Age | Commit message (Collapse) | Author | |
---|---|---|---|
2019-05-29 | Adding instructions on training. | Gregor Richards | |
2019-05-29 | Neural network model files | Gregor Richards | |
Extending the neural network dumper to dump to a simple text file format, and adding reader functions to read a neural network description from a FILE *. | |||
2019-05-29 | Made dump_rnn output in nu format. | Gregor Richards | |
2017-09-08 | New features (#9) | Jean-Marc Valin | |
Also, adding an error^4 term to the loss function | |||
2017-08-14 | constraining the weights to +/- 0.5 so they can be quantized with 8 bits | Jean-Marc Valin | |
2017-08-08 | Initial weights | Jean-Marc Valin | |
2017-08-04 | toplevel function | Jean-Marc Valin | |
2017-08-04 | more header cleanup | Jean-Marc Valin | |
2017-08-04 | automate header generation too | Jean-Marc Valin | |
2017-08-04 | RNN C code | Jean-Marc Valin | |
2017-08-03 | Keras training code | Jean-Marc Valin | |