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!
Você não pode selecionar mais de 25 tópicos Os tópicos devem começar com uma letra ou um número, podem incluir traços ('-') e podem ter até 35 caracteres.
Stanislaw Adaszewski 6cf3175950 Remove an extra newline. 4 anos atrás
..
unused Remove loss as no longer necessary. 4 anos atrás
__init__.py Work on icosagon.trainprep. 4 anos atrás
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). 4 anos atrás
compile.py Performance tests. 4 anos atrás
convlayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 anos atrás
convolve.py Remove an extra newline. 4 anos atrás
data.py Clean up _equal(). 4 anos atrás
declayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 anos atrás
decode.py Use torch.nn.Parameter(List) in decode. 4 anos atrás
dropout.py Fix for sparse_coo_tensor(). 4 anos atrás
input.py Fix for non-leaf .grad warning. 4 anos atrás
model.py Add TrainLoop. 4 anos atrás
normalize.py Fixes for bool sparse tensors. 4 anos atrás
sampling.py Fixes for the GPU. 4 anos atrás
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 anos atrás
trainprep.py Fixes for the GPU. 4 anos atrás
weights.py Bring more elements to icosagon. 4 anos atrás