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!
Vous ne pouvez pas sélectionner plus de 25 sujets Les noms de sujets doivent commencer par une lettre ou un nombre, peuvent contenir des tirets ('-') et peuvent comporter jusqu'à 35 caractères.
Stanislaw Adaszewski c210be41b3 Add databatch. il y a 4 ans
..
unused Remove loss as no longer necessary. il y a 4 ans
__init__.py Work on icosagon.trainprep. il y a 4 ans
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). il y a 4 ans
bulkdec.py Add bulkdec. il y a 4 ans
compile.py Performance tests. il y a 4 ans
convlayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. il y a 4 ans
convolve.py Remove an extra newline. il y a 4 ans
data.py Clean up _equal(). il y a 4 ans
databatch.py Add databatch. il y a 4 ans
declayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. il y a 4 ans
decode.py Use torch.nn.Parameter(List) in decode. il y a 4 ans
dropout.py Remove unnecessary .detach() call in dropout_dense(). il y a 4 ans
input.py Fix for non-leaf .grad warning. il y a 4 ans
model.py Add TrainLoop. il y a 4 ans
normalize.py Fixes for bool sparse tensors. il y a 4 ans
sampling.py Fixes for the GPU. il y a 4 ans
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. il y a 4 ans
trainprep.py Fixes for the GPU. il y a 4 ans
weights.py Bring more elements to icosagon. il y a 4 ans