A simple way to build ML models with Keras and Tensorflow as base frameworks.
APACHE-2.0 License
This package implements an API over Keras and Tensorflow to build Deep Learning models easily without losing the framework flexibility. BaseNet API tries to implement almost everything from a few lines of code.
Disclaimer: This API is under development. This means that there isn't a stable release yet. However, some features are stable and can be used. Check the tutorials for more info. Please, check the roadmap below to see the future updates.
Any feature request is wellcome and appreciated; and has a high probability to be implemented.
Any issue is wellcome and appreciated; and it will often be inspected.
Author: A.Palomo-Alonso ([email protected])
Universidad de Alcalá.
Escuela Politécnica Superior.
Departamento de Teoría De la Señal y Comunicaciones (TDSC).
ISDEFE Chair of Research.
Feeder databases.
Computational clustering.
Monitoring.
BaseNetDeployment:
Ray
or Spark
clusters).Reinforcement learning:
Computer Vision:
Natural Language Processing:
HuggingFace
package.BaseNetCompiler.set_up_devices()
configures the GPUs according to the free RAM to be used in the API.BaseNetModel.fit_stop()
method.BaseNetDatabase.size
and BaseNetDatabase.distribution
.BaseNetDatabase.fit_stop()
.BaseNetModel._threshold()
private method now takes a set of outputs instead only one.BaseNetModel.recover()
.BaseNetModel.recover()
is a private method: BaseNetModel._recover()
.BaseNetDatabase
modified the incoming list of instances in the database; avoiding checkpointsnvml
library if NVIDIA Drivers are not installed`in the machine.BaseNetDatabase
utils: merge and split databases.BaseNetDatabase
equality check.BaseNetDatabase._reversion()
, BaseNetCompiler._reversion()
and BaseNetModel.__version__
. WhichBaseNetHeuristic
BaseNetDatabase
binarization and normalization of databases.BaseNetDatabase
to read TensorFlow
and Pandas
databases.BaseNetDatabase
for minor bug fixing. (1.7.0)BaseNetFeeder
Class to generate dynamic BaseNetDatabase
s. (1.7.0)BaseNetDeployment
Class to deploy scalable Machine Learning models (in alpha, do not use until 3.0).BaseNetHeuristic
algorithms that implements MetaHeuristic methods such as PSO. (1.8.0)BaseNetLMSE
, solving linear problems with matrix multiplication.CassandraDatabase
.categorical
entry to compile_options
in the BaseNetCompiler
.BaseNetCompiler.set_up_devices()
BaseNetDatabase
as .define_map()
and the mapping method map()
.shape
to the BaseNetDatabase
telling the input-output data shapes.BaseNetDatabase
for Fuzzy-Logic mapping.BaseNetCVVisualizer
and basenet_cv_gui
for computer vision dataset and results visualization.BaseNetStackRoom
, which is a Database manager for big databases.BaseNetCompiler
so it can be built from several YAML files.There are Jupyter Notebooks with usage tutorials! Refer to them HERE. You should run your notebook creating a virtual environment in this README path.
Please, cite this library as:
@misc{basenetapi,
title={BaseNet: A simpler way to build AI models.},
author={A. Palomo-Alonso},
booktitle={PhD in TIC: Machine Learning and NLP.},
year={2022}
}