Python utils.midiread函数代码示例

	def train(self, file_name, weight_save_file, batch_size=1, num_epoch=200):
                print('load data ---------------')

                file_train=os.path.join(os.path.split(os.path.dirname(__file__))[0],
                                'data',file_name,'train','*.mid')
                dataset = [midiread(f, self.r, self.dt).piano_roll.astype(theano.config.floatX) for f in glob.glob(file_train)]

                file_test=os.path.join(os.path.split(os.path.dirname(__file__))[0],
                                'data',file_name,'test','*.mid')
                testdataset = [midiread(f, self.r, self.dt).piano_roll.astype(theano.config.floatX) for f in glob.glob(file_test)]
                print('load done --------------')
                try:
                        for epoch in range(num_epoch):
                                t0 = time.time()
                                numpy.random.shuffle(dataset)
                                costs = []
                                accuracys = []
                                for s, sequence in enumerate(dataset):
                                        y = numpy.hstack((sequence,numpy.zeros((sequence.shape[0],1)) ))
                                        x = numpy.roll(y, 1, axis=0)
                                        x[0,:]=0
                                        x[0,self.maxFeatures-1]=1
                                        cost, accuracy= self.rnnModel.train_on_batch(numpy.array([x]), numpy.array([y]), accuracy=True)
                                        costs.append(cost)
                                        accuracys.append(accuracy)

                                print('epoch: %i/%i\tcost: %.5f\taccu: %.5f\ttime: %.4f s' % (epoch+1, num_epoch, numpy.mean(costs), numpy.mean(accuracys),time.time()-t0))
                                sys.stdout.flush()
                                test_accu=self.evaluate(testdataset)
                                print('test_accu: %.5f' % ( numpy.mean(test_accu)) )
                        self.rnnModel.save_weights(weight_save_file)
                except KeyboardInterrupt:
                        print('interrupt by user !')

def modeling_n_gram(n, files):
    
	assert len(files) > 0, 'Training set is empty!' \
					' (did you download the data files?)'
					
	for f in files:

		print 'parsing', f

		each = midiread(f).piano_roll.astype(theano.config.floatX)
		numNote = len(each[0])

		# each [ time ] [ note ]
	
		for timeSlice in range(n-1, len(each)):
			for noteDest in range(numNote):
				valueDest = int(each[timeSlice][noteDest])
				for noteFrom in range(numNote):
					valueFrom = int(each[timeSlice-1][noteFrom])
					
					#print noteDest,valueDest,noteFrom,valueFrom
					
					probability[noteDest][valueDest][noteFrom][valueFrom] \
						= probability[noteDest][valueDest][noteFrom][valueFrom] + 1.0
						
	print 'learning_done'
	
	pkl.dump(probability, open("bi-gram-count.dat", "wb"))
	
	print 'bi-gram-count.dat saved'

    def load_dataset(self):
        re = ["data/JSB Chorales/train/*.mid"]
        re.append("data/JSB Chorales/test/*.mid")
        re.append("data/JSB Chorales/valid/*.mid")
        files = []
        for r in re:
            files += glob.glob(r)
        assert(len(files) > 0)
        print "generating dataset..."
        dataset = [midiread(f, self.r, self.dt).piano_roll.astype(theano.config.floatX) for f in files]
    
        memorization_dataset = [[]]  # memorize the first unit for 100 time-steps with binary noise

        n = 0

        for seq in dataset:
            for i in range(0, len(seq), self.seq_length):
                memorization_dataset[0].append(seq[i:i + self.seq_length])

        while False: #n < 100000:
            sequence = random.choice(dataset)
            if len(sequence) < self.seq_length:
                print " to short !"
            i = random.choice(range(0, len(sequence), self.seq_length))
            memorization_dataset[0].append(sequence[i:i + self.seq_length])
            n = n + 1

        print "number of sequence for training : ", len(memorization_dataset[0])

        self.train = [memorization_dataset[0][:-1000]]
        self.valid = [memorization_dataset[0][-1000:]]

        self.gradient_dataset = SequenceDataset(self.train, batch_size=None, number_batches=1000)
        self.cg_dataset = SequenceDataset(self.train, batch_size=None, number_batches=500)
        self.valid_dataset = SequenceDataset(self.valid, batch_size=None, number_batches=500)

    def train(self, files, batch_size=100, num_epochs=200):
        '''Train the RNN-RBM via stochastic gradient descent (SGD) using MIDI
        files converted to piano-rolls.

        files : list of strings --- List of MIDI files that will be loaded as piano-rolls for training.
        batch_size : integer    --- Training sequences will be split into subsequences of at most this size before applying the SGD updates.
        num_epochs : integer    --- Number of epochs (pass over the training set) performed. The user can safely interrupt training with Ctrl+C at any time.'''

        assert len(files) > 0, 'Training set is empty!' \
                               ' (did you download the data files?)'
        dataset = [midiread(f, self.r,
                            self.dt).piano_roll.astype(theano.config.floatX)
                   for f in files]

        try:
            for epoch in xrange(num_epochs):
                numpy.random.shuffle(dataset)
                costs = []

                for s, sequence in enumerate(dataset):
                    for i in xrange(0, len(sequence), batch_size):
                        cost = self.train_function(sequence[i:i + batch_size])
                        costs.append(cost)

                print 'Epoch %i/%i' % (epoch + 1, num_epochs),
                print numpy.mean(costs)
                sys.stdout.flush()

        except KeyboardInterrupt:
            print 'Interrupted by user.'

def load_jsb(path):
    mkdir_p(path)
    d = os.path.join(path, 'JSB Chorales')
    if not os.path.isdir(d):
        download_jsb(path)

    train_filenames = os.path.join(path, 'JSB Chorales', 'train', '*.mid')
    valid_filenames = os.path.join(path, 'JSB Chorales', 'valid', '*.mid')
    test_filenames = os.path.join(path, 'JSB Chorales', 'test', '*.mid')
    train_files = glob.glob(train_filenames)
    valid_files = glob.glob(valid_filenames)
    test_files = glob.glob(test_filenames)

    train_datasets = [midiread(f, r=(21, 109), dt=0.3).piano_roll.astype(theano.config.floatX) for f in train_files]
    valid_datasets = [midiread(f, r=(21, 109), dt=0.3).piano_roll.astype(theano.config.floatX) for f in valid_files]
    test_datasets = [midiread(f, r=(21, 109), dt=0.3).piano_roll.astype(theano.config.floatX) for f in test_files]

    return (train_datasets, [None]), (valid_datasets, [None]), (test_datasets, [None])

def load_midi_data(data_dir):
    import midi.utils as utils
    from midi import MidiInFile as mf
    from midi import MidiToText as mt

    f = open(data_dir, 'rb')
    midiIn = mf.MidiInFile(mt.MidiToText(), f)
    midiIn.read()
    f.close()

    midi_data = utils.midiread(data_dir, dt=0.5)
    return midi_data.piano_roll

def LoadDataForPreTraining(r=(21, 109), dt=0.3):

    assert len(trainingSet) > 0, 'Training set is empty!' \
                           ' (did you download the data files?)'
    sampleLen=[]
    dataset=[]
    maxLen=0
    nSample=0
    for f in trainingSet:
        currentMidi=midiread(f, (21, 109),0.3).piano_roll
        dataset.append(currentMidi)
        sampleLen.append(currentMidi.shape[0])
        if maxLen< currentMidi.shape[0]:
            maxLen=currentMidi.shape[0]
        nSample=nSample+1
    return (dataset, sampleLen, nSample, maxLen)

    def train(self, files, batch_size=100, num_epochs=200):
        '''Train the RNN-RBM via stochastic gradient descent (SGD) using MIDI
        files converted to piano-rolls.

        files : list of strings
            List of MIDI files that will be loaded as piano-rolls for training.
        batch_size : integer
            Training sequences will be split into subsequences of at most this
            size before applying the SGD updates.
        num_epochs : integer
            Number of epochs (pass over the training set) performed. The user
            can safely interrupt training with Ctrl+C at any time.'''

        assert len(files) > 0, 'Training set is empty!' \
                               ' (did you download the data files?)'
        dataset = [midiread(f, self.r,
                            self.dt).piano_roll.astype(theano.config.floatX)
                   for f in files]
        print "Start training process of the recurrent network RBM machine with the given dataset..." ,
        print "Lenght of the Dataset: ", len(files)
        print "Interrupt if necessariy by pressing Ctrl+C",
        print "...Might take some time :) ..."
        costst = []
        try:
            for epoch in xrange(num_epochs):
                numpy.random.shuffle(dataset)
                costs = []

                for s, sequence in enumerate(dataset):
                    for i in xrange(0, len(sequence), batch_size):
                        cost = self.train_function(sequence[i:i + batch_size])
                        costs.append(cost)

                print 'Epoch %i/%i' % (epoch + 1, num_epochs),
                print "Current mean Energy cost:", numpy.mean(costs)
                costst.append(numpy.mean(costs))
                print "Training %i percent done; interrupt training by pressing Crtl+C." % (float((float(epoch) + 1.0)*100.0 / float(num_epochs)))
                sys.stdout.flush()

        except KeyboardInterrupt:
            print 'Training Interrupted.'
            
        return self, files, costst

def loadDataSet(files):
    #File e il path della carterlla contente i file (*.mid)
    assert len(files) > 0, 'Training set is empty!' \
                           ' (did you download the data files?)'
    #mi calcolo quel'el 'esempio di lunghezza massima
    maxLen=0
    dataset=[]
    for f in files:
        currentMidi=midiread(f, (21, 109),0.3).piano_roll.astype(theano.config.floatX)
        dataset.append(currentMidi)
        if maxLen< currentMidi.shape[0]:
            maxLen=currentMidi.shape[0]
    #porto tutte le tracce a masima lunghezza aggiongendo silenzio
    for i, seq in enumerate(dataset):
            if seq.shape[0]<maxLen:
                dataset[i]=np.concatenate([seq, np.zeros((maxLen-seq.shape[0], 88))])
                        
    #print dataset[0].shape
    return np.array(dataset, dtype=theano.config.floatX)

def loadDataSetMin(files):
    #File e il path della carterlla contente i file (*.mid)
    assert len(files) > 0, 'Training set is empty!' \
                           ' (did you download the data files?)'
    #mi calcolo quel'el 'esempio di lunghezza massima
    minLen=sys.maxint
    dataset=[]
    for f in files:
        currentMidi=midiread(f, (21, 109),0.3).piano_roll.astype(theano.config.floatX)
        dataset.append(currentMidi)
        if minLen> currentMidi.shape[0]:
            minLen=currentMidi.shape[0]
    #porto tutte le tracce a masima lunghezza aggiongendo silenzio
    for i, seq in enumerate(dataset):
            if seq.shape[0]>minLen:
                dataset[i]=seq[0:minLen,:] 
                        
    #print dataset[0].shape
    #print "MINLEN: ", minLen
    return np.array(dataset, dtype=theano.config.floatX)

    def train(self, files, batch_size=500, num_epochs=300):
        assert len(files) > 0, 'Training set is empty!' \
                               ' (did you download the data files?)'
        dataset = [midiread(f, self.r,
                            self.dt).piano_roll.astype(theano.config.floatX)
                   for f in files]
        try:
            for epoch in xrange(num_epochs):
                numpy.random.shuffle(dataset)
                costs = []

                for s, sequence in enumerate(dataset):
                    for i in xrange(0, len(sequence), batch_size):
                        cost = self.train_function(sequence[i:i + batch_size])
                        costs.append(cost)

                print 'Epoch %i/%i' % (epoch + 1, num_epochs),
                print numpy.mean(costs)
                sys.stdout.flush()

        except KeyboardInterrupt:
            print 'Interrupted by user.'

def LoadDataForPreTraining(r=(21, 109), dt=0.3):

    assert len(trainingSet) > 0, 'Training set is empty!' \
                           ' (did you download the data files?)'
    sampleLen=[]
    dataset=[]
    maxLen=0
    nSample=0
    for f in trainingSet:
        
        currentMidi=midiread(f, (21, 109),0.3).piano_roll
        print f,": lenght= ",currentMidi.shape[0]
        sampleLen.append(currentMidi.shape[0])
        
        if maxLen< currentMidi.shape[0]:
            maxLen=currentMidi.shape[0]
        nSample=nSample+1
    print "#-----dataset data-----#"
    print "number of sample: ", len(trainingSet)
    print "max lenght:", maxLen
    print "# rows of matrix M:",sum(sampleLen)
    print "# columns of matrix M:", maxLen*88
    return (dataset, sampleLen, nSample, maxLen)

def main():

    #--- import data ---#
    sizeOfMiniBatch = 5 #how many tunes per miniBatch
    noOfEpoch = 100 
    noOfEpochPerMB = 2
    lengthOfMB = 100
    sparseParam = np.float32(0.01) #increases with no. of cells
    path = './Piano-midi.de/train-individual/hpps'
    #path = './Piano-midi.de/train'
    files = os.listdir(path)
    assert len(files) > 0, 'Training set is empty!' \
                               ' (did you download the data files?)'
    #pitch range is from 21 to 109
    dataset = [midiread((path + "/" + f), (21, 109),0.3).piano_roll.astype(theano.config.floatX) for f in files]
                  
    #check number of notes for each tune:       
    print(str([np.array(dataset[n]).shape[0] for n in np.arange(np.array(dataset).shape[0])]))

    # set "silent" to zero in 1-hot format
    for k in np.arange(np.array(dataset).shape[0]):
        for n in np.arange(0,np.array(dataset[k]).shape[0],1):
            if np.sum(dataset[k][n], dtype=theano.config.floatX) == 0 :
                dataset[k][n][0] = np.float32(1.0)
                

    #--- training with data ---#
    
    myRNN4Music = RNN4Music(h1_length=176, h2_length=176, h3_length=176, io_length=88, R1=np.float32(0.001), R2=np.float32(0.001), R3=np.float32(0.001), Rout=np.float32(0.001)) 
    
    #myRNN4Music.loadParameters('120_120_120_0_001_xEn_150epoch_hpps')
    #myRNN4Music.loadParameters('120_120_120_0_001_sqr_150epoch_hpps')
    myRNN4Music.loadParameters('176_176_176_0_001_xEn_L1_0_01_100epoch_hpps')
    #myRNN4Music.saveParameters('176_176_176_0_001_xEn_L1_0_1_300epoch_hpps')
    
    #myRNN4Music.train(dataset, noOfEpochPerMB, noOfEpoch, sizeOfMiniBatch, lengthOfMB, sparseParam)
    #myRNN4Music.saveParameters('176_176_176_0_001_xEn_L1_0_01_100epoch_hpps')
    #myRNN4Music.train(dataset, noOfEpochPerMB, noOfEpoch, sizeOfMiniBatch, lengthOfMB, sparseParam)
    #myRNN4Music.saveParameters('176_176_176_0_001_xEn_L1_0_01_200epoch_hpps')
    #myRNN4Music.train(dataset, noOfEpochPerMB, noOfEpoch, sizeOfMiniBatch, lengthOfMB, sparseParam)
    #myRNN4Music.saveParameters('176_176_176_0_001_xEn_L1_0_01_300epoch_hpps')
    #myRNN4Music.train(dataset, noOfEpochPerMB, noOfEpoch, sizeOfMiniBatch, lengthOfMB, sparseParam)
    #myRNN4Music.saveParameters('176_176_176_0_001_xEn_L1_0_01_400epoch_hpps')




    #--- plot some genearted tunes ---#

    for baseSample in np.array([0, 20, 15, 31]):
        exampleLength = 50
        myRNN4Music.resetStates()
        generatedTune = myRNN4Music.genMusic(np.float32(dataset[baseSample][0:exampleLength]), 300)
        midiwrite('176_176_176_0_001_sqr_hpps150_' + str(baseSample) + '.mid', generatedTune[0], (21, 109),0.3)
        #generatedTune[0] is the tune, generatedTune[1] is the probability at each iteration
        
        #plot genearted probability
        plt.figure(0 + baseSample*100)
        plt.imshow(np.array(generatedTune[1][0:50,25:65]), origin = 'lower', extent=[25,65,0,50], aspect=0.5,
                        interpolation = 'nearest', cmap='gist_stern_r')
        plt.title('probability of generated midi note piano-roll')
        plt.xlabel('midi note')
        plt.ylabel('sample number (time steps)')
        plt.colorbar()##
        #plot leading example for generation
        plt.figure(1 + baseSample*100)
        plt.imshow(np.transpose(dataset[baseSample]), origin='lower', aspect='auto',
                                 interpolation='nearest', cmap=pylab.cm.gray_r)
        plt.colorbar()
        plt.title('original piano-roll')
        plt.xlabel('sample number (time steps)')
        plt.ylabel('midi note')

        #plot generated tune
        plt.figure(2 + baseSample*100)
        plt.imshow(np.transpose(np.array(generatedTune[0][0:500])), origin='lower', aspect='auto',
                                 interpolation='nearest', cmap=pylab.cm.gray_r)
        plt.colorbar()
        plt.title('generated piano-roll')
        plt.xlabel('sample number (time steps)')
        plt.ylabel('midi note')
    plt.show()

      save_dir = './'

      ### read MIDI
      #data_dir = '../Data/Cirriculum/easy/'
      #data_dir = '../biaxial-rnn-music-composition/music/'

      files = os.listdir(data_dir)
      files = [data_dir + f for f in files if '.mid' in f or '.MID' in f]

      print files 

      dataset = []

      for f in files:
          try:
              dataset.append(midiread(f, MIDI_RANGE, DT).piano_roll)
              print "{} loaded".format(f)
          except IndexError:
              print "Skipping {}".format(f)
              pass

      print np.shape(dataset)

      X = []
      y = []

      for song in dataset:
          for i in range(0, len(song) - TICKS_PER_INPUT, STEP):
              X.append(song[i: i + TICKS_PER_INPUT])
              y.append(song[i + TICKS_PER_INPUT])

# In[109]:

model.train(onlyfiles)


# In[117]:

model.generate('testHaydn3.mid')


# In[23]:

get_ipython().magic(u'pylab inline')
f = 'testNotthingham6.mid'
extent = (0, 0.25 * len(piano_roll)) + (21, 109)
piano_roll = midiread(f, (21, 109), 0.25).piano_roll.astype(theano.config.floatX)
pylab.figure()
pylab.imshow(piano_roll.T, origin='lower', aspect='auto',
             interpolation='nearest', cmap=pylab.cm.gray_r,
             extent=extent)
pylab.xlabel('time (s)')
pylab.ylabel('MIDI note number')
pylab.title('generated piano-roll')
pylab.show()


# In[ ]: