Port MobileNet (#2049)

* kaggle weights

* updated Mobilenet backbone to match it with torch implementation

* Deleted presets

* Mobilenet preset deleted

* code reformat

* padding changed

* downsample_padding

* typo fixed

* timm script added

* checkpoint conversion added

* preset added

* preset testcase added

BytePairTokenizer must not split sequences of \n (#1910)

* fix for loading of special tokens in Llama tokenizer

* fix for Llama tokenizer which can have multiple end tokens

* bug fix

* adding some missing tokens to Llama3 tokenizer

* fixed tests and Llama3Tokenizer init.

* now loading correct eos_token config from Hugging Face checkpoint. Using hack for Keras checkpoint because it does not have this info

* fix for BytePairTokenizer to make Lllama3-instruct work in chat: \n\n sequences are significant in the chat template and must be preserved by the tokenizer

---------

Co-authored-by: Martin Görner <[email protected]>

fix for generation that never stops in Llama3-Instruct variants (#1904)

* fix for loading of special tokens in Llama tokenizer

* fix for Llama tokenizer which can have multiple end tokens

* bug fix

* adding some missing tokens to Llama3 tokenizer

* fixed tests and Llama3Tokenizer init.

* now loading correct eos_token config from Hugging Face checkpoint. Using hack for Keras checkpoint because it does not have this info

---------

Co-authored-by: Martin Görner <[email protected]>

fix failing JAX GPU test (#1911)

* fix tests

* fix test

Refactor `MMDiT`, add `ImageToImage` and `Inpaint` for SD3 (#1909)

* Refactor `MMDiT` and add `ImageToImage`

* Update model version

* Fix minor bugs.

* Add `Inpaint` for SD3.

* Fix warnings of MMDiT.

* Addcomment to Inpaint

* Simplify `MMDiT` implementation and info of `summary()`.

* Refactor `generate()` API of `TextToImage`, `ImageToImage` and `Inpaint`.

Minor bug fix (#1915)

Change to image_converter.image_size since it is a tuple and it's not a callable function.

[Mix Transformer] Add Presets for MiTB0...MiTB5 (#1893)

* add presets for mit

* add standin paths

* register presets in __init__.py

* fix op in overlapping patching and embedding, start adding conversion utils

* style

* add padding to MiT patchingandembedding

* update to support other presets

* update conversin script

* fix link for b5

* add cityscapes weights

* update presets

* update presets

* update conversion script to make directories

* use save_preset

* change name of output dir

* add preprocessor flow

* api gen and add preprocessor to mits

* conform to new image classifier style

* format

* resizing image converter -> ImageConverter

* address comments

refactoring

remove default resizing for vision backbones (#1916)

* remove defailt resizing

* fix GPU test

Update VGG model to be compatible with HF and add conversion scripts (#1914)

Deeplab presets (#1918)

* add preset configurations for deeplabv3

* fix uri

* Add training details

update presets to point to the main Keras Kaggle page (#1921)

* update presets to point to the main keras page

* update mit path

Added test for the way BytePairTokenizer handles the \n\n sequence, which is important in Lama chat templates (#1912)

* added test for the way BytePairTokenizer handles the \n\n sequence, which is important in Lama chat templates

* un commented the test lines that were commented by mistake

* fixed linter errors

Task models fix (#1922)

* added test for the way BytePairTokenizer handles the \n\n sequence, which is important in Lama chat templates

* fix for wrongly configured task models LLama, PaliGemma, Mistral and Phi3 + test

* comments

* un commented the test lines that were commented by mistake

* fixed linter errors

adding option strip_prompt to generate() (#1913)

* added test for the way BytePairTokenizer handles the \n\n sequence, which is important in Lama chat templates

* un commented the test lines that were commented by mistake

* fixed linter errors

* added options strip_prompt to generate()

* fix for tensorflow: the compiled version of generate(strip_prompt=True) now works + code refactoring to make it more understandable

* added test for generate(strip_prompt=True)

* minor edits

Layout map for Llama (#1923)

* added test for the way BytePairTokenizer handles the \n\n sequence, which is important in Lama chat templates

* un commented the test lines that were commented by mistake

* fixed linter errors

* added default layout map for Llama

* minor fixes in tests

Update deeplab_v3_presets.py (#1924)

Add paths to get SAM weights from (#1925)

Two fixes for image resizing in preprocessing (#1927)

1. Properly display when are not resizing the input image in
   `model.summary()`
2. Allow setting the `image_size` directly on a preprocessing layer.

2. is just to allow a more consistent way to set the input shape
across tasks. We now have:

```python
text_classifier = keras_hub.models.TextClassifer.from_preset(
    "bert_base_en",
)
text_classifier.preprocessor.sequence_length = 256

image_classifier = keras_hub.models.TextClassifer.from_preset(
    "bert_base_en",
)
image_classifier.preprocessor.image_size = (256, 256)

multi_modal_lm = keras_hub.models.CausalLM.from_preset(
    "some_preset",
)
multi_modal_lm.preprocessor.sequence_length = 256
multi_modal_lm.preprocessor.image_size = (256, 256)
```

add back default image resizing (#1926)

Update deeplab_v3_presets.py (#1928)

* Update deeplab_v3_presets.py

* Update deeplab_v3_presets.py

Update PaliGemma to remove `include_rescaling` arg (#1917)

* update PaliGemma

* update conversion script

* fix GPU tests

fix path (#1929)

* fix path

* nit

Fix paligemma checkpoint conversion script (#1931)

* add back default image resizing

* fix bug in image converter

* fix paligemma checkpoint conversion file

* fix preset name

* remove debug code

* revert unintended changes

update preset path to point to latest version of models (#1932)

Update sdv3 path (#1934)

update sam docstring to show correct backbone in docstring (#1936)

Convert input dict to tensors during train_on_batch (#1919)

Register VGG presets. (#1935)

* register vgg preset

* nit

* nit

* nit

Add ResNetVD presets (#1897)

* Add ResNetVD presets

* Updated Kaggle handles

* Add weight conversion script for ResNet_vd

* Add usage

rebase conflict resolved

conflict resolve

Update sam_presets.py (#1940)

Update vit_det_backbone.py (#1941)

fix gpu test (#1939)

* fix gpu test

* cast input

* update dtype

* change to resnet preset

* remove arg

Added Support for Returning Attention Scores in TransformerEncoder call (#1879)

* Added: Return attention scores argument to transformer encoder

* Added: docstring for return_attention_scores and added a test to chek the working of the argument

* Fixed: Test case by removing print stmts and using self.assertAllEqual

* Fixed: Linting

Mark preset tests as large (#1942)

* fix tests

* fix test

* Update preset_utils_test.py

version bump to 0.17.0.dev0 (#1944)

Update stable_diffusion_3_presets.py (#1946)

[Semantic Segmentation] - Add SegFormer Architecture, Weight Conversion Script and Presets (#1883)

* initial commit - tf-based, kcv

* porting to keras_hub structure - removing aliases, presets, etc.

* enable instantiation of segformer backbone with custom MiT backbone

* remove num_classes from backbone

* fix input

* add imports to __init__

* update preset

* update docstrings

* add basic tests

* remove redundant imports

* update docstrings

* remove unused import

* running api_gen.py

* undo refactor of mit

* update docstrings

* add presets for mit

* add standin paths

* add presets for segformer backbone

* register presets in __init__.py

* addressing comments

* addressing comments

* addressing comments

* update most tests

* add remaining tests

* remove copyright

* fix test

* override from_config

* fix op in overlapping patching and embedding, start adding conversion utils

* style

* add padding to MiT patchingandembedding

* update to support other presets

* update conversin script

* fix link for b5

* add cityscapes weights

* update presets

* update presets

* update conversion script to make directories

* use save_preset

* change name of output dir

* add preprocessor flow

* api gen and add preprocessor to mits

* conform to new image classifier style

* format

* resizing image converter -> ImageConverter

* merge mit branch into segformer branch

* add preprocessor and converter

* address comments

* clarify backbone usage

* add conversion script

* numerical equivalence changes

* fix numerical inaccuracies

* update conversion script

* update conversion script

* remove transpose

* add preprocessor to segformer class

* fix preset path

* update test shape

* update presets

* update test shape

* expand docstrings

* add rescaling and normalization to preprocessor

* remove backbone presets, remove copyrights, remove backbone cls from segmenter

* remove copyright and unused import

* apply same transformation to masks as input images

* fix import

* fix shape in tests

Update readme (#1949)

* Update README.md

* Update README.md

Update llama_backbone.py docstring (#1950)

Update path (#1953)

Update preset path for keras.io.

There is no LLaMA2 in keras.io https://keras.io/api/keras_hub/models/llama2

This is the actual link:
https://keras.io/api/keras_hub/models/llama2

For Vicuna it does not have it's own model direcotry, since it is also the part of Llama,, updated the path.

Update SD3 init parameters (replacing `height`, `width` with `image_shape`) (#1951)

* Replace SD3 `height` and `width` with `image_shape`

* Update URI

* Revert comment

* Update SD3 handle

* Replace `height` and `width` with `image_shape`

* Update docstrings

* Fix CI

Update docstring (#1954)

AudioConverter is registered as "keras_hub.layers.WhisperAudioConverter" and not as part of models.

 updated Mobilenet backbone to match it with torch implementation

timm script added

checkpoint conversion added

Refactoring

* rebase done

* code formatting

* preset path updated

* WIP mobilenet fixes, subblock refactoring

* WIP refactored, classifier/task changes

* matched mobilenetv3 inference, working now

* format pass

* actual format pass

* fix import

* update test, attempting to fix format issue

* fix format back to original style

* review updates, format fixes etc.

* update fix DepthwiseConvBlock args

* implement compute output shape for squeeze_and_excite layer

* update arguments to IR Block

* explicitly build head before transfer

* updates, fixes to ensure colab workflow works

* add noqa, fix protected variable issue

* fix remaining test issues

* update expected test output/presets

* fix merge typo

---------

Co-authored-by: Usha Rengaraju <[email protected]>
Co-authored-by: ushareng <[email protected]>

Author: 3 people

keras_hub/api/layers/__init__.py

@@ -52,6 +52,9 @@
     EfficientNetImageConverter,
 )
 from keras_hub.src.models.mit.mit_image_converter import MiTImageConverter
+from keras_hub.src.models.mobilenet.mobilenet_image_converter import (
+    MobileNetImageConverter,
+)
 from keras_hub.src.models.pali_gemma.pali_gemma_image_converter import (
     PaliGemmaImageConverter,
 )

keras_hub/api/models/__init__.py

@@ -228,6 +228,9 @@
 from keras_hub.src.models.mobilenet.mobilenet_image_classifier import (
     MobileNetImageClassifier,
 )
+from keras_hub.src.models.mobilenet.mobilenet_image_classifier_preprocessor import (
+    MobileNetImageClassifierPreprocessor,
+)
 from keras_hub.src.models.object_detector import ObjectDetector
 from keras_hub.src.models.object_detector import (
     ObjectDetector as ImageObjectDetector,