akaniklaus

Can you please let me know what the "num_layers" parameter is for? and how I should select that? I checked the paper but couldn't find an explanation for that one.

Thank you for sharing this beautiful work. I have three convolutional layers followed by a global average pooling and then finally a linear layer. Do you recommend placing the BAM...

Population Based Training of Neural Networks

4

Hello, is it possible to include following technique in the repository as well? Population Based Training of Neural Networks https://arxiv.org/abs/1711.09846

Training Wavelet Filters

3

Hello, thank you for sharing this beautiful work. I have also implemented the RCF framework in this paper except for the part where the discrete wavelet filter coefficients are trained....

Thank you very much. I would welcome if you can share the 1d version of OctConv as well.

LSTM Support

1

Would this also work for LSTM? Do you have any benchmark of the method on that?

Ideas for Extension

2

Merhaba Atilim, I would like to share few ideas for extension of the method. 1) Warm Restarts: It would be great to use the method in a cyclic learning-rate fashion....

create_returns_tear_sheet gives a ValueError

4

**ValueError: The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().** ``` ~/.local/lib/python3.6/site-packages/pyfolio/plotting.py in call_w_context(*args, **kwargs) 50 if set_context: 51 with plotting_context(), axes_style(): ---> 52...

Calmar Ratio w/ EMDD

3

It would be great if you can add this. http://alumnus.caltech.edu/~amir/mdd-risk.pdf ``` function EDD = emaxdrawdown(Mu, Sigma, T) %EMAXDRAWDOWN Compute expected maximum drawdown for a Brownian motion. % % EDD =...

Regression & SSDKL variant

1

First of all, thank you for such a great work. In the below repository, they used VAT for regression and also proposed another method called SSDKL, which they claim to...