keras-hub-nightly 0.21.0.dev202505060405__py3-none-any.whl → 0.21.0.dev202505080407__py3-none-any.whl

keras_hub/src/models/cspnet/cspnet_backbone.py

@@ -81,7 +81,7 @@ class CSPNetBackbone(FeaturePyramidBackbone):
 
     # Pretrained backbone
     model = keras_hub.models.CSPNetBackbone.from_preset(
-        "cspdarknet53_ra_imagenet"
+        "csp_darknet_53_ra_imagenet"
     )
     model(input_data)
 
@@ -357,18 +357,6 @@ def bottleneck_block(
             dtype=dtype,
             name=f"{name}_bottleneck_block_bn_3",
         )(x)
-        if activation == "leaky_relu":
-            x = layers.LeakyReLU(
-                negative_slope=0.01,
-                dtype=dtype,
-                name=f"{name}_bottleneck_block_activation_3",
-            )(x)
-        else:
-            x = layers.Activation(
-                activation,
-                dtype=dtype,
-                name=f"{name}_bottleneck_block_activation_3",
-            )(x)
 
         x = layers.add(
             [x, shortcut], dtype=dtype, name=f"{name}_bottleneck_block_add"
@@ -673,6 +661,13 @@ def cross_stage(
                         name=f"{name}_csp_activation_1",
                     )(x)
             else:
+                if strides > 1:
+                    x = layers.ZeroPadding2D(
+                        1,
+                        data_format=data_format,
+                        dtype=dtype,
+                        name=f"{name}_csp_conv_pad_1",
+                    )(x)
                 x = layers.Conv2D(
                     filters=down_chs,
                     kernel_size=3,
@@ -882,6 +877,13 @@ def cross_stage3(
                         name=f"{name}_cs3_activation_1",
                     )(x)
             else:
+                if strides > 1:
+                    x = layers.ZeroPadding2D(
+                        1,
+                        data_format=data_format,
+                        dtype=dtype,
+                        name=f"{name}_cs3_conv_pad_1",
+                    )(x)
                 x = layers.Conv2D(
                     filters=down_chs,
                     kernel_size=3,
@@ -1062,6 +1064,13 @@ def dark_stage(
                     name=f"{name}_dark_activation_1",
                 )(x)
         else:
+            if strides > 1:
+                x = layers.ZeroPadding2D(
+                    1,
+                    data_format=data_format,
+                    dtype=dtype,
+                    name=f"{name}_dark_conv_pad_1",
+                )(x)
             x = layers.Conv2D(
                 filters=filters,
                 kernel_size=3,
@@ -1091,18 +1100,18 @@ def dark_stage(
                     dtype=dtype,
                     name=f"{name}_dark_activation_1",
                 )(x)
-            for i in range(depth):
-                x = block_fn(
-                    filters=block_channels,
-                    dilation=dilation,
-                    bottle_ratio=bottle_ratio,
-                    groups=groups,
-                    activation=activation,
-                    data_format=data_format,
-                    channel_axis=channel_axis,
-                    dtype=dtype,
-                    name=f"{name}_block_{i}",
-                )(x)
+        for i in range(depth):
+            x = block_fn(
+                filters=block_channels,
+                dilation=dilation,
+                bottle_ratio=bottle_ratio,
+                groups=groups,
+                activation=activation,
+                data_format=data_format,
+                channel_axis=channel_axis,
+                dtype=dtype,
+                name=f"{name}_block_{i}",
+            )(x)
         return x
 
     return apply
@@ -1135,6 +1144,13 @@ def create_csp_stem(
                 or (i == last_idx and strides > 2 and not pooling)
                 else 1
             )
+            if conv_strides > 1:
+                x = layers.ZeroPadding2D(
+                    (kernel_size - 1) // 2,
+                    data_format=data_format,
+                    dtype=dtype,
+                    name=f"csp_stem_pad_{i}",
+                )(x)
             x = layers.Conv2D(
                 filters=chs,
                 kernel_size=kernel_size,
@@ -1167,10 +1183,19 @@ def create_csp_stem(
 
         if pooling == "max":
             assert strides > 2
+            # Use manual padding to handle edge case scenario to ignore zero's
+            # as max value instead consider negative values from Leaky Relu type
+            # of activations.
+            pad_width = [[1, 1], [1, 1]]
+            if data_format == "channels_last":
+                pad_width += [[0, 0]]
+            else:
+                pad_width = [[0, 0]] + pad_width
+            pad_width = [[0, 0]] + pad_width
+            x = ops.pad(x, pad_width=pad_width, constant_values=float("-inf"))
             x = layers.MaxPooling2D(
                 pool_size=3,
                 strides=2,
-                padding="same",
                 data_format=data_format,
                 dtype=dtype,
                 name="csp_stem_pool",

keras_hub/src/models/cspnet/cspnet_presets.py

@@ -6,11 +6,46 @@ backbone_presets = {
             "description": (
                 "A CSP-DarkNet (Cross-Stage-Partial) image classification model"
                 " pre-trained on the Randomly Augmented ImageNet 1k dataset at "
-                "a 224x224 resolution."
+                "a 256x256 resolution."
             ),
-            "params": 26652512,
+            "params": 27642184,
             "path": "cspnet",
         },
-        "kaggle_handle": "kaggle://keras/cspdarknet/keras/csp_darknet_53_ra_imagenet/1",
+        "kaggle_handle": "kaggle://keras/cspdarknet/keras/csp_darknet_53_ra_imagenet/2",
+    },
+    "csp_resnext_50_ra_imagenet": {
+        "metadata": {
+            "description": (
+                "A CSP-ResNeXt (Cross-Stage-Partial) image classification model"
+                " pre-trained on the Randomly Augmented ImageNet 1k dataset at "
+                "a 256x256 resolution."
+            ),
+            "params": 20569896,
+            "path": "cspnet",
+        },
+        "kaggle_handle": "kaggle://keras/cspdarknet/keras/csp_resnext_50_ra_imagenet/1",
+    },
+    "csp_resnet_50_ra_imagenet": {
+        "metadata": {
+            "description": (
+                "A CSP-ResNet (Cross-Stage-Partial) image classification model"
+                " pre-trained on the Randomly Augmented ImageNet 1k dataset at "
+                "a 256x256 resolution."
+            ),
+            "params": 21616168,
+            "path": "cspnet",
+        },
+        "kaggle_handle": "kaggle://keras/cspdarknet/keras/csp_resnet_50_ra_imagenet/1",
+    },
+    "darknet_53_imagenet": {
+        "metadata": {
+            "description": (
+                "A DarkNet image classification model pre-trained on the"
+                "ImageNet 1k dataset at a 256x256 resolution."
+            ),
+            "params": 41609928,
+            "path": "cspnet",
+        },
+        "kaggle_handle": "kaggle://keras/cspdarknet/keras/darknet_53_imagenet/1",
     },
 }

keras_hub/src/models/segformer/segformer_image_segmenter_preprocessor.py

@@ -1,5 +1,3 @@
-import keras
-
 from keras_hub.src.api_export import keras_hub_export
 from keras_hub.src.models.image_segmenter_preprocessor import (
     ImageSegmenterPreprocessor,
@@ -8,25 +6,9 @@ from keras_hub.src.models.segformer.segformer_backbone import SegFormerBackbone
 from keras_hub.src.models.segformer.segformer_image_converter import (
     SegFormerImageConverter,
 )
-from keras_hub.src.utils.tensor_utils import preprocessing_function
-
-IMAGENET_DEFAULT_MEAN = [0.485, 0.456, 0.406]
-IMAGENET_DEFAULT_STD = [0.229, 0.224, 0.225]
 
 
 @keras_hub_export("keras_hub.models.SegFormerImageSegmenterPreprocessor")
 class SegFormerImageSegmenterPreprocessor(ImageSegmenterPreprocessor):
     backbone_cls = SegFormerBackbone
     image_converter_cls = SegFormerImageConverter
-
-    @preprocessing_function
-    def call(self, x, y=None, sample_weight=None):
-        if self.image_converter:
-            x = self.image_converter(x)
-            if y is not None:
-                y = self.image_converter(y)
-
-        x = x / 255
-        x = (x - IMAGENET_DEFAULT_MEAN) / IMAGENET_DEFAULT_STD
-
-        return keras.utils.pack_x_y_sample_weight(x, y, sample_weight)

keras_hub/src/models/segformer/segformer_presets.py

@@ -10,7 +10,7 @@ presets = {
             "params": 3719027,
             "path": "segformer_b0",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b0_ade20k_512/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b0_ade20k_512/3",
     },
     "segformer_b1_ade20k_512": {
         "metadata": {
@@ -21,7 +21,7 @@ presets = {
             "params": 13682643,
             "path": "segformer_b1",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b1_ade20k_512/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b1_ade20k_512/5",
     },
     "segformer_b2_ade20k_512": {
         "metadata": {
@@ -32,7 +32,7 @@ presets = {
             "params": 24727507,
             "path": "segformer_b2",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b2_ade20k_512/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b2_ade20k_512/3",
     },
     "segformer_b3_ade20k_512": {
         "metadata": {
@@ -43,7 +43,7 @@ presets = {
             "params": 44603347,
             "path": "segformer_b3",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b3_ade20k_512/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b3_ade20k_512/3",
     },
     "segformer_b4_ade20k_512": {
         "metadata": {
@@ -54,7 +54,7 @@ presets = {
             "params": 61373907,
             "path": "segformer_b4",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b4_ade20k_512/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b4_ade20k_512/3",
     },
     "segformer_b5_ade20k_640": {
         "metadata": {
@@ -65,7 +65,7 @@ presets = {
             "params": 81974227,
             "path": "segformer_b5",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b5_ade20k_640/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b5_ade20k_640/3",
     },
     "segformer_b0_cityscapes_1024": {
         "metadata": {
@@ -76,7 +76,7 @@ presets = {
             "params": 3719027,
             "path": "segformer_b0",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b0_cityscapes_1024/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b0_cityscapes_1024/3",
     },
     "segformer_b1_cityscapes_1024": {
         "metadata": {
@@ -87,7 +87,7 @@ presets = {
             "params": 13682643,
             "path": "segformer_b1",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b1_ade20k_512/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b1_ade20k_512/1",
     },
     "segformer_b2_cityscapes_1024": {
         "metadata": {
@@ -98,7 +98,7 @@ presets = {
             "params": 24727507,
             "path": "segformer_b2",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b2_cityscapes_1024/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b2_cityscapes_1024/3",
     },
     "segformer_b3_cityscapes_1024": {
         "metadata": {
@@ -109,7 +109,7 @@ presets = {
             "params": 44603347,
             "path": "segformer_b3",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b3_cityscapes_1024/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b3_cityscapes_1024/3",
     },
     "segformer_b4_cityscapes_1024": {
         "metadata": {
@@ -120,7 +120,7 @@ presets = {
             "params": 61373907,
             "path": "segformer_b4",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b4_cityscapes_1024/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b4_cityscapes_1024/3",
     },
     "segformer_b5_cityscapes_1024": {
         "metadata": {
@@ -131,6 +131,6 @@ presets = {
             "params": 81974227,
             "path": "segformer_b5",
         },
-        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b5_cityscapes_1024/2",
+        "kaggle_handle": "kaggle://keras/segformer/keras/segformer_b5_cityscapes_1024/3",
     },
 }

keras_hub/src/utils/timm/convert_cspnet.py

@@ -17,10 +17,69 @@ def convert_backbone_config(timm_config):
         bottle_ratio = (0.5,) + (1.0,)
         block_ratio = (1.0,) + (0.5,)
         expand_ratio = (2.0,) + (1.0,)
+        stem_padding = "same"
+        stem_pooling = None
         stage_type = "csp"
+        groups = 1
         block_type = "dark_block"
         down_growth = True
-        stackwise_strides = 2
+        stackwise_strides = [2, 2, 2, 2, 2]
+        avg_down = False
+        cross_linear = False
+    elif timm_architecture == "cspresnet50":
+        stem_filters = 64
+        stem_kernel_size = 7
+        stem_strides = 4
+        stackwise_depth = [3, 3, 5, 2]
+        stackwise_strides = [1, 2, 2, 2]
+        stackwise_num_filters = [128, 256, 512, 1024]
+        block_type = "bottleneck_block"
+        stage_type = "csp"
+        bottle_ratio = [0.5]
+        block_ratio = [1.0]
+        expand_ratio = [2.0]
+        stem_padding = "valid"
+        stem_pooling = "max"
+        avg_down = False
+        groups = 1
+        down_growth = False
+        cross_linear = True
+    elif timm_architecture == "cspresnext50":
+        stem_filters = 64
+        stem_kernel_size = 7
+        stem_strides = 4
+        stackwise_depth = [3, 3, 5, 2]
+        stackwise_num_filters = [256, 512, 1024, 2048]
+        bottle_ratio = [1.0]
+        block_ratio = [0.5]
+        expand_ratio = [1.0]
+        stage_type = "csp"
+        block_type = "bottleneck_block"
+        stem_pooling = "max"
+        stackwise_strides = [1, 2, 2, 2]
+        groups = 32
+        stem_padding = "valid"
+        avg_down = False
+        down_growth = False
+        cross_linear = True
+    elif timm_architecture == "darknet53":
+        stem_filters = 32
+        stem_kernel_size = 3
+        stem_strides = 1
+        stackwise_depth = [1, 2, 8, 8, 4]
+        stackwise_num_filters = [64, 128, 256, 512, 1024]
+        bottle_ratio = [0.5]
+        block_ratio = [1.0]
+        groups = 1
+        expand_ratio = [1.0]
+        stage_type = "dark"
+        block_type = "dark_block"
+        stem_pooling = None
+        stackwise_strides = [2, 2, 2, 2, 2]
+        stem_padding = "same"
+        avg_down = False
+        down_growth = False
+        cross_linear = False
     else:
         raise ValueError(
             f"Currently, the architecture {timm_architecture} is not supported."
@@ -38,6 +97,11 @@ def convert_backbone_config(timm_config):
         block_type=block_type,
         stackwise_strides=stackwise_strides,
         down_growth=down_growth,
+        stem_pooling=stem_pooling,
+        stem_padding=stem_padding,
+        avg_down=avg_down,
+        cross_linear=cross_linear,
+        groups=groups,
     )
 
 
@@ -81,21 +145,36 @@ def convert_weights(backbone, loader, timm_config):
     stackwise_depth = backbone.stackwise_depth
     stage_type = backbone.stage_type
     block_type = backbone.block_type
+    strides = backbone.stackwise_strides
 
     for idx, block in enumerate(stackwise_depth):
-        port_conv2d(
-            f"stages.{idx}.conv_down.conv",
-            f"stage_{idx}_{stage_type}_conv_down_1",
-        )
-        port_batch_normalization(
-            f"stages.{idx}.conv_down.bn", f"stage_{idx}_{stage_type}_bn_1"
-        )
-        port_conv2d(
-            f"stages.{idx}.conv_exp.conv", f"stage_{idx}_{stage_type}_conv_exp"
-        )
-        port_batch_normalization(
-            f"stages.{idx}.conv_exp.bn", f"stage_{idx}_{stage_type}_bn_2"
-        )
+        if strides[idx] != 1 or stage_type == "dark":
+            if strides[idx] == 2 and backbone.avg_down:
+                port_conv2d(
+                    f"stages.{idx}.conv_down.1.conv",
+                    f"stage_{idx}_{stage_type}_conv_down_1",
+                )
+                port_batch_normalization(
+                    f"stages.{idx}.conv_down.1.bn",
+                    f"stage_{idx}_{stage_type}_bn_1",
+                )
+            else:
+                port_conv2d(
+                    f"stages.{idx}.conv_down.conv",
+                    f"stage_{idx}_{stage_type}_conv_down_1",
+                )
+                port_batch_normalization(
+                    f"stages.{idx}.conv_down.bn",
+                    f"stage_{idx}_{stage_type}_bn_1",
+                )
+        if stage_type != "dark":
+            port_conv2d(
+                f"stages.{idx}.conv_exp.conv",
+                f"stage_{idx}_{stage_type}_conv_exp",
+            )
+            port_batch_normalization(
+                f"stages.{idx}.conv_exp.bn", f"stage_{idx}_{stage_type}_bn_2"
+            )
 
         for i in range(block):
             port_conv2d(
@@ -133,16 +212,8 @@ def convert_weights(backbone, loader, timm_config):
                 f"stages.{idx}.conv_transition_b.bn",
                 f"stage_{idx}_{stage_type}_transition_b_bn",
             )
-            port_conv2d(
-                f"stages.{idx}.conv_transition.conv",
-                f"stage_{idx}_{stage_type}_conv_transition",
-            )
-            port_batch_normalization(
-                f"stages.{idx}.conv_transition.bn",
-                f"stage_{idx}_{stage_type}_transition_bn",
-            )
 
-        else:
+        if stage_type != "dark":
             port_conv2d(
                 f"stages.{idx}.conv_transition.conv",
                 f"stage_{idx}_{stage_type}_conv_transition",

keras_hub/src/utils/timm/preset_loader.py

@@ -16,17 +16,17 @@ class TimmPresetLoader(PresetLoader):
     def __init__(self, preset, config):
         super().__init__(preset, config)
         architecture = self.config["architecture"]
-        if "resnet" in architecture:
+        if architecture.startswith("resnet"):
             self.converter = convert_resnet
-        elif "csp" in architecture:
+        elif architecture.startswith(("csp", "dark")):
             self.converter = convert_cspnet
-        elif "densenet" in architecture:
+        elif architecture.startswith("densenet"):
             self.converter = convert_densenet
-        elif "mobilenet" in architecture:
+        elif architecture.startswith("mobilenet"):
             self.converter = convert_mobilenet
-        elif "vgg" in architecture:
+        elif architecture.startswith("vgg"):
             self.converter = convert_vgg
-        elif "efficientnet" in architecture:
+        elif architecture.startswith("efficientnet"):
             self.converter = convert_efficientnet
         else:
             raise ValueError(

keras_hub/src/utils/transformers/convert_mixtral.py

@@ -50,19 +50,19 @@ def convert_weights(backbone, loader, transformers_config):
         # Attention layers
         ## Query
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._query_dense.kernel,
+            keras_variable=decoder_layer._self_attention_layer.query_dense.kernel,
             hf_weight_key=f"model.layers.{i}.self_attn.q_proj.weight",
             hook_fn=transpose_and_reshape,
         )
         ## Key
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._key_dense.kernel,
+            keras_variable=decoder_layer._self_attention_layer.key_dense.kernel,
             hf_weight_key=f"model.layers.{i}.self_attn.k_proj.weight",
             hook_fn=transpose_and_reshape,
         )
         ## Value
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._value_dense.kernel,
+            keras_variable=decoder_layer._self_attention_layer.value_dense.kernel,
             hf_weight_key=f"model.layers.{i}.self_attn.v_proj.weight",
             hook_fn=transpose_and_reshape,
         )

keras_hub/src/utils/transformers/convert_qwen_moe.py

@@ -64,34 +64,34 @@ def convert_weights(backbone, loader, transformers_config):
 
         ## Query
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._query_dense.kernel,
+            keras_variable=decoder_layer._self_attention_layer.query_dense.kernel,
             hf_weight_key=f"model.layers.{i}.self_attn.q_proj.weight",
             hook_fn=transpose_and_reshape,
         )
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._query_dense.bias,
+            keras_variable=decoder_layer._self_attention_layer.query_dense.bias,
             hf_weight_key=f"model.layers.{i}.self_attn.q_proj.bias",
             hook_fn=transpose_and_reshape,
         )
         ## Key
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._key_dense.kernel,
+            keras_variable=decoder_layer._self_attention_layer.key_dense.kernel,
             hf_weight_key=f"model.layers.{i}.self_attn.k_proj.weight",
             hook_fn=transpose_and_reshape,
         )
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._key_dense.bias,
+            keras_variable=decoder_layer._self_attention_layer.key_dense.bias,
             hf_weight_key=f"model.layers.{i}.self_attn.k_proj.bias",
             hook_fn=transpose_and_reshape,
         )
         ## Value
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._value_dense.kernel,
+            keras_variable=decoder_layer._self_attention_layer.value_dense.kernel,
             hf_weight_key=f"model.layers.{i}.self_attn.v_proj.weight",
             hook_fn=transpose_and_reshape,
         )
         loader.port_weight(
-            keras_variable=decoder_layer._self_attention_layer._value_dense.bias,
+            keras_variable=decoder_layer._self_attention_layer.value_dense.bias,
             hf_weight_key=f"model.layers.{i}.self_attn.v_proj.bias",
             hook_fn=transpose_and_reshape,
         )

keras_hub/src/version.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.dev202505060405"
+__version__ = "0.21.0.dev202505080407"
 
 
 @keras_hub_export("keras_hub.version")

{keras_hub_nightly-0.21.0.dev202505060405.dist-info → keras_hub_nightly-0.21.0.dev202505080407.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: keras-hub-nightly
-Version: 0.21.0.dev202505060405
+Version: 0.21.0.dev202505080407
 Summary: Pretrained models for Keras.
 Author-email: Keras team <keras-users@googlegroups.com>
 License-Expression: Apache-2.0

{keras_hub_nightly-0.21.0.dev202505060405.dist-info → keras_hub_nightly-0.21.0.dev202505080407.dist-info}/RECORD

@@ -5,7 +5,7 @@ keras_hub/models/__init__.py,sha256=kFWNpjemQ8FLzDlFfMdAOOXJKtxuVHFxyZm7-1mH4Gc,
 keras_hub/samplers/__init__.py,sha256=aFQIkiqbZpi8vjrPp2MVII4QUfE-eQjra5fMeHsoy7k,886
 keras_hub/src/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/api_export.py,sha256=9pQZK27JObxWZ96QPLBp1OBsjWigh1iuV6RglPGMRk0,1499
-keras_hub/src/version.py,sha256=mDGGmnAALEffzSVUqMpzYSiGVm-bXRZqLLdR7dzwTN0,222
+keras_hub/src/version.py,sha256=rBTUFDM2BdW6kVkflfCUyRLvhQnE6YbD5CLSFM9OCyk,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
@@ -110,11 +110,11 @@ keras_hub/src/models/clip/clip_tokenizer.py,sha256=6gIm_LWRbCeBQUI9M2gA8-OXb4tXG
 keras_hub/src/models/clip/clip_vision_embedding.py,sha256=6_qC7T1dqKd-39EreGmHZj-YfjOLEDDKjWnEKcKIyuY,3667
 keras_hub/src/models/clip/clip_vision_encoder.py,sha256=q62MXySZN38uCsjqq8cttfBxD7P5abaKQV2i8_u4N6E,6385
 keras_hub/src/models/cspnet/__init__.py,sha256=TOpvk2cfOVv1bPA1BOGZj0mhmhc6E98zZmW9e0PIvhk,257
-keras_hub/src/models/cspnet/cspnet_backbone.py,sha256=xCeu8BpQSpf-EgCrQehQDg4jNKRAWm0h8paWBfN2DGE,41381
+keras_hub/src/models/cspnet/cspnet_backbone.py,sha256=meHzxubG_9vHQHSelDfrROaQERkDiWkjTtk_gKaWsDc,42457
 keras_hub/src/models/cspnet/cspnet_image_classifier.py,sha256=JqfBHIBTFxaLOyAWx6TdXs0aAOMbcCx1oo47RoQnytc,510
 keras_hub/src/models/cspnet/cspnet_image_classifier_preprocessor.py,sha256=ACRnOhjslk2ZZhpPfJioW4um4RLYa-Suk59z9wa5vfo,543
 keras_hub/src/models/cspnet/cspnet_image_converter.py,sha256=f-ICTY2T-RlCykU6qOHDxg0fY7ECfZ_xpSJzIVmbvpc,342
-keras_hub/src/models/cspnet/cspnet_presets.py,sha256=fWzPz3eZuhFNxxPn9MJHabcXiyJA2PRRVlzNmoFBwWg,533
+keras_hub/src/models/cspnet/cspnet_presets.py,sha256=n01_7DTvbmaA_qs2GWiNLkBXNrrEvigPXSGc2NDTot8,1870
 keras_hub/src/models/deberta_v3/__init__.py,sha256=6E-QtAD1uvTBobrn5bUoyB1qtaCJU-t73TtbAEH6i9g,288
 keras_hub/src/models/deberta_v3/deberta_v3_backbone.py,sha256=oXdV7naTiMowuU3GsXEUo5K0GXiKbPKxdo27o5fXWjc,7258
 keras_hub/src/models/deberta_v3/deberta_v3_masked_lm.py,sha256=ADBktf1DdiP9T6LCaMhdFiZ_mUbBRKMekY5mGwAeJIo,4186
@@ -353,8 +353,8 @@ keras_hub/src/models/segformer/__init__.py,sha256=ERgxA8tyeG2l4G6ywHisn6Oo0Iu7_9
 keras_hub/src/models/segformer/segformer_backbone.py,sha256=T61WQ50T6IwSeiK1NfUKJu3eqbj_m5gz9cpUPtqMfcc,5666
 keras_hub/src/models/segformer/segformer_image_converter.py,sha256=zePZ1cYZl-2TaEF82lj3y7kXjDao5Hgw8c7qfKI2Jd8,360
 keras_hub/src/models/segformer/segformer_image_segmenter.py,sha256=JzX8oJASWdkw8wbm8cohjPnumIvBvj7GGEpbK7ex-6w,5926
-keras_hub/src/models/segformer/segformer_image_segmenter_preprocessor.py,sha256=4xj6_E-JlYpXv064VtEewxaQuD8aXw5egoUKlr_fLPg,1125
-keras_hub/src/models/segformer/segformer_presets.py,sha256=ET39ospixkTaCsjoMLdJrr3wlGvTAQu5prleVC5lMZI,4793
+keras_hub/src/models/segformer/segformer_image_segmenter_preprocessor.py,sha256=Jlsy41n7IymjvU3ENKQJtsQ4xkJEGRtxEm-defz2Nbc,568
+keras_hub/src/models/segformer/segformer_presets.py,sha256=4fPkGTP_jjd3Qcd1KbWYZ7-ze0wdJskMwKG4GZ-UwEg,4793
 keras_hub/src/models/siglip/__init__.py,sha256=uImQYl06pioLwla6c_tiF2PSJKHtq0aSxDPsynQbXcA,257
 keras_hub/src/models/siglip/siglip_backbone.py,sha256=dXp7BU7mqKWthl70KFZ2AMILjNIu5A6itQFu6XD22Qs,8372
 keras_hub/src/models/siglip/siglip_image_converter.py,sha256=yjYc0XOyL37WLlr-X6V4QXI1FCyiKngbHXrZK0hNB1U,342
@@ -461,13 +461,13 @@ keras_hub/src/utils/coco/coco_utils.py,sha256=x_QnUUvZ92zoFzMJugiInHORc4NrMdWVBk
 keras_hub/src/utils/imagenet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/utils/imagenet/imagenet_utils.py,sha256=07ilM5feeD7Ut6YSbVj99RXAZOQONSC1IeKa3I9U6UQ,40161
 keras_hub/src/utils/timm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-keras_hub/src/utils/timm/convert_cspnet.py,sha256=O5HCdeKcSFWOoFr8_wIUQb4Noc0tBEo5Aogk2d6SEes,5676
+keras_hub/src/utils/timm/convert_cspnet.py,sha256=9p1IF0B4UPbDTruQQXR6mJEUdhvQvHx9E0SKNn_Lbw4,8047
 keras_hub/src/utils/timm/convert_densenet.py,sha256=fu8HBIQis5o3ib2tyI2qnmYScVrVIQySok8vTfa1qJ8,3393
 keras_hub/src/utils/timm/convert_efficientnet.py,sha256=SgEIlyyinS04qoQpEgh3WazHq544zNUCCpfmWh3EjSs,17100
 keras_hub/src/utils/timm/convert_mobilenet.py,sha256=XTqHOK4nJwigKefsw7ktWJtOgRpEVMO9MtRhuP5qP_k,9219
 keras_hub/src/utils/timm/convert_resnet.py,sha256=8JFkVtdpy5z9h83LJ97rD-a8FRejXPZvMNksNuStqjM,5834
 keras_hub/src/utils/timm/convert_vgg.py,sha256=MT5jGnLrzenPpe66Af_Lp1IdR9KGtsSrcmn6_UPqHvQ,2419
-keras_hub/src/utils/timm/preset_loader.py,sha256=j2HYi61Zbt0CGd33evFJ8j2fraXl0Zardf4qqAb82K0,3841
+keras_hub/src/utils/timm/preset_loader.py,sha256=4hULdq2K2hgPYTZR71PGV4YNDHLG1zcoxF9TXpg6fGE,3905
 keras_hub/src/utils/transformers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 keras_hub/src/utils/transformers/convert_albert.py,sha256=VdKclZpCxtDWq3UbUUQZf4fR9DJK_JYZ73B4O_G9skg,7695
 keras_hub/src/utils/transformers/convert_bart.py,sha256=Tk4h9Md9rwN5wjQbGIVrC7qzDpF8kI8qm-FKL8HlUok,14411
@@ -477,16 +477,16 @@ keras_hub/src/utils/transformers/convert_gemma.py,sha256=ElCgwBpSN5Q7rV5PJawTsoy
 keras_hub/src/utils/transformers/convert_gpt2.py,sha256=HCeHN_-GiQJRxLCM9OCJJ1watPVpIBF8ujS8pGbBOWc,5703
 keras_hub/src/utils/transformers/convert_llama3.py,sha256=c5phNl-QayQ_BS0s-lenbu6oHxqfwDShKJoh9DluxUU,6146
 keras_hub/src/utils/transformers/convert_mistral.py,sha256=kVhN9h1ZFVhwkNW8p3wnS7eANJUXIsNy1RxWXy20Gqw,4760
-keras_hub/src/utils/transformers/convert_mixtral.py,sha256=vSaqnbMyh31eIj7VQAzoCqLjrc5EHbuOXbrct-49xGM,5512
+keras_hub/src/utils/transformers/convert_mixtral.py,sha256=_esUzVRYABR5pHHSALqUieSuAeBg4te1JnlGQENqECU,5509
 keras_hub/src/utils/transformers/convert_pali_gemma.py,sha256=B1leeDw96Yvu81hYumf66hIid07k5NLqoeWAJgPnaLs,10649
 keras_hub/src/utils/transformers/convert_qwen.py,sha256=WUxMAEFVqRs7TRw7QU5TH3_ev4yf02R1xFVliMvTQqg,5886
-keras_hub/src/utils/transformers/convert_qwen_moe.py,sha256=hRdN5M3czBy_jASm20z-FkO7oB20Aj7EwJgYn-WWaqE,10624
+keras_hub/src/utils/transformers/convert_qwen_moe.py,sha256=a7R28aln-PdAcNuKAXdrtzvslho2Co6GypChxLMKPpc,10618
 keras_hub/src/utils/transformers/convert_vit.py,sha256=9SUZ9utNJhW_5cj3acMn9cRy47u2eIcDsrhmzj77o9k,5187
 keras_hub/src/utils/transformers/preset_loader.py,sha256=1nfS5xVsl-JROGXJXltTqV1fQdcUlZbGGcbf-n79pXM,4225
 keras_hub/src/utils/transformers/safetensor_utils.py,sha256=CYUHyA4y-B61r7NDnCsFb4t_UmSwZ1k9L-8gzEd6KRg,3339
 keras_hub/tokenizers/__init__.py,sha256=4etC--bzhczJrRcvCmxZmOC9hJJcIVOUCgmqMLB3bp0,4051
 keras_hub/utils/__init__.py,sha256=jXPqVGBpJr_PpYmqD8aDG-fRMlxH-ulqCR2SZMn288Y,646
-keras_hub_nightly-0.21.0.dev202505060405.dist-info/METADATA,sha256=oxvVAtbYQvfOFjjOKYBxYbatGhpqwKtu05psmFmCIlM,7393
-keras_hub_nightly-0.21.0.dev202505060405.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
-keras_hub_nightly-0.21.0.dev202505060405.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
-keras_hub_nightly-0.21.0.dev202505060405.dist-info/RECORD,,
+keras_hub_nightly-0.21.0.dev202505080407.dist-info/METADATA,sha256=KW4fkkzlPY8ODeA5TKmEUQZen2irnGeLn9N7CSxQxcQ,7393
+keras_hub_nightly-0.21.0.dev202505080407.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
+keras_hub_nightly-0.21.0.dev202505080407.dist-info/top_level.txt,sha256=N4J6piIWBKa38A4uV-CnIopnOEf8mHAbkNXafXm_CuA,10
+keras_hub_nightly-0.21.0.dev202505080407.dist-info/RECORD,,