I have recently gone through this paper. I want to implement it in python. I am not getting how to implement it. I am very new to this topic. I am not able to understand what equations have they used. I have read this but I am not able to relate this to the paper.
How to approach it using python? I want to build a function which can tell me the possible source location. Also, I am not able to understand the dataset also.
I am studying some source codes from PytorchGeometric.
Actually I am really finding from torch_sparse import SparseTensor in Google, to get how to use SparseTensor.
But there is nothing I can see explanation. I saw many documents about COO,CSR something like that, but how can I use SparseTensor?
I read : https://pytorch.org/docs/stable/sparse.html# but there is nothing like SparseTensor.
Thank you in advance :)
I just had the same problem and stumbled upon your question, so I will just detail what I did here, maybe it helps someone. I think the main confusion results from the naming of the package. SparseTensoris from torch_sparse, but you posted the documentation of torch.sparse. The first is an individual project in the pytorch ecosystem and a part of the foundation of PyTorch Geometric, but the latter is a submodule of the actual official PyTorch package.
So, looking at the right package (torch_sparse), there is not much information about how to use the SparseTensor class there (Link).
If we go to the source code on the other hand (Link) you can see that the class has a bunch of classmethods that you can use to genereate your own SparseTensor from well documented pytorch classes.
In my case, all I needed was a way to feed the RGCNConvLayer with just one Tensor including both the edges and edge types, so I put them together with the following line:
edge_index = SparseTensor.from_edge_index(edge_index, edge_types)
If you, however, already have a COO or CSR Tensor, you can use the appropriate classmethods instead.
I want to have the source code for the math operations of pytorch. I know they are not all in the same file but hopefully someone can help me. I saw that there is an Aten folder on the github of pytorch but for me its quite confusing to go through.
Its my first question here. Sorry for anything annoying.
I would like to use the STL (Seasonal-Trend-Loess) approach implemented in statsmodels here to pull out the seasonal component of some time series data. Just one problem... the code for the STL doesn't seem to exist. I've reinstalled statsmodels, checked their github, and gone through the actual .py files... can't find it in statsmodels.tsa.seasonal at all. Only seasonal_decompose which is not as good.
Any suggestions on where I might find the code needed for STL? Or good alternatives?
I'm trying to extend the joint.shapes.devs.Atomic model but get a "maximum call stack size exceeded" error.
This is apparently normal behavior for the devs module. ( see the following link: https://groups.google.com/forum/#!topic/jointjs/md5s_fKPl_M ).
I was wondering if there is a way to work around this? Would it be better to just edit the devs module directly? The solution in the above link won't work for me, since I'll need to be able to convert the data into JSON.
Edit
I've made my own object based on the devs model. I can extend this model as I need to, but I still don't like this as a solution. I don't think it offers the same kind of flexibility with extending as I was looking for. If anyone has a better option please let me know.