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 1ee89509ee Fixes for bool sparse tensors. преди 3 години
..
unused Remove loss as no longer necessary. преди 3 години
__init__.py Work on icosagon.trainprep. преди 4 години
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). преди 3 години
compile.py Performance tests. преди 3 години
convlayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. преди 3 години
convolve.py Fixes for the GPU. преди 3 години
data.py Clean up _equal(). преди 3 години
declayer.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. преди 3 години
decode.py Use torch.nn.Parameter(List) in decode. преди 3 години
dropout.py Fix for sparse_coo_tensor(). преди 3 години
input.py Fix for non-leaf .grad warning. преди 3 години
model.py Add TrainLoop. преди 3 години
normalize.py Fixes for bool sparse tensors. преди 3 години
sampling.py Fixes for the GPU. преди 3 години
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. преди 3 години
trainprep.py Fixes for the GPU. преди 3 години
weights.py Bring more elements to icosagon. преди 4 години