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
sforkowany z sadaszewski/decagon-pytorch
1
0
Forkuj 0
Kod Zgłoszenia 0 Oczekujące zmiany 0 Wydania 0 Wiki Aktywność
Nie możesz wybrać więcej, niż 25 tematów Tematy muszą się zaczynać od litery lub cyfry, mogą zawierać myślniki ('-') i mogą mieć do 35 znaków.
150 Commity
1 Gałąź
866KB
Drzewo: 13940671cc
Gałęzie Tagi
${ item.name }
Utwórz gałąź ${ searchTerm }
z '13940671cc'
${ noResults }
decagon-pytorch/src/icosagon
Stanislaw Adaszewski 13940671cc Performance tests. 3 lat temu
..
unused Remove loss as no longer necessary. 4 lat temu
__init__.py Work on icosagon.trainprep. 4 lat temu
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). 4 lat temu
compile.py Performance tests. 3 lat temu
convlayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 3 lat temu
convolve.py Fixes for the GPU. 3 lat temu
data.py Clean up _equal(). 3 lat temu
declayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 3 lat temu
decode.py Use torch.nn.Parameter(List) in decode. 4 lat temu
dropout.py Fix for sparse_coo_tensor(). 3 lat temu
input.py Increase test coverage. 4 lat temu
model.py Add TrainLoop. 4 lat temu
normalize.py Fix for sparse_coo_tensor(). 3 lat temu
sampling.py Fixes for the GPU. 3 lat temu
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 3 lat temu
trainprep.py Fixes for the GPU. 3 lat temu
weights.py Bring more elements to icosagon. 4 lat temu