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
Hello, do you know some way to put my gpu at work? I think all packages are well installed, but is running on cpu `computer_setup()` `os : Linux-5.15.0-46-generic-x86_64-with-glibc2.31 python :...
Is there some simple way for me to turn a normal csv file (ex Date Open High Low Close) to the required format for multivariate timeseries?
 
**Context**: A common way to deploy models is using TorchServe (https://pytorch.org/serve/). The simplest way to do this requires a TorchScripted model (https://pytorch.org/docs/stable/jit.html). **Issue**: While many tsai model architectures are already...
**edit** Having read the other issues, this might be related to #738 & #713 as it's trying a multivariate input/univariate output. I'm happy to make some code changes if you...
For variable length sequences, does tsai algorithms inheriently support using [packed padded sequences](https://pytorch.org/docs/stable/generated/torch.nn.utils.rnn.pack_padded_sequence.html) supported in PyTorch? Thanks! Relevant topic: https://github.com/timeseriesAI/tsai/discussions/319
The PatchTST tutorial is trying to download data from a location no longer available. In the "Load and Prepare Data" section of the tutorial it says: You can download all...
Hi! I have noticed that the LSTM/GRU/etc. models only output the last time step of the sequence. Is there some option to obtain the full sequence instead? Thanks!
When I run the first demo 'Binary univariate classification', I find that in line 8: 'clf.fit_one_cycle(100, 3e-4)', the intepreter notices an error: 'graph_out is 'NoneType' which has no attribute 'update''....
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