decagon-pytorch

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!

Stanislaw Adaszewski 6cf3175950 Remove an extra newline.		4年前
..
unused	Remove loss as no longer necessary.	4年前
__init__.py	Work on icosagon.trainprep.	4年前
batch.py	Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices().	4年前
compile.py	Performance tests.	4年前
convlayer.py	Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.	4年前
convolve.py	Remove an extra newline.	4年前
data.py	Clean up _equal().	4年前
declayer.py	Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.	4年前
decode.py	Use torch.nn.Parameter(List) in decode.	4年前
dropout.py	Fix for sparse_coo_tensor().	4年前
input.py	Fix for non-leaf .grad warning.	4年前
model.py	Add TrainLoop.	4年前
normalize.py	Fixes for bool sparse tensors.	4年前
sampling.py	Fixes for the GPU.	4年前
trainloop.py	Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.	4年前
trainprep.py	Fixes for the GPU.	4年前
weights.py	Bring more elements to icosagon.	4年前