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!

Verlauf

Stanislaw Adaszewski a5b8701a0d Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.		vor 4 Jahren
..
unused	Rename test_loss.	vor 4 Jahren
test_batch.py	Add test_flatten_predictions_05().	vor 4 Jahren
test_convlayer.py	Add test_parameter_count_01().	vor 4 Jahren
test_convolve.py	Add test_dropout_graph_conv_activation_parameter_count_01().	vor 4 Jahren
test_data.py	Make _equal() much faster.	vor 4 Jahren
test_declayer.py	Add test_decode_layer_parameter_count_[01-03]().	vor 4 Jahren
test_decode.py	Add test_[dedicom,dist_mult,bilinear,inner_product]_decoder_parameter_count_01().	vor 4 Jahren
test_dropout.py	Bring more elements to icosagon.	vor 4 Jahren
test_input.py	Add test_[one_hot_]input_layer_parameter_count_01().	vor 4 Jahren
test_model.py	Add test_model_08().	vor 4 Jahren
test_normalize.py	New implementation of normalize for one/two node types and sparse/dense - good.	vor 4 Jahren
test_sampling.py	Change test in test_unigram_03().	vor 4 Jahren
test_trainloop.py	Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.	vor 4 Jahren
test_trainprep.py	Fix test names in test_trainprep.	vor 4 Jahren
test_weights.py	Work on declayer.	vor 4 Jahren