aiexperiments-ai-duet

History

python273 3af4766358 Add Dockerfile; fix predict.py and server.py		2016-11-17 07:33:16 +03:00
..
__init__.py	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
BUILD	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
melody_rnn_create_dataset_test.py	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
melody_rnn_create_dataset.py	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
melody_rnn_generate.py	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
melody_rnn_graph_test.py	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
melody_rnn_graph.py	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
melody_rnn_sequence_generator.py	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
melody_rnn_train.py	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
primer.mid	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00
README.md	Add Dockerfile; fix predict.py and server.py	2016-11-17 07:33:16 +03:00

README.md

This directory contains code and content that is shared by multiple models.

The primer.mid MIDI file is an original three bar long monophonic melody. It can be used as a priming melody when generating melodies with any of the melody RNN models. Example usage:

bazel build magenta/models/basic_rnn:basic_rnn_generate

./bazel-bin/magenta/models/basic_rnn/basic_rnn_generate \
--run_dir=/tmp/basic_rnn/logdir/run1 \
--output_dir=/tmp/basic_rnn/generated \
--num_outputs=10 \
--num_steps=128 \
--primer_midi=<absolute path to primer.mid>