def read_wav(wav_file, output_file): in_processor = RNNPianoNoteProcessor() peak_picking = PeakPickingProcessor(threshold=0.35, smooth=0.09, combine=0.05) #output = write_notes output = write_midi out_processor = [peak_picking, output] processor = IOProcessor(in_processor, out_processor) processor.process(wav_file, output_file)
def beat_extractor(queue_beat): kwargs = dict( fps=100, correct=True, infile=None, outfile=None, max_bpm=170, min_bpm=60, #nn_files = [BEATS_LSTM[0]], transition_lambda=100, num_frames=1, online=True, verbose=1) def beat_callback(beats, output=None): if len(beats) > 0: # Do something with the beat (for now, just print the array to stdout) queue_beat.put(beats[0]) #print(beats) #print('Process to write betas: %s' % os.getpid()) in_processor = RNNBeatProcessor(**kwargs) beat_processor = DBNBeatTrackingProcessor(**kwargs) out_processor = [beat_processor, beat_callback] processor = IOProcessor(in_processor, out_processor) process_online(processor, **kwargs)
def main(): """ music_process """ # define parser p = argparse.ArgumentParser( formatter_class=argparse.RawDescriptionHelpFormatter, description=''' python music_process.py ./data/Jian_chrous.wav -o ./data/jian_beat.txt ''') # version p.add_argument('--version', action='version', version='FDGame-music-process-0.1') # input/output options # p.add_argument('single') # p.add_argument('./data/Jian_chrous.wav') io_arguments_single(p) ActivationsProcessor.add_arguments(p) # signal processing arguments SignalProcessor.add_arguments(p, norm=False, gain=0) # peak picking arguments DBNBeatTrackingProcessor.add_arguments(p) NeuralNetworkEnsemble.add_arguments(p, nn_files=None) # parse arguments args = p.parse_args() # set immutable arguments args.fps = 100 # print arguments if args.verbose: print(args) # input processor if args.load: # load the activations from file in_processor = ActivationsProcessor(mode='r', **vars(args)) else: # use a RNN to predict the beats in_processor = RNNBeatProcessor(**vars(args)) # output processor if args.save: # save the RNN beat activations to file out_processor = ActivationsProcessor(mode='w', **vars(args)) else: # track the beats with a DBN and output them beat_processor = DBNBeatTrackingProcessor(**vars(args)) out_processor = [beat_processor, write_beats] # create an IOProcessor processor = IOProcessor(in_processor, out_processor) # and call the processing function args.func(processor, **vars(args))
def main(): parser = argparse.ArgumentParser("merges a csv of survey responses, and a sqlite3 database of responses.") parser.add_argument("dumpfile", help="The output of \"flask dumpdb --outfile=dump.json\"") parser.add_argument("samples", help="folder with the actual mp3 samples") parser.add_argument('outfile', help='output file (EX: train_dataset.npz)') parser.add_argument('--fps', action='store', type=float, default=100, help='frames per second [default=100]') args = parser.parse_args() trials = json.load(open(args.dumpfile, "r"))['dataset'] data = [] labels = [] sample_names = [] for trial in trials: final_response = [r['timestamp'] for r in trial['data']['final_response']] sample_url = trial['url'] o = urlparse(sample_url) sample_name = os.path.split(o.path)[-1] preprocessor = TfRhythmicGroupingPreProcessor() infile = os.path.join(args.samples, sample_name) print(infile) label_processor = LabelOutputProcessor(final_response, args.fps) # create an IOProcessor processor = IOProcessor(preprocessor, label_processor) sample_data, sample_labels = _process((processor, infile, None, vars(args))) data.append(sample_data) if sample_data.shape != data[0].shape: print("Shapes do not match, ", data[0].shape, sample_data.shape, "Skipping.") data.pop() continue labels.append(sample_labels) sample_names.append(sample_name) np.savez(args.outfile, x=data, labels=labels, sample_names=sample_names)
def main(): """DBNBeatTracker""" # define parser p = argparse.ArgumentParser( formatter_class=argparse.RawDescriptionHelpFormatter, description=''' The DBNBeatTracker.py program detects all beats in an audio file according to the method described in: "A Multi-Model Approach to Beat Tracking Considering Heterogeneous Music Styles" Sebastian Böck, Florian Krebs and Gerhard Widmer. Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR), 2014. It does not use the multi-model (Section 2.2.) and selection stage (Section 2.3), i.e. this version corresponds to the pure DBN version of the algorithm for which results are given in Table 2. Instead of the originally proposed state space and transition model for the DBN, the following is used: "An Efficient State Space Model for Joint Tempo and Meter Tracking" Florian Krebs, Sebastian Böck and Gerhard Widmer. Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR), 2015. This program can be run in 'single' file mode to process a single audio file and write the detected beats to STDOUT or the given output file. $ DBNBeatTracker.py single INFILE [-o OUTFILE] If multiple audio files should be processed, the program can also be run in 'batch' mode to save the detected beats to files with the given suffix. $ DBNBeatTracker.py batch [-o OUTPUT_DIR] [-s OUTPUT_SUFFIX] FILES If no output directory is given, the program writes the files with the detected beats to the same location as the audio files. The 'pickle' mode can be used to store the used parameters to be able to exactly reproduce experiments. ''') # version p.add_argument('--version', action='version', version='DBNBeatTracker.py.2016') # input/output options io_arguments(p, output_suffix='.beats.txt', online=True) ActivationsProcessor.add_arguments(p) # signal processing arguments SignalProcessor.add_arguments(p, norm=False, gain=0) # peak picking arguments DBNBeatTrackingProcessor.add_arguments(p) NeuralNetworkEnsemble.add_arguments(p, nn_files=None) # parse arguments args = p.parse_args() # set immutable arguments args.fps = 100 # print arguments if args.verbose: print(args) # input processor if args.load: # load the activations from file in_processor = ActivationsProcessor(mode='r', **vars(args)) else: # use a RNN to predict the beats in_processor = RNNBeatProcessor(**vars(args)) # output processor if args.save: # save the RNN beat activations to file out_processor = ActivationsProcessor(mode='w', **vars(args)) else: # track the beats with a DBN beat_processor = DBNBeatTrackingProcessor(**vars(args)) # output handler from madmom.utils import write_events as writer # sequentially process everything out_processor = [beat_processor, writer] # create an IOProcessor processor = IOProcessor(in_processor, out_processor) # and call the processing function args.func(processor, **vars(args))
def main(): """DBNBeatTracker""" # define parser p = argparse.ArgumentParser( formatter_class=argparse.RawDescriptionHelpFormatter, description=''' The DBNBeatTracker program detects all beats in an audio file according to the method described in: "A Multi-Model Approach to Beat Tracking Considering Heterogeneous Music Styles" Sebastian Böck, Florian Krebs and Gerhard Widmer. Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR), 2014. It does not use the multi-model (Section 2.2.) and selection stage (Section 2.3), i.e. this version corresponds to the pure DBN version of the algorithm for which results are given in Table 2. Instead of the originally proposed state space and transition model for the DBN, the following is used: "An Efficient State Space Model for Joint Tempo and Meter Tracking" Florian Krebs, Sebastian Böck and Gerhard Widmer. Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR), 2015. This program can be run in 'single' file mode to process a single audio file and write the detected beats to STDOUT or the given output file. $ DBNBeatTracker single INFILE [-o OUTFILE] If multiple audio files should be processed, the program can also be run in 'batch' mode to save the detected beats to files with the given suffix. $ DBNBeatTracker batch [-o OUTPUT_DIR] [-s OUTPUT_SUFFIX] FILES If no output directory is given, the program writes the files with the detected beats to the same location as the audio files. The 'pickle' mode can be used to store the used parameters to be able to exactly reproduce experiments. ''') # version p.add_argument('--version', action='version', version='DBNBeatTracker.2016') # input/output options io_arguments(p, output_suffix='.beats.txt', online=True) ActivationsProcessor.add_arguments(p) # signal processing arguments SignalProcessor.add_arguments(p, norm=False, gain=0) # peak picking arguments DBNBeatTrackingProcessor.add_arguments(p) NeuralNetworkEnsemble.add_arguments(p, nn_files=None) # parse arguments args = p.parse_args() # set immutable arguments args.fps = 100 # print arguments if args.verbose: print(args) print("The following mesxxsage shows the args :\n", args, "\n\n\nshows the vars(args) message:\n", vars(args)) ''' The args's message: Namespace(correct=True, fps=100, func=<function process_online at 0x00000000055E9AC8>, gain=0, infile=None, load=False, max_bpm=215.0, min_bpm=55.0, nn_files=None, norm=False, num_frames=1, num_tempi=None, num_threads=1, observation_lambda=16, online=True, origin='stream', outfile=<open file '<stdout>', mode 'w' at 0x0000000002DFB0C0>, save=False, sep=None, threshold=0, transition_lambda=100, verbose=None) ''' # input processor if args.load: # load the activations from file in_processor = ActivationsProcessor(mode='r', **vars(args)) else: # use a RNN to predict the beats in_processor = RNNBeatProcessor(**vars(args)) # output processor if args.save: # save the RNN beat activations to file out_processor = ActivationsProcessor(mode='w', **vars(args)) else: # track the beats with a DBN and output them beat_processor = DBNBeatTrackingProcessor(**vars(args)) out_processor = [beat_processor, write_beats] print("ok") # create an IOProcessor processor = IOProcessor(in_processor, out_processor) # and call the processing function args.func(processor, **vars(args))
"Otherwise the model's performance will be very poor.\n") # initialize network print("Initializing tagging network ...") model = select_model(args.model) net = model.build_model(batch_size=1) # initialize neural network TAGGER = Network(net, print_architecture=False) # load model parameters network if args.params is not None: dump_file = args.params else: out_path = os.path.join(os.path.join(EXP_ROOT), model.EXP_NAME) dump_file, log_file = get_dump_file_paths(out_path, 1) dump_file = dump_file.replace(".pkl", "_it0.pkl") print("Loading model from: %s" % dump_file) TAGGER.load(dump_file) # set prediction rate PREDICT_EVERY_K = args.predict_every_k # dummy prediction to compile model print("Compiling prediction function ...") TAGGER.predict(SLIDING_WINDOW[np.newaxis, np.newaxis]) print("Starting prediction loop ...") processor = IOProcessor(in_processor=processor_pipeline2, out_processor=output_processor) process_online(processor, infile=None, outfile=None, sample_rate=32000)
def main(): parser = argparse.ArgumentParser( "merges a csv of survey responses, and a sqlite3 database of responses." ) parser.add_argument( "dumpfile", help="The output of \"flask dumpdb --outfile=dump.json\"") parser.add_argument("samples", help="folder with the actual mp3 samples") parser.add_argument('outfile', help='output file (EX: train_dataset.npz)') parser.add_argument('--fps', action='store', type=float, default=100, help='frames per second [default=100]') args = parser.parse_args() experiments = util.load_by_url(args.dumpfile) responses_by_url = util.get_final_responses_list(experiments) # trials = json.load(open(args.dumpfile, "r"))['dataset'] n_features = 314 n_frames = 800 data = [] labels = [] sample_names = [] for sample_url, final_responses in responses_by_url.items(): o = urlparse(sample_url) sample_name = os.path.split(o.path)[-1] preprocessor = TfRhythmicGroupingPreProcessor() infile = os.path.join(args.samples, sample_name) print(infile) label_processor = LabelOutputProcessor(final_responses, args.fps) # create an IOProcessor processor = IOProcessor(preprocessor, label_processor) sample_data, sample_labels = _process( (processor, infile, None, vars(args))) if sample_data.shape[0] < n_frames or sample_data.shape[ 1] != n_features: print("SKIPPING: Shapes is {} but it must be (>={}, {}), ".format( sample_data.shape, n_frames, n_features)) continue sample_data = np.expand_dims(sample_data, axis=2) data.append(sample_data[:n_frames]) labels.append(sample_labels[:n_frames]) sample_names.append(sample_name) print("DATASET:") print('{} clips'.format(len(data))) print('{} frames of audio at {} fps'.format(n_frames, args.fps)) print('{} features per frame'.format(n_features)) print("saving {} ...".format(args.outfile)) data = np.array(data) labels = np.array(labels) np.savez(args.outfile, x=data, labels=labels, sample_names=sample_names) print("done.")