Open isears opened 3 years ago
I used it inside a model and no issue when running on TPU (kaggle). Works with GPU, TPU.
# Preprocessing
data_preprocessing = keras.Sequential(
[
Resizing(
*INP_SIZE,
interpolation="bilinear"
)
],
name='PreprocessingLayers'
)
# Augmentation
data_augmentations = keras.Sequential(
[
RandomCrop(*INP_SIZE),
RandomFlip("horizontal"),
RandomZoom(0.1, fill_mode='nearest'),
RandomRotation(0.1, fill_mode='nearest'),
CLAHE(
tile_grid_size=(4, 4), clip_limit=3.0
)
],
name='AugmentationLayers'
)
model = keras.Sequential(
[
keras.layers.InputLayer(input_shape=INP_SIZE+(3,)),
data_preprocessing,
data_augmentations,
applications.EfficientNetB0(include_top=False, pooling='avg'),
...
]
)
One thing though, if I place CLAHE
right after the Resize
method, then there's a problem.
There are reports of this library not working when running on a TPU.