Can you add a DEMO of LSTM for time series ,Please
sharpwood opened this issue Β· 41 comments
SiaNet is great ! Thanks for your work.
Can you add a DEMO of LSTM for time series .
thanks!
Thanks mate! sure will add to my plan
Thanks very muchγ
I see you mark this issue as a question, is it possible that the existing version of the function can be implemented? But I see that class Recurrent has not been cited
If the existing version can be implemented, can you give a line of key code, thank you.
Sorry my bad. I have to implement LSTM, GRU and RNN properly and provide examples. One the plan of development.
π
LSTM has been added to the layer folder. Is it available now?
I added a LSTM layer, but it was wrong when traning: Objects that can be empty must have a value
I only try add a line :
model.Add(new LSTM(dim:20,cellDim:1));
in HousingRegression BuildModel method
Fixed the issue with the LSTM. Can you please check now. Although I am not sure if LSTM will work with MSE loss function. Also with Sparse input like starting with Embedding layer. Please advice?
Will try to implement this example: https://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural-networks-python-keras/
Hope to complete by tomorrow
that is great!!!
model.Add(new LSTM(20, cellDim: 5));
still in HousingRegression
Should work now! Please take the latest
That is ok.
When will TimeSeriesPrediction be finished?
I added the example code and testing in progress. Having some issue with training. Will try to complete by tomorrow
Try out this example code with some of your sample data: https://github.com/deepakkumar1984/SiaNet/blob/master/SieNet.Examples/TimeSeriesPrediction.cs
I changed lookback to 3, how to define LSTM shape, as if it was different from Keras
The lookback is the shape of the input. The number of lookback will convert the series data to tabular dataset with 3 columns which will be the input shape.
I have updated the time series example, could you please try again?
model.Add(new LSTM(dim: 4, shape: Shape.Create(lookback)));
I have got last version, it works ,thanks.
If I have multiple features in csv file, how to define the shape?
Ok Its not implemented for multivariate. Let me work on that now and have another example ready for you.
I think it may be that I don't make it clear. My English is poor.
I mean not a multi-layer LSTM, but a number of features input data.
For example:
https://machinelearningmastery.com/multivariate-time-series-forecasting-lstms-keras/
Is this example appropriate?
Reshape layer has been committed , Would you update the example?
Looks interesting :) Will follow up this project / thread.
How's the example program going?
I will have something by tomorrow. Was working on other fixes on priority.
Please use this example to use Reshape layer: https://github.com/deepakkumar1984/SiaNet/blob/master/SieNet.Examples/MiltiVariateTimeSeriesPrediction.cs
Do you have any documentation that explains what are shapes, and why do we need a reshape layer ?
Nevermind, found explanation here: https://www.tensorflow.org/programmers_guide/tensors :)
Normalize and ConvertTimeSeries method seems to have some problems.
Normalize method generate some NaN values , and The ConvertTimeSeries method does not seem to be able to handle multi - column data.
The data frame is bit basic now. Need to enhance with missing values and load datatype other than float. For now you need to sanitize the dataset by yourself and then load it. You can use the framework like Deedle to load the csv and make it ready for training. I may plan to make use of Deedle in the project and way of converting Deedle output to CNTK value.
Closing it off as there is no activity in last 180 days