Merge branch 'master' into master

README.md

@@ -4,7 +4,7 @@
 [![contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/keras-team/keras-hub/issues)
 
 > [!IMPORTANT]
-> 📢 KerasNLP is becoming KerasHub! 📢 Read
+> 📢 KerasNLP is now KerasHub! 📢 Read
 > [the announcement](https://github.com/keras-team/keras-hub/issues/1831).
 >
 > We have renamed the repo to KerasHub in preparation for the release, but have not yet
@@ -26,7 +26,7 @@ All models support JAX, TensorFlow, and PyTorch from a single model
 definition and can be fine-tuned on GPUs and TPUs out of the box. Models can
 be trained on individual accelerators with built-in PEFT techniques, or
 fine-tuned at scale with model and data parallel training. See our
-[Getting Started guide](https://keras.io/guides/keras_nlp/getting_started)
+[Getting Started guide](https://keras.io/guides/keras_hub/getting_started)
 to start learning our API. Browse our models on
 [Kaggle](https://www.kaggle.com/organizations/keras/models).
 We welcome contributions.
@@ -35,9 +35,9 @@ We welcome contributions.
 
 ### For everyone
 
-- [Home Page](https://keras.io/keras_nlp)
-- [Developer Guides](https://keras.io/guides/keras_nlp)
-- [API Reference](https://keras.io/api/keras_nlp)
+- [Home Page](https://keras.io/keras_hub)
+- [Developer Guides](https://keras.io/guides/keras_hub)
+- [API Reference](https://keras.io/api/keras_hub)
 - [Pre-trained Models](https://www.kaggle.com/organizations/keras/models)
 
 ### For contributors
@@ -56,7 +56,7 @@ Fine-tune a BERT classifier on IMDb movie reviews:
 import os
 os.environ["KERAS_BACKEND"] = "jax"  # Or "tensorflow" or "torch"!
 
-import keras_nlp
+import keras_hub
 import tensorflow_datasets as tfds
 
 imdb_train, imdb_test = tfds.load(
@@ -67,7 +67,7 @@ imdb_train, imdb_test = tfds.load(
 )
 
 # Load a BERT model.
-classifier = keras_nlp.models.Classifier.from_preset(
+classifier = keras_hub.models.Classifier.from_preset(
     "bert_base_en",
     num_classes=2,
     activation="softmax",
@@ -79,25 +79,17 @@ classifier.fit(imdb_train, validation_data=imdb_test)
 classifier.predict(["What an amazing movie!", "A total waste of my time."])
 ```
 
-Try it out [in a colab](https://colab.research.google.com/gist/mattdangerw/e457e42d5ea827110c8d5cb4eb9d9a07/kerasnlp-quickstart.ipynb).
+Try it out [in a colab](https://colab.research.google.com/drive/1gSWkh3yOLwmKAaNh2dQQ6kQIlnGte7P2?usp=sharing).
 For more in depth guides and examples, visit
-[keras.io/keras_nlp](https://keras.io/keras_nlp/).
+[keras.io/keras_hub](https://keras.io/keras_hub/).
 
 ## Installation
 
-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:
-
-```bash
-pip install keras-nlp==0.15.1
-```
-
-To try out the latest pre-release version of KerasHub, you can use
+To try out the latest version of KerasHub, you can use
 our nightly package:
 
 ```bash
-pip install keras-hub-nightly
+pip install keras-hub
 ```
 
 KerasHub currently requires TensorFlow to be installed for use of the

keras_hub/api/layers/__init__.py

@@ -34,21 +34,34 @@
 from keras_hub.src.layers.preprocessing.random_deletion import RandomDeletion
 from keras_hub.src.layers.preprocessing.random_swap import RandomSwap
 from keras_hub.src.layers.preprocessing.start_end_packer import StartEndPacker
+from keras_hub.src.models.clip.clip_image_converter import CLIPImageConverter
 from keras_hub.src.models.deeplab_v3.deeplab_v3_image_converter import (
     DeepLabV3ImageConverter,
 )
 from keras_hub.src.models.densenet.densenet_image_converter import (
     DenseNetImageConverter,
 )
+from keras_hub.src.models.efficientnet.efficientnet_image_converter import (
+    EfficientNetImageConverter,
+)
+from keras_hub.src.models.mit.mit_image_converter import MiTImageConverter
 from keras_hub.src.models.pali_gemma.pali_gemma_image_converter import (
     PaliGemmaImageConverter,
 )
 from keras_hub.src.models.resnet.resnet_image_converter import (
     ResNetImageConverter,
 )
+from keras_hub.src.models.retinanet.anchor_generator import AnchorGenerator
+from keras_hub.src.models.retinanet.retinanet_image_converter import (
+    RetinaNetImageConverter,
+)
 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.segformer.segformer_image_converter import (
+    SegFormerImageConverter,
+)
+from keras_hub.src.models.vgg.vgg_image_converter import VGGImageConverter
 from keras_hub.src.models.whisper.whisper_audio_converter import (
     WhisperAudioConverter,
 )

keras_hub/api/models/__init__.py

@@ -54,8 +54,11 @@
 from keras_hub.src.models.bloom.bloom_tokenizer import BloomTokenizer
 from keras_hub.src.models.causal_lm import CausalLM
 from keras_hub.src.models.causal_lm_preprocessor import CausalLMPreprocessor
+from keras_hub.src.models.clip.clip_backbone import CLIPBackbone
 from keras_hub.src.models.clip.clip_preprocessor import CLIPPreprocessor
+from keras_hub.src.models.clip.clip_text_encoder import CLIPTextEncoder
 from keras_hub.src.models.clip.clip_tokenizer import CLIPTokenizer
+from keras_hub.src.models.clip.clip_vision_encoder import CLIPVisionEncoder
 from keras_hub.src.models.csp_darknet.csp_darknet_backbone import (
     CSPDarkNetBackbone,
 )
@@ -129,6 +132,12 @@
 from keras_hub.src.models.efficientnet.efficientnet_backbone import (
     EfficientNetBackbone,
 )
+from keras_hub.src.models.efficientnet.efficientnet_image_classifier import (
+    EfficientNetImageClassifier,
+)
+from keras_hub.src.models.efficientnet.efficientnet_image_classifier_preprocessor import (
+    EfficientNetImageClassifierPreprocessor,
+)
 from keras_hub.src.models.electra.electra_backbone import ElectraBackbone
 from keras_hub.src.models.electra.electra_tokenizer import ElectraTokenizer
 from keras_hub.src.models.f_net.f_net_backbone import FNetBackbone
@@ -177,6 +186,10 @@
 from keras_hub.src.models.image_classifier_preprocessor import (
     ImageClassifierPreprocessor,
 )
+from keras_hub.src.models.image_object_detector import ImageObjectDetector
+from keras_hub.src.models.image_object_detector_preprocessor import (
+    ImageObjectDetectorPreprocessor,
+)
 from keras_hub.src.models.image_segmenter import ImageSegmenter
 from keras_hub.src.models.image_segmenter_preprocessor import (
     ImageSegmenterPreprocessor,
@@ -203,11 +216,10 @@
     MistralCausalLMPreprocessor,
 )
 from keras_hub.src.models.mistral.mistral_tokenizer import MistralTokenizer
-from keras_hub.src.models.mix_transformer.mix_transformer_backbone import (
-    MiTBackbone,
-)
-from keras_hub.src.models.mix_transformer.mix_transformer_classifier import (
-    MiTImageClassifier,
+from keras_hub.src.models.mit.mit_backbone import MiTBackbone
+from keras_hub.src.models.mit.mit_image_classifier import MiTImageClassifier
+from keras_hub.src.models.mit.mit_image_classifier_preprocessor import (
+    MiTImageClassifierPreprocessor,
 )
 from keras_hub.src.models.mobilenet.mobilenet_backbone import MobileNetBackbone
 from keras_hub.src.models.mobilenet.mobilenet_image_classifier import (
@@ -246,6 +258,13 @@
 from keras_hub.src.models.resnet.resnet_image_classifier_preprocessor import (
     ResNetImageClassifierPreprocessor,
 )
+from keras_hub.src.models.retinanet.retinanet_backbone import RetinaNetBackbone
+from keras_hub.src.models.retinanet.retinanet_object_detector import (
+    RetinaNetObjectDetector,
+)
+from keras_hub.src.models.retinanet.retinanet_object_detector_preprocessor import (
+    RetinaNetObjectDetectorPreprocessor,
+)
 from keras_hub.src.models.roberta.roberta_backbone import RobertaBackbone
 from keras_hub.src.models.roberta.roberta_masked_lm import RobertaMaskedLM
 from keras_hub.src.models.roberta.roberta_masked_lm_preprocessor import (
@@ -269,6 +288,13 @@
 from keras_hub.src.models.sam.sam_image_segmenter_preprocessor import (
     SAMImageSegmenterPreprocessor,
 )
+from keras_hub.src.models.segformer.segformer_backbone import SegFormerBackbone
+from keras_hub.src.models.segformer.segformer_image_segmenter import (
+    SegFormerImageSegmenter,
+)
+from keras_hub.src.models.segformer.segformer_image_segmenter_preprocessor import (
+    SegFormerImageSegmenterPreprocessor,
+)
 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 (
@@ -298,6 +324,9 @@
 from keras_hub.src.models.text_to_image import TextToImage
 from keras_hub.src.models.vgg.vgg_backbone import VGGBackbone
 from keras_hub.src.models.vgg.vgg_image_classifier import VGGImageClassifier
+from keras_hub.src.models.vgg.vgg_image_classifier_preprocessor import (
+    VGGImageClassifierPreprocessor,
+)
 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

keras_hub/src/bounding_box/__init__.py

@@ -17,4 +17,4 @@
 from keras_hub.src.bounding_box.utils import as_relative
 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
+from keras_hub.src.bounding_box.validate_format import validate_format

keras_hub/src/bounding_box/converters.py

@@ -20,29 +20,74 @@ class RequiresImagesException(Exception):
 ALL_AXES = 4
 
 
-def _encode_box_to_deltas(
+def encode_box_to_deltas(
     anchors,
     boxes,
-    anchor_format: str,
-    box_format: str,
+    anchor_format,
+    box_format,
+    encoding_format="center_yxhw",
     variance=None,
     image_shape=None,
 ):
-    """Converts bounding_boxes from `center_yxhw` to delta format."""
+    """Encodes bounding boxes relative to anchors as deltas.
+
+    This function calculates the deltas that represent the difference between
+    bounding boxes and provided anchors. Deltas encode the offsets and scaling
+    factors to apply to anchors to obtain the target boxes.
+
+    Boxes and anchors are first converted to the specified `encoding_format`
+    (defaulting to `center_yxhw`) for consistent delta representation.
+
+    Args:
+        anchors: `Tensors`. Anchor boxes with shape of `(N, 4)` where N is the
+            number of anchors.
+        boxes:  `Tensors` Bounding boxes to encode. Boxes can be of shape
+            `(B, N, 4)` or `(N, 4)`.
+        anchor_format: str. The format of the input `anchors`
+            (e.g., "xyxy", "xywh", etc.).
+        box_format: str. The format of the input `boxes`
+            (e.g., "xyxy", "xywh", etc.).
+        encoding_format: str. The intermediate format to which boxes and anchors
+            are converted before delta calculation. Defaults to "center_yxhw".
+        variance: `List[float]`. A 4-element array/tensor representing variance
+            factors to scale the box deltas. If provided, the calculated deltas
+            are divided by the variance. Defaults to None.
+        image_shape: `Tuple[int]`. The shape of the image (height, width, 3).
+            When using relative bounding box format for `box_format` the
+            `image_shape` is used for normalization.
+    Returns:
+        Encoded box deltas. The return type matches the `encode_format`.
+
+    Raises:
+        ValueError: If `variance` is not None and its length is not 4.
+        ValueError: If `encoding_format` is not `"center_xywh"` or
+            `"center_yxhw"`.
+
+    """
     if variance is not None:
         variance = ops.convert_to_tensor(variance, "float32")
         var_len = variance.shape[-1]
 
         if var_len != 4:
             raise ValueError(f"`variance` must be length 4, got {variance}")
+
+    if encoding_format not in ["center_xywh", "center_yxhw"]:
+        raise ValueError(
+            "`encoding_format` should be one of 'center_xywh' or 'center_yxhw', "
+            f"got {encoding_format}"
+        )
+
     encoded_anchors = convert_format(
         anchors,
         source=anchor_format,
-        target="center_yxhw",
+        target=encoding_format,
         image_shape=image_shape,
     )
     boxes = convert_format(
-        boxes, source=box_format, target="center_yxhw", image_shape=image_shape
+        boxes,
+        source=box_format,
+        target=encoding_format,
+        image_shape=image_shape,
     )
     anchor_dimensions = ops.maximum(
         encoded_anchors[..., 2:], keras.backend.epsilon()
@@ -61,27 +106,72 @@ def _encode_box_to_deltas(
     return boxes_delta
 
 
-def _decode_deltas_to_boxes(
+def decode_deltas_to_boxes(
     anchors,
     boxes_delta,
-    anchor_format: str,
-    box_format: str,
+    anchor_format,
+    box_format,
+    encoded_format="center_yxhw",
     variance=None,
     image_shape=None,
 ):
-    """Converts bounding_boxes from delta format to `center_yxhw`."""
+    """Converts bounding boxes from delta format to the specified `box_format`.
+
+    This function decodes bounding box deltas relative to anchors to obtain the
+    final bounding box coordinates. The boxes are encoded in a specific
+    `encoded_format` (center_yxhw by default) during the decoding process.
+    This allows flexibility in how the deltas are applied to the anchors.
+
+    Args:
+        anchors: Can be `Tensors` or `Dict[Tensors]` where keys are level
+            indices and values are corresponding anchor boxes.
+            The shape of the array/tensor should be `(N, 4)` where N is the
+            number of anchors.
+        boxes_delta Can be `Tensors` or `Dict[Tensors]` Bounding box deltas
+            must have the same type and structure as `anchors`.  The
+            shape of the array/tensor can be `(N, 4)` or `(B, N, 4)` where N is
+            the number of boxes.
+        anchor_format: str. The format of the input `anchors`.
+            (e.g., `"xyxy"`, `"xywh"`, etc.)
+        box_format: str. The desired format for the output boxes.
+            (e.g., `"xyxy"`, `"xywh"`, etc.)
+        encoded_format: str. Raw output format from regression head. Defaults
+            to `"center_yxhw"`.
+        variance: `List[floats]`. A 4-element array/tensor representing
+            variance factors to scale the box deltas. If provided, the deltas
+            are multiplied by the variance before being applied to the anchors.
+            Defaults to None.
+        image_shape:  The shape of the image (height, width).  This is needed
+            if normalization to image size is required when converting between
+            formats. Defaults to None.
+
+    Returns:
+        Decoded box coordinates. The return type matches the `box_format`.
+
+    Raises:
+        ValueError: If `variance` is not None and its length is not 4.
+        ValueError: If `encoded_format` is not `"center_xywh"` or
+            `"center_yxhw"`.
+
+    """
     if variance is not None:
         variance = ops.convert_to_tensor(variance, "float32")
         var_len = variance.shape[-1]
 
         if var_len != 4:
             raise ValueError(f"`variance` must be length 4, got {variance}")
 
+    if encoded_format not in ["center_xywh", "center_yxhw"]:
+        raise ValueError(
+            f"`encoded_format` should be 'center_xywh' or 'center_yxhw', "
+            f"but got '{encoded_format}'."
+        )
+
     def decode_single_level(anchor, box_delta):
         encoded_anchor = convert_format(
             anchor,
             source=anchor_format,
-            target="center_yxhw",
+            target=encoded_format,
             image_shape=image_shape,
         )
         if variance is not None:
@@ -97,7 +187,7 @@ def decode_single_level(anchor, box_delta):
         )
         box = convert_format(
             box,
-            source="center_yxhw",
+            source=encoded_format,
             target=box_format,
             image_shape=image_shape,
         )