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
I have dataset with the following columns: click_time, attributed_time, ip, app, device, os, channel, is_attributed I am trying to predict [attributed_time, ip, app, device, os, channel, is_attributed] at a particular...
### Discussed in https://github.com/timeseriesAI/tsai/discussions/857 Originally posted by **ChrystleMyrnaLobo** November 14, 2023 Hi! I'm using the [MiniRocket Pytorch implementation](tutorial_nbs/10_Time_Series_Classification_and_Regression_with_MiniRocket.ipynb) for multivariate time series classification. Thanks for the GPU compatible implementation! :D...
Many models do not have a 'backbone' attribute and can not be used as base_arch for mWDNPlus. Some of them have 'backbone' but it seems many models do not have....
Hello, thank you for sharing such high-quality code. I have training data and a requirement as follows, and I'm wondering if your code can be used to achieve it: I...
After applying a workaround for issue #847, continuing to run notebook `01a_MultiClass_MultiLabel_TSClassification.ipynb` under the MultiLabel section runs into this error (which is thought not to be related to the previous...
When running notebook `01a_MultiClass_MultiLabel_TSClassification.ipynb` under the MultiLabel section, specifically [this cell code](https://github.com/timeseriesAI/tsai/blob/main/tutorial_nbs/01a_MultiClass_MultiLabel_TSClassification.ipynb?short_path=3442af8#L1256), results in this error (cropped screen shot):  Here is the full traceback: ``` --------------------------------------------------------------------------- ValueError Traceback (most...
How can I see the detailed architecture inside `XResNet1d.py` for `xresnet1d50`? I want to debug in detail and view the `forward` process of `xresnet1d50` because I want to draw its...
``` class _RNN_Base(Module): def __init__(self, c_in, c_out, hidden_size=100, n_layers=1, bias=True, rnn_dropout=0, bidirectional=False, fc_dropout=0., init_weights=True): self.rnn = self._cell(c_in, hidden_size, num_layers=n_layers, bias=bias, batch_first=True, dropout=rnn_dropout, bidirectional=bidirectional) self.dropout = nn.Dropout(fc_dropout) if fc_dropout else nn.Identity()...
My apologies for the dumb question. I have a target variable and continuous and categorical features in a dataframe. The categorical features are dynamic. I'd like to train a time...
Hi..When I am using oretarin=true and give a path to the retrain weight it gives me a error that RSRegressor is not utterable..how I can solve this problem?
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