def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorException('This model supports at most one input_sections message, but got %s' %len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorException('This model supports only 1 generate_sections message, but got %s' %len(generator_options.generate_sections)) qpm = (input_sequence.tempos[0].qpm if input_sequence and input_sequence.tempos else mm.DEFAULT_QUARTERS_PER_MINUTE) steps_per_second = mm.steps_per_quarter_to_steps_per_second(self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence(input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step(input_section.start_time, steps_per_second, quantize_cutoff=0) else: primer_sequence = input_sequence input_start_step = 0 last_end_time = (max(n.end_time for n in primer_sequence.notes) if primer_sequence.notes else 0) if last_end_time > generate_section.start_time: raise mm.SequenceGeneratorException('start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) quantized_sequence = mm.quantize_note_sequence(primer_sequence, self.steps_per_quarter) extracted_melodies, _ = mm.extract_melodies(quantized_sequence, search_start_step=input_start_step, min_bars=0,min_unique_pitches=1, gap_bars=float('inf'),ignore_polyphonic_notes=True) assert len(extracted_melodies) <= 1 start_step = mm.quantize_to_step( generate_section.start_time, steps_per_second, quantize_cutoff=0) end_step = mm.quantize_to_step(generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_melodies and extracted_melodies[0]: melody = extracted_melodies[0] else: steps_per_bar = int(mm.steps_per_bar_in_quantized_sequence(quantized_sequence)) melody = mm.Melody([],start_step=max(0, start_step - 1),steps_per_bar=steps_per_bar,steps_per_quarter=self.steps_per_quarter) melody.set_length(start_step - melody.start_step) arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) generated_melody = self._model.generate_melody(end_step - melody.start_step, melody, **args) generated_sequence = generated_melody.to_sequence(qpm=qpm) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorError( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorError( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) # This sequence will be quantized later, so it is guaranteed to have only 1 # tempo. qpm = mm.DEFAULT_QUARTERS_PER_MINUTE if input_sequence.tempos: qpm = input_sequence.tempos[0].qpm steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence(input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step(input_section.start_time, steps_per_second, quantize_cutoff=0) else: primer_sequence = input_sequence input_start_step = 0 if primer_sequence.notes: last_end_time = max(n.end_time for n in primer_sequence.notes) else: last_end_time = 0 if last_end_time > generate_section.start_time: raise mm.SequenceGeneratorError( 'Got GenerateSection request for section that is before or equal to ' 'the end of the NoteSequence. This model can only extend sequences. ' 'Requested start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_primer_sequence = mm.quantize_note_sequence( primer_sequence, self.steps_per_quarter) extracted_seqs, _ = pianoroll_pipeline.extract_pianoroll_sequences( quantized_primer_sequence, start_step=input_start_step) assert len(extracted_seqs) <= 1 generate_start_step = mm.quantize_to_step(generate_section.start_time, steps_per_second, quantize_cutoff=0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. generate_end_step = mm.quantize_to_step(generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_seqs and extracted_seqs[0]: pianoroll_seq = extracted_seqs[0] else: raise ValueError('No priming pianoroll could be extracted.') # Ensure that the track extends up to the step we want to start generating. pianoroll_seq.set_length(generate_start_step - pianoroll_seq.start_step) # Extract generation arguments from generator options. arg_types = { 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) total_steps = pianoroll_seq.num_steps + (generate_end_step - generate_start_step) pianoroll_seq = self._model.generate_pianoroll_sequence( total_steps, pianoroll_seq, **args) pianoroll_seq.set_length(total_steps) generated_sequence = pianoroll_seq.to_sequence(qpm=qpm) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise sequence_generator.SequenceGeneratorError( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise sequence_generator.SequenceGeneratorError( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) # This sequence will be quantized later, so it is guaranteed to have only 1 # tempo. qpm = mm.DEFAULT_QUARTERS_PER_MINUTE if input_sequence.tempos: qpm = input_sequence.tempos[0].qpm steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence(input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step(input_section.start_time, steps_per_second, quantize_cutoff=0) else: primer_sequence = input_sequence input_start_step = 0 if primer_sequence.notes: last_end_time = max(n.end_time for n in primer_sequence.notes) else: last_end_time = 0 if last_end_time > generate_section.start_time: raise sequence_generator.SequenceGeneratorError( 'Got GenerateSection request for section that is before or equal to ' 'the end of the NoteSequence. This model can only extend sequences. ' 'Requested start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_primer_sequence = mm.quantize_note_sequence( primer_sequence, self.steps_per_quarter) extracted_seqs, _ = polyphony_lib.extract_polyphonic_sequences( quantized_primer_sequence, start_step=input_start_step) assert len(extracted_seqs) <= 1 generate_start_step = mm.quantize_to_step(generate_section.start_time, steps_per_second, quantize_cutoff=0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. generate_end_step = mm.quantize_to_step(generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_seqs and extracted_seqs[0]: poly_seq = extracted_seqs[0] else: # If no track could be extracted, create an empty track that starts at the # requested generate_start_step. This will result in a sequence that # contains only the START token. poly_seq = polyphony_lib.PolyphonicSequence( steps_per_quarter=(quantized_primer_sequence.quantization_info. steps_per_quarter), start_step=generate_start_step) # Ensure that the track extends up to the step we want to start generating. poly_seq.set_length(generate_start_step - poly_seq.start_step) # Trim any trailing end events to prepare the sequence for more events to be # appended during generation. poly_seq.trim_trailing_end_events() # Extract generation arguments from generator options. arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) # Inject the priming sequence as melody in the output of the generator, if # requested. # This option starts with no_ so that if it is unspecified (as will be the # case when used with the midi interface), the default will be to inject the # primer. if not (generator_options.args['no_inject_primer_during_generation']. bool_value): melody_to_inject = copy.deepcopy(poly_seq) if generator_options.args['condition_on_primer'].bool_value: inject_start_step = poly_seq.num_steps else: # 0 steps because we'll overwrite poly_seq with a blank sequence below. inject_start_step = 0 args['modify_events_callback'] = functools.partial( _inject_melody, melody_to_inject, inject_start_step) # If we don't want to condition on the priming sequence, then overwrite # poly_seq with a blank sequence to feed into the generator. if not generator_options.args['condition_on_primer'].bool_value: poly_seq = polyphony_lib.PolyphonicSequence( steps_per_quarter=(quantized_primer_sequence.quantization_info. steps_per_quarter), start_step=generate_start_step) poly_seq.trim_trailing_end_events() total_steps = poly_seq.num_steps + (generate_end_step - generate_start_step) while poly_seq.num_steps < total_steps: # Assume it takes ~5 rnn steps to generate one quantized step. # Can't know for sure until generation is finished because the number of # notes per quantized step is variable. steps_to_gen = total_steps - poly_seq.num_steps rnn_steps_to_gen = 5 * steps_to_gen tf.logging.info( 'Need to generate %d more steps for this sequence, will try asking ' 'for %d RNN steps' % (steps_to_gen, rnn_steps_to_gen)) poly_seq = self._model.generate_polyphonic_sequence( len(poly_seq) + rnn_steps_to_gen, poly_seq, **args) poly_seq.set_length(total_steps) if generator_options.args['condition_on_primer'].bool_value: generated_sequence = poly_seq.to_sequence(qpm=qpm) else: # Specify a base_note_sequence because the priming sequence was not # included in poly_seq. generated_sequence = poly_seq.to_sequence( qpm=qpm, base_note_sequence=copy.deepcopy(primer_sequence)) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorException( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorException( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) qpm = (input_sequence.tempos[0].qpm if input_sequence and input_sequence.tempos else mm.DEFAULT_QUARTERS_PER_MINUTE) steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence(input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step(input_section.start_time, steps_per_second) else: primer_sequence = input_sequence input_start_step = 0 last_end_time = (max( n.end_time for n in primer_sequence.notes) if primer_sequence.notes else 0) if last_end_time > generate_section.start_time: raise mm.SequenceGeneratorException( 'Got GenerateSection request for section that is before the end of ' 'the NoteSequence. This model can only extend sequences. Requested ' 'start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_sequence = mm.quantize_note_sequence(primer_sequence, self.steps_per_quarter) # Setting gap_bars to infinite ensures that the entire input will be used. extracted_melodies, _ = mm.extract_melodies( quantized_sequence, search_start_step=input_start_step, min_bars=0, min_unique_pitches=1, gap_bars=float('inf'), ignore_polyphonic_notes=True) assert len(extracted_melodies) <= 1 start_step = mm.quantize_to_step(generate_section.start_time, steps_per_second) end_step = mm.quantize_to_step(generate_section.end_time, steps_per_second) if extracted_melodies and extracted_melodies[0]: melody = extracted_melodies[0] else: # If no melody could be extracted, create an empty melody that starts 1 # step before the request start_step. This will result in 1 step of # silence when the melody is extended below. steps_per_bar = int( mm.steps_per_bar_in_quantized_sequence(quantized_sequence)) melody = mm.Melody([], start_step=max(0, start_step - 1), steps_per_bar=steps_per_bar, steps_per_quarter=self.steps_per_quarter) # Ensure that the melody extends up to the step we want to start generating. melody.set_length(start_step - melody.start_step) # Extract generation arguments from generator options. arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) generated_melody = self._model.generate_melody( end_step - melody.start_step, melody, **args) generated_sequence = generated_melody.to_sequence(qpm=qpm) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorException( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorException( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) qpm = (input_sequence.tempos[0].qpm if input_sequence and input_sequence.tempos else mm.DEFAULT_QUARTERS_PER_MINUTE) steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence( input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step( input_section.start_time, steps_per_second, quantize_cutoff=0) else: primer_sequence = input_sequence input_start_step = 0 last_end_time = (max(n.end_time for n in primer_sequence.notes) if primer_sequence.notes else 0) if last_end_time > generate_section.start_time: raise mm.SequenceGeneratorException( 'Got GenerateSection request for section that is before the end of ' 'the NoteSequence. This model can only extend sequences. Requested ' 'start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_sequence = mm.quantize_note_sequence( primer_sequence, self.steps_per_quarter) # Setting gap_bars to infinite ensures that the entire input will be used. extracted_melodies, _ = mm.extract_melodies( quantized_sequence, search_start_step=input_start_step, min_bars=0, min_unique_pitches=1, gap_bars=float('inf'), ignore_polyphonic_notes=True) assert len(extracted_melodies) <= 1 start_step = mm.quantize_to_step( generate_section.start_time, steps_per_second, quantize_cutoff=0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. end_step = mm.quantize_to_step( generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_melodies and extracted_melodies[0]: melody = extracted_melodies[0] else: # If no melody could be extracted, create an empty melody that starts 1 # step before the request start_step. This will result in 1 step of # silence when the melody is extended below. steps_per_bar = int( mm.steps_per_bar_in_quantized_sequence(quantized_sequence)) melody = mm.Melody([], start_step=max(0, start_step - 1), steps_per_bar=steps_per_bar, steps_per_quarter=self.steps_per_quarter) # Ensure that the melody extends up to the step we want to start generating. melody.set_length(start_step - melody.start_step) # Extract generation arguments from generator options. arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) generated_melody = self._model.generate_melody( end_step - melody.start_step, melody, **args) generated_sequence = generated_melody.to_sequence(qpm=qpm) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise sequence_generator.SequenceGeneratorError( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise sequence_generator.SequenceGeneratorError( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) if input_sequence and input_sequence.tempos: qpm = input_sequence.tempos[0].qpm else: qpm = mm.DEFAULT_QUARTERS_PER_MINUTE steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence(input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step(input_section.start_time, steps_per_second, quantize_cutoff=0.0) else: primer_sequence = input_sequence input_start_step = 0 if primer_sequence.notes: last_end_time = max(n.end_time for n in primer_sequence.notes) else: last_end_time = 0 if last_end_time > generate_section.start_time: raise sequence_generator.SequenceGeneratorError( 'Got GenerateSection request for section that is before the end of ' 'the NoteSequence. This model can only extend sequences. Requested ' 'start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_sequence = mm.quantize_note_sequence(primer_sequence, self.steps_per_quarter) # Setting gap_bars to infinite ensures that the entire input will be used. extracted_drum_tracks, _ = drum_pipelines.extract_drum_tracks( quantized_sequence, search_start_step=input_start_step, min_bars=0, gap_bars=float('inf'), ignore_is_drum=True) assert len(extracted_drum_tracks) <= 1 start_step = mm.quantize_to_step(generate_section.start_time, steps_per_second, quantize_cutoff=0.0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. end_step = mm.quantize_to_step(generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_drum_tracks and extracted_drum_tracks[0]: drums = extracted_drum_tracks[0] else: # If no drum track could be extracted, create an empty drum track that # starts 1 step before the request start_step. This will result in 1 step # of silence when the drum track is extended below. steps_per_bar = int( mm.steps_per_bar_in_quantized_sequence(quantized_sequence)) drums = mm.DrumTrack([], start_step=max(0, start_step - 1), steps_per_bar=steps_per_bar, steps_per_quarter=self.steps_per_quarter) # Ensure that the drum track extends up to the step we want to start # generating. drums.set_length(start_step - drums.start_step) # Extract generation arguments from generator options. arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) generated_drums = self._model.generate_drum_track( end_step - drums.start_step, drums, **args) generated_sequence = generated_drums.to_sequence(qpm=qpm) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorError( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorError( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) if input_sequence and input_sequence.tempos: qpm = input_sequence.tempos[0].qpm else: qpm = mm.DEFAULT_QUARTERS_PER_MINUTE steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: # Use primer melody from input section only. Take backing chords from # beginning of input section through end of generate section. input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence(input_sequence, input_section.start_time, input_section.end_time) backing_sequence = mm.trim_note_sequence(input_sequence, input_section.start_time, generate_section.end_time) input_start_step = mm.quantize_to_step(input_section.start_time, steps_per_second, quantize_cutoff=0.0) else: # No input section. Take primer melody from the beginning of the sequence # up until the start of the generate section. primer_sequence = mm.trim_note_sequence( input_sequence, 0.0, generate_section.start_time) backing_sequence = mm.trim_note_sequence(input_sequence, 0.0, generate_section.end_time) input_start_step = 0 if primer_sequence.notes: last_end_time = max(n.end_time for n in primer_sequence.notes) else: last_end_time = 0 if last_end_time >= generate_section.start_time: raise mm.SequenceGeneratorError( 'Got GenerateSection request for section that is before or equal to ' 'the end of the input section. This model can only extend melodies. ' 'Requested start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming and backing sequences. quantized_primer_sequence = mm.quantize_note_sequence( primer_sequence, self.steps_per_quarter) quantized_backing_sequence = mm.quantize_note_sequence( backing_sequence, self.steps_per_quarter) # Setting gap_bars to infinite ensures that the entire input will be used. extracted_melodies, _ = mm.extract_melodies( quantized_primer_sequence, search_start_step=input_start_step, min_bars=0, min_unique_pitches=1, gap_bars=float('inf'), ignore_polyphonic_notes=True) assert len(extracted_melodies) <= 1 start_step = mm.quantize_to_step(generate_section.start_time, steps_per_second, quantize_cutoff=0.0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. end_step = mm.quantize_to_step(generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_melodies and extracted_melodies[0]: melody = extracted_melodies[0] else: # If no melody could be extracted, create an empty melody that starts 1 # step before the request start_step. This will result in 1 step of # silence when the melody is extended below. steps_per_bar = int( mm.steps_per_bar_in_quantized_sequence( quantized_primer_sequence)) melody = mm.Melody([], start_step=max(0, start_step - 1), steps_per_bar=steps_per_bar, steps_per_quarter=self.steps_per_quarter) extracted_chords, _ = mm.extract_chords(quantized_backing_sequence) chords = extracted_chords[0] # Make sure that chords and melody start on the same step. if chords.start_step < melody.start_step: chords.set_length( len(chords) - melody.start_step + chords.start_step) assert chords.end_step == end_step # Ensure that the melody extends up to the step we want to start generating. melody.set_length(start_step - melody.start_step) # Extract generation arguments from generator options. arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) generated_melody = self._model.generate_melody(melody, chords, **args) generated_lead_sheet = mm.LeadSheet(generated_melody, chords) generated_sequence = generated_lead_sheet.to_sequence(qpm=qpm) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorError( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorError( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) # This sequence will be quantized later, so it is guaranteed to have only 1 # tempo. qpm = mm.DEFAULT_QUARTERS_PER_MINUTE if input_sequence.tempos: qpm = input_sequence.tempos[0].qpm steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence( input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step( input_section.start_time, steps_per_second, quantize_cutoff=0) else: primer_sequence = input_sequence input_start_step = 0 if primer_sequence.notes: last_end_time = max(n.end_time for n in primer_sequence.notes) else: last_end_time = 0 if last_end_time > generate_section.start_time: raise mm.SequenceGeneratorError( 'Got GenerateSection request for section that is before or equal to ' 'the end of the NoteSequence. This model can only extend sequences. ' 'Requested start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_primer_sequence = mm.quantize_note_sequence( primer_sequence, self.steps_per_quarter) extracted_seqs, _ = mm.extract_pianoroll_sequences( quantized_primer_sequence, start_step=input_start_step) assert len(extracted_seqs) <= 1 generate_start_step = mm.quantize_to_step( generate_section.start_time, steps_per_second, quantize_cutoff=0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. generate_end_step = mm.quantize_to_step( generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_seqs and extracted_seqs[0]: pianoroll_seq = extracted_seqs[0] else: raise ValueError('No priming pianoroll could be extracted.') # Ensure that the track extends up to the step we want to start generating. pianoroll_seq.set_length(generate_start_step - pianoroll_seq.start_step) # Extract generation arguments from generator options. arg_types = { 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) total_steps = pianoroll_seq.num_steps + ( generate_end_step - generate_start_step) pianoroll_seq = self._model.generate_pianoroll_sequence( total_steps, pianoroll_seq, **args) pianoroll_seq.set_length(total_steps) generated_sequence = pianoroll_seq.to_sequence(qpm=qpm) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorException( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorException( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) # This sequence will be quantized later, so it is guaranteed to have only 1 # tempo. qpm = mm.DEFAULT_QUARTERS_PER_MINUTE if input_sequence.tempos: qpm = input_sequence.tempos[0].qpm steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.extract_subsequence( input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step( input_section.start_time, steps_per_second) else: primer_sequence = input_sequence input_start_step = 0 last_end_time = (max(n.end_time for n in primer_sequence.notes) if primer_sequence.notes else 0) if last_end_time > generate_section.start_time: raise mm.SequenceGeneratorException( 'Got GenerateSection request for section that is before or equal to ' 'the end of the NoteSequence. This model can only extend sequences. ' 'Requested start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_primer_sequence = mm.quantize_note_sequence( primer_sequence, self.steps_per_quarter) extracted_seqs, _ = polyphony_lib.extract_polyphonic_sequences( quantized_primer_sequence, start_step=input_start_step) assert len(extracted_seqs) <= 1 generate_start_step = mm.quantize_to_step( generate_section.start_time, steps_per_second) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. generate_end_step = mm.quantize_to_step( generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_seqs and extracted_seqs[0]: poly_seq = extracted_seqs[0] else: # If no track could be extracted, create an empty track that starts at the # requested generate_start_step. This will result in a sequence that # contains only the START token. poly_seq = polyphony_lib.PolyphonicSequence( steps_per_quarter=( quantized_primer_sequence.quantization_info.steps_per_quarter), start_step=generate_start_step) # Ensure that the track extends up to the step we want to start generating. poly_seq.set_length(generate_start_step - poly_seq.start_step) # Trim any trailing end events to prepare the sequence for more events to be # appended during generation. poly_seq.trim_trailing_end_events() # Extract generation arguments from generator options. arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) # Inject the priming sequence as melody in the output of the generator. # Note that start_step is 0 because we overwrite poly_seq below. If we # included the priming sequence in poly_seq, it would be poly_seq.num_steps. melody_to_inject = copy.deepcopy(poly_seq) args['modify_events_callback'] = partial( _inject_melody, melody_to_inject, 0) # Overwrite poly_seq with a blank sequence to feed into the generator so it # is conditioned only on the melody events that are injected as the sequence # is created. Otherwise, the generator would have to determine the most # likely sequence to follow a monophonic line, which is something not # present in the current training data (Bach Chorales). poly_seq = polyphony_lib.PolyphonicSequence( steps_per_quarter=( quantized_primer_sequence.quantization_info.steps_per_quarter), start_step=generate_start_step) poly_seq.trim_trailing_end_events() # If we wanted to include the priming sequence and didn't clear poly_seq # above, this is how we would calculate total_steps. # total_steps = poly_seq.num_steps + ( # generate_end_step - generate_start_step) total_steps = generate_end_step - generate_start_step while poly_seq.num_steps < total_steps: # Assume it takes ~5 rnn steps to generate one quantized step. # Can't know for sure until generation is finished because the number of # notes per quantized step is variable. steps_to_gen = total_steps - poly_seq.num_steps rnn_steps_to_gen = 5 * steps_to_gen tf.logging.info( 'Need to generate %d more steps for this sequence, will try asking ' 'for %d RNN steps' % (steps_to_gen, rnn_steps_to_gen)) poly_seq = self._model.generate_polyphonic_sequence( len(poly_seq) + rnn_steps_to_gen, poly_seq, **args) poly_seq.set_length(total_steps) # Specify a base_note_sequence because the priming sequence is not included # in poly_seq. If we did not clear poly_seq above, then we would not want to # specify a base_note_sequence. generated_sequence = poly_seq.to_sequence( qpm=qpm, base_note_sequence=copy.deepcopy(primer_sequence)) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorError( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorError( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) if input_sequence and input_sequence.tempos: qpm = input_sequence.tempos[0].qpm else: qpm = mm.DEFAULT_QUARTERS_PER_MINUTE steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: # Use primer melody from input section only. Take backing chords from # beginning of input section through end of generate section. input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence( input_sequence, input_section.start_time, input_section.end_time) backing_sequence = mm.trim_note_sequence( input_sequence, input_section.start_time, generate_section.end_time) input_start_step = mm.quantize_to_step( input_section.start_time, steps_per_second, quantize_cutoff=0.0) else: # No input section. Take primer melody from the beginning of the sequence # up until the start of the generate section. primer_sequence = mm.trim_note_sequence( input_sequence, 0.0, generate_section.start_time) backing_sequence = mm.trim_note_sequence( input_sequence, 0.0, generate_section.end_time) input_start_step = 0 if primer_sequence.notes: last_end_time = max(n.end_time for n in primer_sequence.notes) else: last_end_time = 0 if last_end_time >= generate_section.start_time: raise mm.SequenceGeneratorError( 'Got GenerateSection request for section that is before or equal to ' 'the end of the input section. This model can only extend melodies. ' 'Requested start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming and backing sequences. quantized_primer_sequence = mm.quantize_note_sequence( primer_sequence, self.steps_per_quarter) quantized_backing_sequence = mm.quantize_note_sequence( backing_sequence, self.steps_per_quarter) # Setting gap_bars to infinite ensures that the entire input will be used. extracted_melodies, _ = mm.extract_melodies( quantized_primer_sequence, search_start_step=input_start_step, min_bars=0, min_unique_pitches=1, gap_bars=float('inf'), ignore_polyphonic_notes=True) assert len(extracted_melodies) <= 1 start_step = mm.quantize_to_step( generate_section.start_time, steps_per_second, quantize_cutoff=0.0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. end_step = mm.quantize_to_step( generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_melodies and extracted_melodies[0]: melody = extracted_melodies[0] else: # If no melody could be extracted, create an empty melody that starts 1 # step before the request start_step. This will result in 1 step of # silence when the melody is extended below. steps_per_bar = int( mm.steps_per_bar_in_quantized_sequence(quantized_primer_sequence)) melody = mm.Melody([], start_step=max(0, start_step - 1), steps_per_bar=steps_per_bar, steps_per_quarter=self.steps_per_quarter) extracted_chords, _ = mm.extract_chords(quantized_backing_sequence) chords = extracted_chords[0] # Make sure that chords and melody start on the same step. if chords.start_step < melody.start_step: chords.set_length(len(chords) - melody.start_step + chords.start_step) assert chords.end_step == end_step # Ensure that the melody extends up to the step we want to start generating. melody.set_length(start_step - melody.start_step) # Extract generation arguments from generator options. arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) generated_melody = self._model.generate_melody(melody, chords, **args) generated_lead_sheet = mm.LeadSheet(generated_melody, chords) generated_sequence = generated_lead_sheet.to_sequence(qpm=qpm) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _generate(self, input_sequence, generator_options): if len(generator_options.input_sections) > 1: raise mm.SequenceGeneratorException( 'This model supports at most one input_sections message, but got %s' % len(generator_options.input_sections)) if len(generator_options.generate_sections) != 1: raise mm.SequenceGeneratorException( 'This model supports only 1 generate_sections message, but got %s' % len(generator_options.generate_sections)) # This sequence will be quantized later, so it is guaranteed to have only 1 # tempo. qpm = mm.DEFAULT_QUARTERS_PER_MINUTE if input_sequence.tempos: qpm = input_sequence.tempos[0].qpm steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence( input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step( input_section.start_time, steps_per_second, quantize_cutoff=0) else: primer_sequence = input_sequence input_start_step = 0 last_end_time = (max(n.end_time for n in primer_sequence.notes) if primer_sequence.notes else 0) if last_end_time > generate_section.start_time: raise mm.SequenceGeneratorException( 'Got GenerateSection request for section that is before or equal to ' 'the end of the NoteSequence. This model can only extend sequences. ' 'Requested start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_primer_sequence = mm.quantize_note_sequence( primer_sequence, self.steps_per_quarter) extracted_seqs, _ = polyphony_lib.extract_polyphonic_sequences( quantized_primer_sequence, start_step=input_start_step) assert len(extracted_seqs) <= 1 generate_start_step = mm.quantize_to_step( generate_section.start_time, steps_per_second, quantize_cutoff=0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. generate_end_step = mm.quantize_to_step( generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_seqs and extracted_seqs[0]: poly_seq = extracted_seqs[0] else: # If no track could be extracted, create an empty track that starts at the # requested generate_start_step. This will result in a sequence that # contains only the START token. poly_seq = polyphony_lib.PolyphonicSequence( steps_per_quarter=( quantized_primer_sequence.quantization_info.steps_per_quarter), start_step=generate_start_step) # Ensure that the track extends up to the step we want to start generating. poly_seq.set_length(generate_start_step - poly_seq.start_step) # Trim any trailing end events to prepare the sequence for more events to be # appended during generation. poly_seq.trim_trailing_end_events() # Extract generation arguments from generator options. arg_types = { 'temperature': lambda arg: arg.float_value, 'beam_size': lambda arg: arg.int_value, 'branch_factor': lambda arg: arg.int_value, 'steps_per_iteration': lambda arg: arg.int_value } args = dict((name, value_fn(generator_options.args[name])) for name, value_fn in arg_types.items() if name in generator_options.args) # Inject the priming sequence as melody in the output of the generator, if # requested. # This option starts with no_ so that if it is unspecified (as will be the # case when used with the midi interface), the default will be to inject the # primer. if not (generator_options.args[ 'no_inject_primer_during_generation'].bool_value): melody_to_inject = copy.deepcopy(poly_seq) if generator_options.args['condition_on_primer'].bool_value: inject_start_step = poly_seq.num_steps else: # 0 steps because we'll overwrite poly_seq with a blank sequence below. inject_start_step = 0 args['modify_events_callback'] = partial( _inject_melody, melody_to_inject, inject_start_step) # If we don't want to condition on the priming sequence, then overwrite # poly_seq with a blank sequence to feed into the generator. if not generator_options.args['condition_on_primer'].bool_value: poly_seq = polyphony_lib.PolyphonicSequence( steps_per_quarter=( quantized_primer_sequence.quantization_info.steps_per_quarter), start_step=generate_start_step) poly_seq.trim_trailing_end_events() total_steps = poly_seq.num_steps + ( generate_end_step - generate_start_step) while poly_seq.num_steps < total_steps: # Assume it takes ~5 rnn steps to generate one quantized step. # Can't know for sure until generation is finished because the number of # notes per quantized step is variable. steps_to_gen = total_steps - poly_seq.num_steps rnn_steps_to_gen = 5 * steps_to_gen tf.logging.info( 'Need to generate %d more steps for this sequence, will try asking ' 'for %d RNN steps' % (steps_to_gen, rnn_steps_to_gen)) poly_seq = self._model.generate_polyphonic_sequence( len(poly_seq) + rnn_steps_to_gen, poly_seq, **args) poly_seq.set_length(total_steps) if generator_options.args['condition_on_primer'].bool_value: generated_sequence = poly_seq.to_sequence(qpm=qpm) else: # Specify a base_note_sequence because the priming sequence was not # included in poly_seq. generated_sequence = poly_seq.to_sequence( qpm=qpm, base_note_sequence=copy.deepcopy(primer_sequence)) assert (generated_sequence.total_time - generate_section.end_time) <= 1e-5 return generated_sequence
def _primer_melody_to_event_sequence(self, input_sequence, generator_options, config): qpm = (input_sequence.tempos[0].qpm if input_sequence and input_sequence.tempos else mm.DEFAULT_QUARTERS_PER_MINUTE) steps_per_second = mm.steps_per_quarter_to_steps_per_second( self.steps_per_quarter, qpm) generate_section = generator_options.generate_sections[0] if generator_options.input_sections: input_section = generator_options.input_sections[0] primer_sequence = mm.trim_note_sequence(input_sequence, input_section.start_time, input_section.end_time) input_start_step = mm.quantize_to_step(input_section.start_time, steps_per_second, quantize_cutoff=0) else: primer_sequence = input_sequence input_start_step = 0 last_end_time = (max( n.end_time for n in primer_sequence.notes) if primer_sequence.notes else 0) if last_end_time > generate_section.start_time: raise mm.SequenceGeneratorException( 'Got GenerateSection request for section that is before the end of ' 'the NoteSequence. This model can only extend sequences. Requested ' 'start time: %s, Final note end time: %s' % (generate_section.start_time, last_end_time)) # Quantize the priming sequence. quantized_sequence = mm.quantize_note_sequence(primer_sequence, self.steps_per_quarter) # Setting gap_bars to infinite ensures that the entire input will be used. extracted_melodies, _ = mm.extract_melodies( quantized_sequence, search_start_step=input_start_step, min_bars=0, min_unique_pitches=1, gap_bars=float('inf'), ignore_polyphonic_notes=True) assert len(extracted_melodies) <= 1 start_step = mm.quantize_to_step(generate_section.start_time, steps_per_second, quantize_cutoff=0) # Note that when quantizing end_step, we set quantize_cutoff to 1.0 so it # always rounds down. This avoids generating a sequence that ends at 5.0 # seconds when the requested end time is 4.99. end_step = mm.quantize_to_step(generate_section.end_time, steps_per_second, quantize_cutoff=1.0) if extracted_melodies and extracted_melodies[0]: melody = extracted_melodies[0] else: # If no melody could be extracted, create an empty melody that starts 1 # step before the request start_step. This will result in 1 step of # silence when the melody is extended below. steps_per_bar = int( mm.steps_per_bar_in_quantized_sequence(quantized_sequence)) melody = mm.Melody([], start_step=max(0, start_step - 1), steps_per_bar=steps_per_bar, steps_per_quarter=self.steps_per_quarter) # Ensure that the melody extends up to the step we want to start generating. melody.set_length(start_step - melody.start_step - 2) now_encoding = config.encoder_decoder._one_hot_encoding # Extract generation arguments from generator options. primer_events = self._model.primer_melody_to_events( end_step - melody.start_step, melody) for i, event in enumerate(primer_events): primer_events[i] = now_encoding.encode_event(event) return primer_events