ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Chronos: add tf forecaster doc (#4923)

Browse source
This commit is contained in:
David smurf 2022-06-27 11:33:41 +08:00 committed by GitHub
parent 76608a5034
commit 500b7bbe99
2 changed files with 49 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/readthedocs/source/conf.py
View file

@ -18,7 +18,7 @@ import glob
import shutil
import urllib
autodoc_mock_imports = ["openvino", "pytorch_lightning"]
autodoc_mock_imports = ["openvino", "pytorch_lightning", "keras"]
# documentation root, use os.path.abspath to make it absolute, like shown here.
#sys.path.insert(0, '.')

63
docs/readthedocs/source/doc/PythonAPI/Chronos/forecasters.rst
View file

@ -4,43 +4,76 @@ Forecasters
LSTMForecaster
----------------------------------------
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`.
Long short-term memory(LSTM) is a special type of recurrent neural network(RNN). We implement the basic version of LSTM - VanillaLSTM for this forecaster for time-series forecasting task. It has two LSTM layers, two dropout layer and a dense layer.
For the detailed algorithm description, please refer to `here <https://github.com/intel-analytics/BigDL/blob/main/docs/docs/Chronos/Algorithm/LSTMAlgorithm.md>`__.
`version:pytorch`
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`.
.. automodule:: bigdl.chronos.forecaster.lstm_forecaster
:members:
:undoc-members:
:show-inheritance:
`version:tensorflow`
:strong:`Please refer to` `BaseTF2Forecaster <https://qp-bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#module-bigdl.chronos.forecaster.tf.base_forecaster>`__ :strong:`for other methods other than initialization`.
.. automodule:: bigdl.chronos.forecaster.tf.lstm_forecaster
:members:
:undoc-members:
:show-inheritance:
Seq2SeqForecaster
-------------------------------------------
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`.
Seq2SeqForecaster wraps a sequence to sequence model based on LSTM, and is suitable for multivariant & multistep time series forecasting.
`version:pytorch`
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`.
.. automodule:: bigdl.chronos.forecaster.seq2seq_forecaster
:members:
:undoc-members:
:show-inheritance:
`version:tensorflow`
:strong:`Please refer to` `BaseTF2Forecaster <https://qp-bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#module-bigdl.chronos.forecaster.tf.base_forecaster>`__ :strong:`for other methods other than initialization`.
.. automodule:: bigdl.chronos.forecaster.tf.seq2seq_forecaster
:members:
:undoc-members:
:show-inheritance:
TCNForecaster
----------------------------------------
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`.
Temporal Convolutional Networks (TCN) is a neural network that use convolutional architecture rather than recurrent networks. It supports multi-step and multi-variant cases. Causal Convolutions enables large scale parallel computing which makes TCN has less inference time than RNN based model such as LSTM.
`version:pytorch`
:strong:`Please refer to` `BasePytorchForecaster <https://bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#basepytorchforecaster>`__ :strong:`for other methods other than initialization`.
.. automodule:: bigdl.chronos.forecaster.tcn_forecaster
:members:
:undoc-members:
:show-inheritance:
`version:tensorflow`
:strong:`Please refer to` `BaseTF2Forecaster <https://qp-bigdl.readthedocs.io/en/latest/doc/PythonAPI/Chronos/forecasters.html#module-bigdl.chronos.forecaster.tf.base_forecaster>`__ :strong:`for other methods other than initialization`.
.. automodule:: bigdl.chronos.forecaster.tf.tcn_forecaster
:members:
:undoc-members:
:show-inheritance:
NBeatsForecaster
----------------------------------------
@ -75,7 +108,6 @@ TCMFForecaster supports distributed training and inference. It is based on Orca
:undoc-members:
:show-inheritance:
MTNetForecaster
----------------------------------------
@ -115,17 +147,18 @@ For the detailed algorithm description, please refer to `here <https://github.co
:show-inheritance:
TFParkForecaster
----------------------------------------
.. automodule:: bigdl.chronos.forecaster.tfpark_forecaster
:members:
:undoc-members:
:show-inheritance:
BasePytorchForecaster
----------------------------------------
.. autoclass:: bigdl.chronos.forecaster.base_forecaster.BasePytorchForecaster
:members:
:show-inheritance:
BaseTF2Forecaster
----------------------------------------
.. automodule:: bigdl.chronos.forecaster.tf.base_forecaster
:members:
:undoc-members:
:show-inheritance: