mirror of
https://github.com/microsoft/qlib.git
synced 2026-06-06 05:51:17 +08:00
c9ed050ef0
* Init model for both dataset * Remove some deprecated code * Add model template; * We must align with previous results * We choose another mode as the initial version * Almost success to run GRU * Successfully run training * Passed general_nn test * gru test * Alignment test passed * comment * fix readme & minor errors * general nn updates & benchmarks * Update examples/benchmarks/GeneralPtNN/workflow_config_gru2mlp.yaml --------- Co-authored-by: Young <afe.young@gmail.com> Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
Introduction
What is GeneralPtNN
- Fix previous design that fail to support both Time-series and tabular data
- Now you can just replace the Pytorch model structure to run a NN model.
We provide an example to demonstrate the effectiveness of the current design.
workflow_config_gru.yamlalign with previous results GRU(Kyunghyun Cho, et al.)workflow_config_gru2mlp.yamlto demonstrate we can convert config from time-series to tabular data with minimal changes- You only have to change the net & dataset class to make the conversion.
workflow_config_mlp.yamlachieved similar functionality with MLP
TODO
-
We will align existing models to current design.
-
The result of
workflow_config_mlp.yamlis different with the result of MLP since GeneralPtNN has a different stopping method compared to previous implementations. Specificly, GeneralPtNN controls training according to epoches, whereas previous methods controlled by max_steps.