IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an email to s dot adaszewski at gmail dot com. User accounts are meant only to report issues and/or generate pull requests. This is a purpose-specific Git hosting for ADARED projects. Thank you for your understanding!
sadaszewski1
/
decagon-pytorch
forkato da sadaszewski/decagon-pytorch
1
0
Forka 0
Codice Problemi 0 Pull Requests 0 Rilasci 0 Wiki Attività
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
156 Commit
1 Ramo (Branch)
866KB
Albero (Tree): 6cf3175950
Rami (Branch) Tag
${ item.name }
Crea branch ${ searchTerm }
da '6cf3175950'
${ noResults }
decagon-pytorch/src/icosagon
Stanislaw Adaszewski 6cf3175950 Remove an extra newline. 4 anni fa
..
unused Remove loss as no longer necessary. 4 anni fa
__init__.py Work on icosagon.trainprep. 4 anni fa
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). 4 anni fa
compile.py Performance tests. 4 anni fa
convlayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 anni fa
convolve.py Remove an extra newline. 4 anni fa
data.py Clean up _equal(). 4 anni fa
declayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 anni fa
decode.py Use torch.nn.Parameter(List) in decode. 4 anni fa
dropout.py Fix for sparse_coo_tensor(). 4 anni fa
input.py Fix for non-leaf .grad warning. 4 anni fa
model.py Add TrainLoop. 4 anni fa
normalize.py Fixes for bool sparse tensors. 4 anni fa
sampling.py Fixes for the GPU. 4 anni fa
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 anni fa
trainprep.py Fixes for the GPU. 4 anni fa
weights.py Bring more elements to icosagon. 4 anni fa