(residual)
+                x = layers.Add(name=f"{prefix}_add", dtype=dtype)([x, residual])
+
+        super().__init__(
+            inputs=image_input,
+            outputs=x,
+            dtype=dtype,
+            **kwargs,
+        )
+
+        # === Config ===
+        self.stackwise_conv_filters = stackwise_conv_filters
+        self.stackwise_pooling = stackwise_pooling
+        self.image_shape = image_shape
+        self.data_format = data_format
+
+    def get_config(self):
+        config = super().get_config()
+        config.update(
+            {
+                "stackwise_conv_filters": self.stackwise_conv_filters,
+                "stackwise_pooling": self.stackwise_pooling,
+                "image_shape": self.image_shape,
+            }
+        )
+        return config

keras_hub/src/models/xception/xception_image_classifier.py

@@ -0,0 +1,12 @@
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.models.image_classifier import ImageClassifier
+from keras_hub.src.models.xception.xception_backbone import XceptionBackbone
+from keras_hub.src.models.xception.xception_image_classifier_preprocessor import (  # noqa: E501
+    XceptionImageClassifierPreprocessor,
+)
+
+
+@keras_hub_export("keras_hub.models.XceptionImageClassifier")
+class XceptionImageClassifier(ImageClassifier):
+    backbone_cls = XceptionBackbone
+    preprocessor_cls = XceptionImageClassifierPreprocessor

keras_hub/src/models/xception/xception_image_classifier_preprocessor.py

@@ -0,0 +1,14 @@
+from keras_hub.src.api_export import keras_hub_export
+from keras_hub.src.models.image_classifier_preprocessor import (
+    ImageClassifierPreprocessor,
+)
+from keras_hub.src.models.xception.xception_backbone import XceptionBackbone
+from keras_hub.src.models.xception.xception_image_converter import (
+    XceptionImageConverter,
+)
+
+
+@keras_hub_export("keras_hub.models.XceptionImageClassifierPreprocessor")
+class XceptionImageClassifierPreprocessor(ImageClassifierPreprocessor):
+    backbone_cls = XceptionBackbone
+    image_converter_cls = XceptionImageConverter

keras_hub/src/models/xception/xception_image_converter.py

@@ -0,0 +1,8 @@
+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.xception.xception_backbone import XceptionBackbone
+
+
+@keras_hub_export("keras_hub.layers.XceptionImageConverter")
+class XceptionImageConverter(ImageConverter):
+    backbone_cls = XceptionBackbone

keras_hub/src/models/xception/xception_presets.py

@@ -0,0 +1,14 @@
+"""Xception preset configurations."""
+
+backbone_presets = {
+    "xception_41_imagenet": {
+        "metadata": {
+            "description": (
+                "41-layer Xception model pre-trained on ImageNet 1k."
+            ),
+            "params": 20861480,
+            "path": "xception",
+        },
+        "kaggle_handle": "kaggle://keras/xception/keras/xception_41_imagenet/2",
+    },
+}

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__ = "0.21.0.dev202504050402"
+__version__ = "0.21.0.dev202504052235"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub_nightly-0.21.0.dev202504050402.dist-info → keras_hub_nightly-0.21.0.dev202504052235.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: keras-hub-nightly
-Version: 0.21.0.dev202504050402
+Version: 0.21.0.dev202504052235
 Summary: Industry-strength Natural Language Processing extensions for Keras.
 Home-page: https://github.com/keras-team/keras-hub
 Author: Keras team

{keras_hub_nightly-0.21.0.dev202504050402.dist-info → keras_hub_nightly-0.21.0.dev202504052235.dist-info}/RECORD

@@ -1,14 +1,14 @@
 keras_hub/__init__.py,sha256=QGdXyHgYt6cMUAP1ebxwc6oR86dE0dkMxNy2eOCQtFo,855
 keras_hub/api/__init__.py,sha256=EzR6D-XWsm_gDrX5LDwKEmrah_gu3ffpj8GKBudE0yI,485
-keras_hub/api/layers/__init__.py,sha256=cALDY20DHCVjJDKCD84zHvTZtAgz0xEvozk7a3Cl1Uk,3719
+keras_hub/api/layers/__init__.py,sha256=MXQbQ0PpkDDRmP7A38aHjF6V2WilFlOxqUx4psoyvFo,3818
 keras_hub/api/metrics/__init__.py,sha256=So8Ec-lOcTzn_UUMmAdzDm8RKkPu2dbRUm2px8gpUEI,381
-keras_hub/api/models/__init__.py,sha256=BLjx4I78cZNGdglXXYHznEiqReWGfvLJ4Xz6w5cMABI,18756
+keras_hub/api/models/__init__.py,sha256=Um3TlN6BfFBC2kLJvAbiQ3PwUaZk0yhq4yQWttxsH1o,19060
 keras_hub/api/samplers/__init__.py,sha256=n-_SEXxr2LNUzK2FqVFN7alsrkx1P_HOVTeLZKeGCdE,730
 keras_hub/api/tokenizers/__init__.py,sha256=ZMrudLg7bR9_ZoXJbiUEU3J6NHBqFRjKqLlfGrIWewo,2766
 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=RCbKMUr0xas-X7UNI-DRIHc-4euw6AeQrku4ibslufk,222
+keras_hub/src/version_utils.py,sha256=Mqk6lNzlQbwKMGLbz6F3S17Wyh3dAXGdlQWnfve5138,222
 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
@@ -396,6 +396,12 @@ keras_hub/src/models/whisper/whisper_decoder.py,sha256=rx9tFiXyGPnu_CScG8t8_7TVC
 keras_hub/src/models/whisper/whisper_encoder.py,sha256=ZJ93D6mP95Mb9cFDZbfMWbB9FlrV3706ZsUwUJMKOdg,3730
 keras_hub/src/models/whisper/whisper_presets.py,sha256=T1koXMeU-S3WCs10oTXIScVvn_4DoB6ah-EkqQLnVKI,3898
 keras_hub/src/models/whisper/whisper_tokenizer.py,sha256=HcF3PMoaLm-bNH9J_mG_iCBWGtJO6ahCRGAjjCptQOs,5575
+keras_hub/src/models/xception/__init__.py,sha256=Q7rwxGiBNrbKuteTF6LepeyCTEPQf-s7AzxGsWqJxdI,269
+keras_hub/src/models/xception/xception_backbone.py,sha256=oSLEZYqOUEFnTyU-81oqZlL6ENcShJN6rJAnr0IKOds,7208
+keras_hub/src/models/xception/xception_image_classifier.py,sha256=dpTD3nnUFaqONL5eU7Mz6lj883l30DlcBFyNkUGLtqY,544
+keras_hub/src/models/xception/xception_image_classifier_preprocessor.py,sha256=bHqPuNyrJEVvhSSBrlpXvztJDbU0kv7JFWpT4W46OS0,563
+keras_hub/src/models/xception/xception_image_converter.py,sha256=eM1gi48RK2-3UW9qgqNpL3OBB14UDOgQUw3HPs_Jiyg,354
+keras_hub/src/models/xception/xception_presets.py,sha256=UUBt_0AN5n0fSVUVNXyuk5KVx5nLDtdu10K0tdox4Ec,391
 keras_hub/src/models/xlm_roberta/__init__.py,sha256=iiCNSvDxPXZdxDyQKRxSLp5qzSpTuodL2TlHfwfqQjQ,303
 keras_hub/src/models/xlm_roberta/xlm_roberta_backbone.py,sha256=x7wSDya7M4qcmzAwskd6qx9avSQs8mWhvAMWS4hnpFY,2922
 keras_hub/src/models/xlm_roberta/xlm_roberta_masked_lm.py,sha256=PTxsd3DSxciKL6ub4hRHXbusx7tFnIBj_pFJXPJu8zQ,4392
@@ -459,7 +465,7 @@ keras_hub/src/utils/transformers/convert_qwen.py,sha256=I2bfwo8AQd_JfwFpiAuCQ3k_
 keras_hub/src/utils/transformers/convert_vit.py,sha256=9SUZ9utNJhW_5cj3acMn9cRy47u2eIcDsrhmzj77o9k,5187
 keras_hub/src/utils/transformers/preset_loader.py,sha256=0Hi7R8HnATcwFVLsJwMMIMWTCXHNfep4IPiRpQXqM-w,3933
 keras_hub/src/utils/transformers/safetensor_utils.py,sha256=CYUHyA4y-B61r7NDnCsFb4t_UmSwZ1k9L-8gzEd6KRg,3339
-keras_hub_nightly-0.21.0.dev202504050402.dist-info/METADATA,sha256=msea5aMQEK0-skeASoimO1KJSlb7uuQVnkx4rIZaAmo,7715
-keras_hub_nightly-0.21.0.dev202504050402.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-keras_hub_nightly-0.21.0.dev202504050402.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub_nightly-0.21.0.dev202504050402.dist-info/RECORD,,
+keras_hub_nightly-0.21.0.dev202504052235.dist-info/METADATA,sha256=YA8wftAkMAfM3SUAwFg2jIkVQD4LN3Mfr8yYeXbVntE,7715
+keras_hub_nightly-0.21.0.dev202504052235.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+keras_hub_nightly-0.21.0.dev202504052235.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
+keras_hub_nightly-0.21.0.dev202504052235.dist-info/RECORD,,