Jost Arndt
Jost Arndt
In the MultiheadAttention the line `self.linears = clones(nn.Linear(d_model, d_model), 4)` occurs, but it should be a 3 instead of a 4: `self.linears = clones(nn.Linear(d_model, d_model), 3)` am I correct?
Für manche LKW-Parkplätze existieren Live-Daten, welche die Auslastung der Parkplätze angeben. Diese sind z.B bei [rlp.verkehr](https://verkehr.rlp.de) auffindbar, allerdings nicht in dieser API. Ist eine Integration dieser Daten geplant oder möglich?
### Is your feature request related to a problem? Please describe. I would like to call the ARIMA on batches of data, i.e. the data has the shape `[batchsize, timesteps]`,...
Hi, I tried downloading the 3D Navier-Stokes (CFD) data with `download_direct.py`, however it freezes after 144 GB. How can I download the rest of the data? A fix would be...
Hi there, another feature request: it would be cool if the GradNorm is able to work with a GradScaler for mixed precision training; or does this functionality already exist? Best,
Hi! Thanks for providing the code for this! I am just not sure if I understood correctly how to use this and have some questions regarding the ReadMe: After calling...
Hi there, I am trying to convert a model from this paper https://www.nature.com/articles/s41586-023-06185-3 downloaded from this GitHub https://github.com/198808xc/Pangu-Weather First of all: thanks a lot for onnx2torch. However, there are some...
Hi, I am trying to use this library for Pangu Weather https://www.nature.com/articles/s41586-023-06185-3 and load their pre-trained model from https://github.com/198808xc/Pangu-Weather However I have some problems with e.g. https://github.com/ENOT-AutoDL/onnx2torch/blob/a5958facd941d66de313603da6336d2257d67dbf/onnx2torch/node_converters/scatter_nd.py#L77 for which `output[tuple(output_indices)]...
Hi! For me it is a bit unclear which data to download: The google cloud bucket contains two dirs: `era5625`, and `era5265_aaai`. So I downloaded the larger one. However, this...