def preprocess(midi_dir, preproc_dir):
midi_dir = Path(midi_dir)
preproc_dir = Path(preproc_dir)
preproc_dir.mkdir(exist_ok=True, parents=True)
if list(preproc_dir.iterdir()):
print(f"'{preproc_dir}' is not empty. Continuing anyway.")
files = []
files.extend(midi_dir.glob("*.mid"))
files.extend(midi_dir.glob("*.midi"))
files.sort()
# TODO: make it output only one file, in tf format
with click.progressbar(files, label="Processing",
item_show_func=str) as prog:
for file in prog:
outfile = preproc_dir / (file.name + ".pickle")
with file.open("rb") as f:
data = encode_midi(f)
with outfile.open("wb") as f:
pickle.dump(data, f)
def preprocess_midi(path):
return encode_midi(path)
else:
config.device = torch.device('cpu')
current_time = datetime.datetime.now().strftime('%Y%m%d-%H%M%S')
gen_log_dir = 'logs/mt_decoder/generate_' + current_time + '/generate'
gen_summary_writer = SummaryWriter(gen_log_dir)
mt = MusicTransformer(embedding_dim=config.embedding_dim,
vocab_size=config.vocab_size,
num_layer=config.num_layers,
max_seq=config.max_seq,
dropout=0,
debug=False)
mt.load_state_dict(torch.load(args.model_dir + '/final.pth'))
mt.test()
print(config.condition_file)
if config.condition_file is not None:
inputs = np.array([encode_midi('dataset/midi/BENABD10.mid')[:500]])
else:
inputs = np.array([[24, 28, 31]])
inputs = torch.from_numpy(inputs)
result = mt(inputs, config.length, gen_summary_writer)
for i in result:
print(i)
decode_midi(result, file_path=config.save_path)
gen_summary_writer.close()
def preprocess_midi(path):
# return encode_midi(path, augumentation=False)
return encode_midi(path)
gen_log_dir = 'logs/mt_decoder/generate_'+current_time+'/generate'
gen_summary_writer = tf.summary.create_file_writer(gen_log_dir)
if mode == 'enc-dec':
print(">> generate with original seq2seq wise... beam size is {}".format(beam))
mt = MusicTransformer(
embedding_dim=256,
vocab_size=par.vocab_size,
num_layer=6,
max_seq=2048,
dropout=0.2,
debug=False, loader_path=load_path)
else:
print(">> generate with decoder wise... beam size is {}".format(beam))
mt = MusicTransformerDecoder(loader_path=load_path)
inputs = encode_midi(args.inputs)
with gen_summary_writer.as_default():
result = mt.generate(inputs[:10], beam=beam, length=length, tf_board=True)
for i in result:
print(i)
if mode == 'enc-dec':
decode_midi(list(inputs[-1*par.max_seq:]) + list(result[1:]), file_path=save_path)
else:
decode_midi(result, file_path=save_path)
gen_log_dir = 'logs/mt_decoder/generate_' + current_time + '/generate'
gen_summary_writer = tf.summary.create_file_writer(gen_log_dir)
if mode == 'enc-dec':
print(">> generate with original seq2seq wise... beam size is {}".format(
beam))
mt = MusicTransformer(embedding_dim=256,
vocab_size=par.vocab_size,
num_layer=6,
max_seq=2048,
dropout=0.2,
debug=False,
loader_path=load_path)
else:
print(">> generate with decoder wise... beam size is {}".format(beam))
mt = MusicTransformerDecoder(loader_path=load_path)
inputs = encode_midi('dataset/midi/BENABD10.mid')
with gen_summary_writer.as_default():
result = mt.generate(inputs[:10], beam=beam, length=length, tf_board=True)
for i in result:
print(i)
if mode == 'enc-dec':
decode_midi(list(inputs[-1 * par.max_seq:]) + list(result[1:]),
file_path=save_path)
else:
decode_midi(result, file_path=save_path)
if mode == 'enc-dec':
print(">> generate with original seq2seq wise... beam size is {}".format(
beam))
mt = MusicTransformer(embedding_dim=256,
vocab_size=par.vocab_size,
num_layer=6,
max_seq=2048,
dropout=0.2,
debug=False,
loader_path=load_path)
else:
print(">> generate with decoder wise... beam size is {}".format(beam))
mt = MusicTransformerDecoder(loader_path=load_path, max_seq=max_seq)
inputs = encode_midi(midi_path)
with gen_summary_writer.as_default():
result = mt.generate(inputs[:crop_length],
beam=beam,
length=length,
tf_board=True)
for i in result:
print(i)
if mode == 'enc-dec':
decode_midi(list(inputs[-1 * par.max_seq:]) + list(result[1:]),
file_path=save_path)
else:
decode_midi(result, file_path=save_path)
gen_summary_writer = tf.summary.create_file_writer(gen_log_dir)
if mode == 'enc-dec':
print(">> generate with original seq2seq wise... beam size is {}".format(
beam))
mt = MusicTransformer(embedding_dim=256,
vocab_size=par.vocab_size,
num_layer=6,
max_seq=2048,
dropout=0.2,
debug=False,
loader_path=load_path)
else:
print(">> generate with decoder wise... beam size is {}".format(beam))
mt = MusicTransformerDecoder(loader_path=load_path)
#inputs = encode_midi('dataset/midi/BENABD10.mid')
inputs = encode_midi(prior_midi)
with gen_summary_writer.as_default():
result = mt.generate(inputs[:10], beam=beam, length=length, tf_board=True)
for i in result:
print(i)
if mode == 'enc-dec':
decode_midi(list(inputs[-1 * par.max_seq:]) + list(result[1:]),
file_path=save_path)
else:
decode_midi(result, file_path=save_path)
mt = MusicTransformer(embedding_dim=config.embedding_dim,
vocab_size=config.vocab_size,
num_layer=config.num_layers,
max_seq=config.max_seq,
dropout=0,
debug=False)
mt.load_state_dict(torch.load(join(args.model_dir, args.ckpt)))
mt.test()
mt.cuda()
#%%
## %%time
if condition_file is not None:
print("use condition file %s, first %d notes" %
(condition_file, args.condition_len))
inputs = np.array([encode_midi(condition_file)[:args.condition_len]])
print(inputs[0])
else:
inputs = np.array([[24, 28, 31]])
inputs = torch.from_numpy(inputs).cuda()
with torch.no_grad():
result = mt(inputs, 2048, gen_summary_writer)
# mid = decode_midi(result.cpu(), file_path=None) #
mid = decode_midi(result,
file_path='result/generated_mod%s_cond%s.mid' %
(args.ckpt.split('.')[0], condition_fn))
gen_summary_writer.close()
ps_roll = mid.get_piano_roll()
figh = plot_piano_roll(ps_roll)
figh.savefig('result/generated_mod%s_cond%s.jpg' %
(args.ckpt.split('.')[0], condition_fn))
gen_log_dir = 'logs/mt_decoder/generate_' + current_time + '/generate'
gen_summary_writer = tf.summary.create_file_writer(gen_log_dir)
if mode == 'enc-dec':
print(">> generate with original seq2seq wise... beam size is {}".format(
beam))
mt = MusicTransformer(embedding_dim=256,
vocab_size=par.vocab_size,
num_layer=6,
max_seq=2048,
dropout=0.2,
debug=False,
loader_path=load_path)
else:
print(">> generate with decoder wise... beam size is {}".format(beam))
mt = MusicTransformerDecoder(loader_path=load_path)
inputs = encode_midi('./dataset/midi/chopin_canon_in_F_minor.mid')
with gen_summary_writer.as_default():
result = mt.generate(inputs[:500], beam=beam, length=length, tf_board=True)
for i in result:
print(i)
if mode == 'enc-dec':
decode_midi(list(inputs[-1 * par.max_seq:]) + list(result[1:]),
file_path='bin/generated.mid')
else:
decode_midi(result, file_path='bin/generated.mid')
def preprocess_midi(path):
# revised code
return encode_midi(path)