tsai
tsai copied to clipboard
timeseriesAI
Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai
1. I am trainning model in python like this model= tsai.LSTM_FCNPlus(train_dsets.vars, train_dsets.c, train_dsets.len, se=8) learn = tsai.Learner(train_dsets, model, metrics=[tsai.mae, tsai.rmse]) learn.fit(80, learnRate *0.9,cbs=[EarlyStoppingCallback(patience=7), ShowGraphCallback()] ) torch.jit.trace(model,).save("model.pt"） predict1 = learn.get_X_preds(inputs) 2....
torch.jit.script(model).save("model_test_script.pt") ^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/jit/_script.py", line 1429, in script ret = _script_impl( ^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/jit/_script.py", line 1147, in _script_impl return torch.jit._recursive.create_script_module( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib64/python3.11/site-packages/torch/jit/_recursive.py", line 557, in create_script_module return create_script_module_impl(nn_module, concrete_type,...
in tsai 0.4.0. I use EarlyStoppingCallback for LSTM_FCNPlus. but it raise File "/home/research/code/FTD_Research5/Model/TSAI/RNNResModel.py", line 285, in learn.fit(500, learnRate,cbs=[EarlyStoppingCallback(monitor='mse_loss', min_delta=0.1, patience=2)] ) File "/usr/local/lib/python3.11/site-packages/fastai/learner.py", line 272, in fit self._with_events(self._do_fit, 'fit', CancelFitException,...
Fixes https://github.com/sktime/sktime/issues/7885 What does this implement / fix? While wiring tsai into sktime I hit two subtle indexing / dtype issues that can also bite vanilla tsai users: ----NumPy scalar...
Title: Try out NBTest: A smarter tool for testing jupyter notebooks Hi tsai developers, We’re researchers at Cornell University focused on quality assurance for machine learning workflows ([our group](https://www.cs.cornell.edu/~saikatd/)). We...
I noticed the only difference may be one having both normalize and denormalize methods, and another one not (if else block instead in forward) Is the duplication a mistake or...
I use MiniRocketClassifier on a multivariate time series dataset ```python cls = MiniRocketClassifier() cls.fit(X, y) ``` An error occurred ```bash Traceback (most recent call last): File "e:\...\src\pipeline\classification\ROCKET.py", line 190, in...
Hi, any idea on how to solve this? > --------------------------------------------------------------------------- > NotImplementedError Traceback (most recent call last) > Cell In [4], line 1 > ----> 1 learn = load_learner_all(path='export', dls_fname='dls',...
This Pull Request addresses an edge case in the `TSNormalize` transform where `max == min` in the input data, which would otherwise result in a `None` return value during normalization....
Metadata
Owner
Metadata
Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai