tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series tasks like classification, regression, forecasting, imputation… tsai is currently under active development by timeseriesAI. During the last few releases, here are some of the most significant additions to tsai:

A number of tutorials have been created to help you get started to use tsai with time series data. Please, feel free to open the notebooks (you can open them in Colab if you want) and tweak them to do your own experiments.

Applies sklearn-type pipeline transforms. ⚠️ Important: save_all and load_all methods are designed for small datasets only. If you are using a larger dataset, you should use the standard save and load_learner methods. source. load_all (path='export', dls_fname='dls', model_fname='model', learner_fname='learner', device=None, pickle_module=<module.

2025年3月2日 · tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series tasks like classification, regression, forecasting, imputation… tsai is currently under active development by timeseriesAI. During the last few releases, here are some of the most significant additions to tsai:

2022年4月25日 · 用于时间序列和序列的最先进的深度学习库。 tsai 是一个基于 Pytorch 和 fastai 的开源深度学习包，专注于时间序列任务的最先进技术，如分类、回归、预测、插补...... tsai 目前正在由 timeseriesAI 积极开发。 ⚡️ 从 tsai 0.3.0 开始，通过更好地使用依赖项，您将获得 更快的安装和导入。 新的可视化方法：learn.feature_importance () 和 learn.step_importance () 将帮助您更好地了解模型的工作原理。 新的校准模型：learn.calibrate_model () 用于时间序列分类任务 …

tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series tasks like classification, regression, forecasting, imputation... tsai is currently under active development by timeseriesAI.

2024年3月21日 · tsai是一个开源PyTorch库，提供高效工具处理时间序列任务，如预测、分类和异常检测。 其模块化设计、预训练模型和社区支持使其成为处理复杂时间序列问题的理想选择。

State-of-the-art Deep Learning library for Time Series and Sequences. tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series tasks like classification, regression, forecasting, imputation… tsai is currently under active development by timeseriesAI.

You can use "relu" or "gelu"') class _TSTEncoderLayer (Module): def __init__ (self, q_len:int, d_model:int, n_heads:int, d_k:Optional [int]=None, d_v:Optional [int]=None, d_ff:int=256, dropout:float=0.1, activation:str="gelu"): assert d_model // n_heads, f"d_model ( {d_model}) must be divisible by n_heads ( {n_heads})" d_k = ifnone (d_k, d_...

Utility functions used to build PyTorch timeseries models. apply_idxs (o, idxs) Function to apply indices to zarr, dask and numpy arrays. source. SeqTokenizer (c_in, embed_dim, token_size=60, norm=False) Generates non-overlapping tokens from sub-sequences within a sequence by applying a sliding window. source. get_embed_size (n_cat, rule='log2')