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 2eff854467 Start working on FastLoop.		5年前
..
unused	Remove loss as no longer necessary.	5年前
__init__.py	Work on icosagon.trainprep.	5年前
batch.py	Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices().	5年前
bulkdec.py	Fix a typo.	5年前
compile.py	Performance tests.	5年前
convlayer.py	Add BatchedData support to DecodeLayer.	5年前
convolve.py	Remove an extra newline.	5年前
data.py	Clean up _equal().	5年前
databatch.py	Add BatchedData support to DecodeLayer.	5年前
declayer.py	Add BatchedData support to DecodeLayer.	5年前
decode.py	Use torch.nn.Parameter(List) in decode.	5年前
dropout.py	Remove unnecessary .detach() call in dropout_dense().	5年前
fastconv.py	Reimplement FastConvLayer.	5年前
fastloop.py	Start working on FastLoop.	5年前
fastmodel.py	Add test_fast_model_01().	5年前
input.py	Fix for non-leaf .grad warning.	5年前
model.py	Add TrainLoop.	5年前
normalize.py	Fixes for bool sparse tensors.	5年前
sampling.py	Fixes for the GPU.	5年前
trainloop.py	Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes.	5年前
trainprep.py	Fixes for the GPU.	5年前
weights.py	Bring more elements to icosagon.	5年前