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!
Вы не можете выбрать более 25 тем Темы должны начинаться с буквы или цифры, могут содержать дефисы(-) и должны содержать не более 35 символов.
Stanislaw Adaszewski 6cf3175950 Remove an extra newline. 4 лет назад
..
unused Remove loss as no longer necessary. 4 лет назад
__init__.py Work on icosagon.trainprep. 4 лет назад
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). 4 лет назад
compile.py Performance tests. 4 лет назад
convlayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 лет назад
convolve.py Remove an extra newline. 4 лет назад
data.py Clean up _equal(). 4 лет назад
declayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 лет назад
decode.py Use torch.nn.Parameter(List) in decode. 4 лет назад
dropout.py Fix for sparse_coo_tensor(). 4 лет назад
input.py Fix for non-leaf .grad warning. 4 лет назад
model.py Add TrainLoop. 4 лет назад
normalize.py Fixes for bool sparse tensors. 4 лет назад
sampling.py Fixes for the GPU. 4 лет назад
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 лет назад
trainprep.py Fixes for the GPU. 4 лет назад
weights.py Bring more elements to icosagon. 4 лет назад