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
Hi, I'm new to timeseriesAI.
Data should be normalized before we fit the model.
For instance, I have data [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]. [1, ..., 8] should be normalized, so 8 would be 1, 9 would be 1.143 after transformation.
When I apply the code in tutorial notebook, does batch_tfms=[TSNormalize()] normalize all data(1, ....,8 in my case) or just normalize the data in 1 batch?
I did some research and someone says that batch_tfms let the GPU do the work, but I don't think I really understand the concept.
Another question is that how can I see the data after transformation? I use show_batch() but I don't know which batch is showing.
Edit: using xb, yb = dls.train.one_batch()seems to see only 1 batch?
Hi, I'm new to timeseriesAI. Data should be normalized before we fit the model. For instance, I have data [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]. [1, ..., 8] should be normalized, so 8 would be 1, 9 would be 1.143 after transformation. When I apply the code in tutorial notebook, does
batch_tfms=[TSNormalize()]
normalize all data(1, ....,8 in my case) or just normalize the data in 1 batch?I did some research and someone says that batch_tfms let the GPU do the work, but I don't think I really understand the concept.
Another question is that how can I see the data after transformation? I use show_batch() but I don't know which batch is showing. Edit: using
xb, yb = dls.train.one_batch()
seems to see only 1 batch?Thanks!