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 ff4fb96bed Add CrossEntropyLoss and test_cross_entropy_loss_01().		5 роки тому
..
__init__.py	Work on icosagon.trainprep.	5 роки тому
convlayer.py	Use torch.nn.ModuleList in convlayer.	5 роки тому
convolve.py	Work on icosagon.	5 роки тому
data.py	Remove node_type_row/node_type_column as redundant in add_relation_type().	5 роки тому
declayer.py	Get test_decode_layer_01 to pass.	5 роки тому
decode.py	Use torch.nn.Parameter(List) in decode.	5 роки тому
dropout.py	Work on icosagon.	5 роки тому
input.py	Increase test coverage.	5 роки тому
loss.py	Add CrossEntropyLoss and test_cross_entropy_loss_01().	5 роки тому
normalize.py	New implementation of normalize for one/two node types and sparse/dense - good.	5 роки тому
sampling.py	Work on icosagon.trainprep.	5 роки тому
trainprep.py	Get test_decode_layer_01 to pass.	5 роки тому
weights.py	Bring more elements to icosagon.	5 роки тому