Where is 3-layer 1 D Resnet? about tfc-pretraining HOT 4 OPEN

I modified the num head, which was originally 2. Speaking of which, I'd have to say that your code is really poorly written.

I used a new dataset with more channels than seq_len, and you ended up swapping dimensions and it all went haywire.

Another point is that you use the torch.cuda package in the data augmentation and then provide an option to not use the GPU. hhh

I guess this is a very early version, right? Can you provide the final version?

from tfc-pretraining.

Can your model solve multivariate time series forecasting? If not, why do you provide the option of multiple channels?

from tfc-pretraining.

I think you can find it in the diff of 6ed4dae.

from tfc-pretraining.