Kimm

What's Changed
* Apply a more defensive way to fix redownloading issue by james77777778 in https://github.com/james77777778/keras-image-models/pull/55


**Full Changelog**: https://github.com/james77777778/keras-image-models/compare/0.2.4...0.2.5

Major Features and Improvements
- Add more docstrings
- Fix redownloading issue when using `keras.saving.load_model`

What's Changed
* Add docstrings and expose some useful properties for all models by james77777778 in https://github.com/james77777778/keras-image-models/pull/48
* Add docstrings to `kimm.list_models`, `kimm.utils.get_reparameterized_model` by james77777778 in https://github.com/james77777778/keras-image-models/pull/49
* Add docstrings for `kimm.blocks.*` by james77777778 in https://github.com/james77777778/keras-image-models/pull/50
* Add docstrings for `kimm.timm_utils.*` by james77777778 in https://github.com/james77777778/keras-image-models/pull/51
* Fix redownloading issue by james77777778 in https://github.com/james77777778/keras-image-models/pull/54


**Full Changelog**: https://github.com/james77777778/keras-image-models/compare/0.2.2...0.2.4

Major Features and Improvements

- Add `GhostNetV3` (currently only `GhostNetV3W100` has ImageNet weights)
- Improve codes

What's Changed
* Refactor reparameterizable layers and add `GhostNetV3` by james77777778 in https://github.com/james77777778/keras-image-models/pull/47


**Full Changelog**: https://github.com/james77777778/keras-image-models/compare/0.2.1...0.2.2

Major Features and Improvements

Add arbitrary shape support for `MobileViT*` and `VisionTransformer*`

python
import numpy as np

import kimm

x = np.random.uniform(size=[1, 150, 150, 3])
model = kimm.models.MobileViTXXS(input_shape=[150, 150, 3])
print(model.predict(x, verbose=0).shape) [1, 1000]
model = kimm.models.VisionTransformerTiny16(input_shape=[150, 150, 3])
print(model.predict(x, verbose=0).shape) [1, 1000]



Add more model weights

- `kimm.models.ConvNeXtXLarge`
- `kimm.models.VisionTransformerLarge16`
- `kimm.models.VisionTransformerLarge32`

Code cleanup and minor improvements

What's Changed
* Add arbitrary shape support for ViT series by james77777778 in https://github.com/james77777778/keras-image-models/pull/46


**Full Changelog**: https://github.com/james77777778/keras-image-models/compare/0.2.0...0.2.1

Major Features and Improvements
- Improve UX of APIs

What's Changed
* Refactor model definition by james77777778 in https://github.com/james77777778/keras-image-models/pull/42
* Refactor APIs using `namex` by james77777778 in https://github.com/james77777778/keras-image-models/pull/43


**Full Changelog**: https://github.com/james77777778/keras-image-models/compare/0.1.8...0.2.0

Major Features and Improvements
* Add `HGNet` and `HGNetV2`

What's Changed
* Update `pyproject.toml` by james77777778 in https://github.com/james77777778/keras-image-models/pull/37
* Update `README.md` by james77777778 in https://github.com/james77777778/keras-image-models/pull/38
* Update `requirements.txt` and `pyproject.toml` by james77777778 in https://github.com/james77777778/keras-image-models/pull/40
* Add `HGNet` and `HGNetV2` by james77777778 in https://github.com/james77777778/keras-image-models/pull/41


**Full Changelog**: https://github.com/james77777778/keras-image-models/compare/0.1.7...0.1.8