losses are always nan about mtad-gat-pytorch HOT 7 CLOSED

Check out my answer on #13, I believe it is due to uninitialized bias parameters.

It works for me now, great!

from mtad-gat-pytorch.

I have further dived into code and came to know that outputs from TemporalAttentionLayer are nan always, and from FeatureAttentionLayer some come out as nans.

from mtad-gat-pytorch.

If you haven't already, I suggest you ensure that

1. input data has the correct format
2. data itself does not contain nan and are scaled properly before input to the model.

Regards,
Axel

from mtad-gat-pytorch.

I have further dived into code and came to know that outputs from TemporalAttentionLayer are nan always, and from FeatureAttentionLayer some come out as nans.

Have you solved this problem yet? I also have this problem, During training, the losses are all nan,and there are many zeros in the data. And I don't understand why the num_values in labeled_anomalies.csv and the shape in the .npy file in the train folder are different. For example, C-1 in labeled_anomalies.csv is 2264, but C-1.npy is 2158. '2264' and '2158' don't match.

from mtad-gat-pytorch.

Same problem with the SMD dataset, using the default hyperparameters.

from mtad-gat-pytorch.

Setting use_gatv2 to False can produce normal loss.

from mtad-gat-pytorch.

Check out my answer on #13, I believe it is due to uninitialized bias parameters.

from mtad-gat-pytorch.