liuyu/qlib

mirror of https://github.com/microsoft/qlib.git synced 2026-07-04 03:21:00 +08:00

Files

dependabot[bot] 5811090a82 Bump tensorflow-gpu from 1.15.0 to 2.12.0 in /examples/benchmarks/TFT

Bumps [tensorflow-gpu](https://github.com/tensorflow/tensorflow) from 1.15.0 to 2.12.0.
- [Release notes](https://github.com/tensorflow/tensorflow/releases)
- [Changelog](https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md)
- [Commits](https://github.com/tensorflow/tensorflow/compare/v1.15.0...v2.12.0)

---
updated-dependencies:
- dependency-name: tensorflow-gpu
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>

2023-03-24 22:24:22 +00:00

data_formatters

fix_typo (#790 )

2021-12-31 22:14:47 +08:00

expt_settings

Refactor to Python3 style

2020-12-15 20:37:43 +08:00

libs

fix_typo (#790 )

2021-12-31 22:14:47 +08:00

README.md

Merge nested main (#597 )

2021-10-01 02:15:30 +08:00

requirements.txt

Bump tensorflow-gpu from 1.15.0 to 2.12.0 in /examples/benchmarks/TFT

2023-03-24 22:24:22 +00:00

tft.py

DDG-DA paper code (#743 )

2022-01-10 16:52:37 +08:00

workflow_config_tft_Alpha158.yaml

simplify signal parameter

2021-10-15 14:48:31 +00:00

README.md

Temporal Fusion Transformers Benchmark

Source

Reference: Lim, Bryan, et al. "Temporal fusion transformers for interpretable multi-horizon time series forecasting." arXiv preprint arXiv:1912.09363 (2019).

GitHub: https://github.com/google-research/google-research/tree/master/tft

Run the Workflow

Users can follow the workflow_by_code_tft.py to run the benchmark.

Notes

Please be aware that this script can only support Python 3.6 - 3.7.
If the CUDA version on your machine is not 10.0, please remember to run the following commands conda install anaconda cudatoolkit=10.0 and conda install cudnn on your machine.
The model must run in GPU, or an error will be raised.
New datasets should be registered in data_formatters, for detail please visit the source.