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