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