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!
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Stanislaw Adaszewski c210be41b3 Add databatch. 4 years ago
..
unused Remove loss as no longer necessary. 4 years ago
__init__.py Work on icosagon.trainprep. 4 years ago
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). 4 years ago
bulkdec.py Add bulkdec. 4 years ago
compile.py Performance tests. 4 years ago
convlayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 years ago
convolve.py Remove an extra newline. 4 years ago
data.py Clean up _equal(). 4 years ago
databatch.py Add databatch. 4 years ago
declayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 years ago
decode.py Use torch.nn.Parameter(List) in decode. 4 years ago
dropout.py Remove unnecessary .detach() call in dropout_dense(). 4 years ago
input.py Fix for non-leaf .grad warning. 4 years ago
model.py Add TrainLoop. 4 years ago
normalize.py Fixes for bool sparse tensors. 4 years ago
sampling.py Fixes for the GPU. 4 years ago
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 4 years ago
trainprep.py Fixes for the GPU. 4 years ago
weights.py Bring more elements to icosagon. 4 years ago