Screen Shot 2022-10-07 at 4.50.16 PM.png
東流TFTS (TensorFlow Time Series) 是基于TensorFlow時(shí)間序列開(kāi)源工具，支持多種深度學(xué)習(xí)模型
- 結(jié)構(gòu)靈活览芳，適配多種時(shí)間序列任務(wù)
- 多套久經(jīng)考驗(yàn)的深度學(xué)習(xí)模型
- 查閱文檔松嘶，快速入門
中文名“東流”闹究，源自辛棄疾“青山遮不住，畢竟東流去袜香。江晚正愁余，山深聞鷓鴣”萝喘。
安裝
pip install tensorflow>=2.0.0
pip install tfts
快速使用
import tensorflow as tf
import tfts
from tfts import AutoModel, KerasTrainer
train, valid = tfts.load_data('sine')
backbone = AutoModel('seq2seq')
model = functools.partial(backbone.build_model, input_shape=[24, 2])
trainer = KerasTrainer(model)
trainer.train(train, valid)
trainer.predict(valid[0])
示例
- 東流Bert模型 獲得KDD CUP2022百度風(fēng)機(jī)功率預(yù)測(cè)第3名
- 東流Seq2seq模型 獲得阿里天池-AI earth人工智能氣象挑戰(zhàn)賽第4名
更多應(yīng)用
- Time_series_prediction
- Time series classification
- Anomaly detection
- Uncertainty prediction
- Parameters tuning with optuna
引用
@misc{tfts2020,
author = {Longxing Tan},
title = {Time series prediction},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/longxingtan/time-series-prediction}},
}
