Deep-Time-Series-Prediction icon indicating copy to clipboard operation
Deep-Time-Series-Prediction copied to clipboard

Seq2Seq, Bert, Transformer, WaveNet for time series prediction.

Results 9 Deep-Time-Series-Prediction issues
Sort by recently updated
recently updated
newest added

ValueError Traceback (most recent call last) in 44 # train model 45 wave_learner = Learner(wave, opt, root_dir="./wave", ) ---> 46 wave_learner.fit(max_epochs=epoch, train_dl=train_dl, valid_dl=valid_dl, early_stopping=True, patient=16) 47 48 # load best...

Running your sample code on CPU without cuda arguments in creating train_dl results in too many values to unpack error while training. Any solution?

Have been playing with your implementation of RNN2RNN mixing it up with [this one](https://github.com/fastai/course-nlp/blob/master/7b-seq2seq-attention-translation.ipynb). I have some remarks that have worked for me: - Inverse the `Dense` layer dropput/linear order....