tsai

tsai copied to clipboard

XCM on multivariate regression

1

Hi , I managed to use show_gradcam func on classification model and it worked well. But when I use it with regression models (through [TSRegression()] tfms): ``` tfms = [None,...

Rabea007

NameError: name 'GatedTabTransformer' is not defined

2

Hi Team, I have been running experiments and trying different models. I have found that I was not able to use GatedTabTransformer model My environment is: ``` os : Windows-10-10.0.19043-SP0...

zmce2018

Minor spelling, grammar and formatting contributions to some tutorial notebooks

1

As I was going through the first tutorial notebooks I noticed a few minor spelling / grammar contributions I could make. I have only touched the markdown cells, not the...

jmp75

Understanding GradCAM

5

Hello, Im not sure to understand the figures ploted by show_gradcam() from the XCM model. Does anyone could explain me the results? Her is an example of plot that I...

IKetchup

Bug:I just can not get the same result after running get_pred func!!!!

12

I just can not get the same result after running get_pred func!!!! https://colab.research.google.com/github/timeseriesAI/tsai/blob/master/tutorial_nbs/01_Intro_to_Time_Series_Classification.ipynb I get the 0.9278 after running learn.get_preds first time , but i get 0.7111 then i run...

yifeiSunny

AttributeError: Exception occured in `ShowGraph` when calling event `after_epoch`: 'NoneType' object has no attribute 'update'

10

from tsai.all import * my_setup() regression_list dsid = 'AppliancesEnergy' X, y, splits = get_regression_data(dsid, split_data=False) X.shape, y.shape, y[:10] check_data(X, y, splits) tfms = [None, [TSRegression()]] batch_tfms = TSStandardize(by_sample=True, by_var=True) dls...

sunmingliu

Hi, I am not able to run the TSSequencerPlus due the following problem: ``` X - shape: [642876 samples x 47 features x 36 timesteps] type: ndarray dtype:float64 isnan: 0...

zmce2018

Can the model trained be transformed to torch script ?

wdongdongde

How to convert between "get_ts_dls" and "torch.utils.data.DataLoader"

1

I want to use tsai for model training and torch for model inference, so I need to convert "get_ts_dls" and "torch.utils.data.DataLoader"

aappaappoo

The `show_batch()` function is not working as expected along with any of the time series to image transformations. **Steps to reproduce** Run the [TS to Image tutorial](https://github.com/timeseriesAI/tsai/blob/main/tutorial_nbs/06_TS_to_image_classification.ipynb) notebook. **Expected behavior**...

abhijitramesh