From 39f7fd2d1fd1f0c81caa1cfb643e8a45122b0e7e Mon Sep 17 00:00:00 2001 From: liangs6212 <80952198+liangs6212@users.noreply.github.com> Date: Wed, 6 Apr 2022 14:55:55 +0800 Subject: [PATCH] Chronos: migrate from tf1.15 to tf2 (MTNetForecaster) (#4334) * convert mtnet_forecaster * fix conflict * add batch_size * fix conflict * change description * change description again * fix doc * change param description --- docs/readthedocs/source/doc/PythonAPI/Chronos/forecasters.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/readthedocs/source/doc/PythonAPI/Chronos/forecasters.rst b/docs/readthedocs/source/doc/PythonAPI/Chronos/forecasters.rst index 32e5b364..cc16b46b 100644 --- a/docs/readthedocs/source/doc/PythonAPI/Chronos/forecasters.rst +++ b/docs/readthedocs/source/doc/PythonAPI/Chronos/forecasters.rst @@ -81,11 +81,11 @@ MTNetForecaster MTNet is a memory-network based solution for multivariate time-series forecasting. In a specific task of multivariate time-series forecasting, we have several variables observed in time series and we want to forecast some or all of the variables' value in a future time stamp. -MTNet is proposed by paper `A Memory-Network Based Solution for Multivariate Time-Series Forecasting `__. MTNetForecaster is derived from tfpark.KerasMode, and can use all methods of KerasModel. Refer to `tfpark.KerasModel API Doc `__ for details. +MTNet is proposed by paper `A Memory-Network Based Solution for Multivariate Time-Series Forecasting `__. For the detailed algorithm description, please refer to `here `__. -.. automodule:: bigdl.chronos.forecaster.mtnet_forecaster +.. automodule:: bigdl.chronos.forecaster.tf.mtnet_forecaster :members: :undoc-members: :show-inheritance: