Keras data format converter
Generates equal keras models with the desired data format
Requirements
tensorflow >= 2.0
API
convert_channels_first_to_last(model: keras.Model, inputs_to_transpose: List[str] = None, verbose: bool = False) -> keras.Model
convert_channels_last_to_first(model: tf.keras.Model, inputs_to_transpose: List[str] = None, verbose: bool = False) \ -> tf.keras.Model
model: Keras model to convert
inputs_to_transpose: list of input names that need to be transposed due tothe data foramt changing
verbose: detailed output
Getting started
from tensorflow import keras
from keras_data_format_converter import convert_channels_last_to_first
# Load Keras model
keras_model = keras.models.load_model("my_image_model")
# Call the converter (image_input is an input that needs to be transposed, can be different for your model)
converted_model = convert_channels_last_to_first(keras_model, ["image_input"])
Supported Layers with Special handling
- Normalization layers
- Permute
- Reshape
- Concatenate
- Dot
- MultiHeadAttention
- TFOpLambda (Inserted by the Functional API construction whenever users call a supported TF symbol on KerasTensors, see here at Tensorflow repo for more info)
Unsupported Layers due to lack of data_format property
- Cropping1D
- Upsampling1D
- Zeropadding1D
- All layers in tensorflow.keras.preprocessing
How to deploy
- Create a new release version on GitHub
- Update parameters in setup.py (usually
versionanddownload_url) - Run
python setup.py sdistin root directory - Run
pip install twine - Run
twine upload dist/*
License
This software is covered by MIT License.
Release files for keras-data-format-converter 0.1.24
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| keras_data_format_converter-0.1.24.tar.gz | 6.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| keras_data_format_converter-0.1.24-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 16.2 kB
Release files / keras_data_format_converter-0.1.24.tar.gz
| Download URL | keras_data_format_converter-0.1.24.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
54637106a010503d0c8c038de01a1544ee2fe252aadd4a77c0f5a8c13bcf48e7
|
|
BLAKE2b-256 checksum How to use checksums |
e17fd3cce9994c286aa9af57744358ceac2921d348e36b96eaa07f06a79beee2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.2.1 CPython/3.12.8 Darwin/24.6.0
|
Release files / keras_data_format_converter-0.1.24-py3-none-any.whl
| Download URL | keras_data_format_converter-0.1.24-py3-none-any.whl |
|---|---|
| Size | 9.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1e78aa5fdd766526e200205a49d10e3e0e17a9fd0eaacdfb24a94fb4f7b88d34
|
|
BLAKE2b-256 checksum How to use checksums |
6bea291eef5273c846585c3416acc3d9076d6c498ae7cc6a5a570c46fc0ec600
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/2.2.1 CPython/3.12.8 Darwin/24.6.0
|