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
feito fork de sadaszewski/decagon-pytorch
1
0
Fork 0
Código Issues 0 Pull requests 0 Versões 0 Wiki Atividade
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.
166 Commits
1 Branch
866KB
Tag: dd41ba9bd0
Branches Tags
${ item.name }
Criar branch ${ searchTerm }
de dd41ba9bd0
${ noResults }
decagon-pytorch/src/icosagon
Stanislaw Adaszewski dd41ba9bd0 Add matrix-multiply illustration. 3 anos atrás
..
unused Remove loss as no longer necessary. 3 anos atrás
__init__.py Work on icosagon.trainprep. 4 anos atrás
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). 3 anos atrás
bulkdec.py Fix a typo. 3 anos atrás
compile.py Performance tests. 3 anos atrás
convlayer.py Add BatchedData support to DecodeLayer. 3 anos atrás
convolve.py Remove an extra newline. 3 anos atrás
data.py Clean up _equal(). 3 anos atrás
databatch.py Add BatchedData support to DecodeLayer. 3 anos atrás
declayer.py Add BatchedData support to DecodeLayer. 3 anos atrás
decode.py Use torch.nn.Parameter(List) in decode. 3 anos atrás
dropout.py Remove unnecessary .detach() call in dropout_dense(). 3 anos atrás
fastconv.py Add matrix-multiply illustration. 3 anos atrás
input.py Fix for non-leaf .grad warning. 3 anos atrás
model.py Add TrainLoop. 3 anos atrás
normalize.py Fixes for bool sparse tensors. 3 anos atrás
sampling.py Fixes for the GPU. 3 anos atrás
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 3 anos atrás
trainprep.py Fixes for the GPU. 3 anos atrás
weights.py Bring more elements to icosagon. 4 anos atrás