def __init__(self,dataset,batch_size,directory='',**kwargs):
if dataset == 'musicnet':
if not directory:
directory = MUSICNET_DIRECTORY
self.dataset = musicnet.MusicNet(root=directory, train=True, window=kwargs[WINDOW], download=kwargs.get(DOWNLOAD,True),pitch_shift=kwargs.get(PITCH_SHIFT,0),jitter=kwargs.get(JITTER,0))
self.loader = torch.utils.data.DataLoader(dataset=self.dataset,batch_size=batch_size)
elif dataset == 'cochleagram':
self.dataset = CochleagramsDataset(root=directory)
self.loader = torch.utils.data.DataLoader(dataset=self.dataset,batch_size=batch_size)
else:
raise NameError(f'dataset {dataset} not handled')
root = 'musicnet'
def worker_init(args):
signal.signal(signal.SIGINT,
signal.SIG_IGN) # ignore signals so parent can handle them
np.random.seed(os.getpid()
^ int(time())) # approximately random seed for workers
batch_size = 100
kwargs = {'num_workers': 0, 'pin_memory': True, 'worker_init_fn': worker_init}
window = 16384
train_set = musicnet.MusicNet(root=root,
train=True,
download=True,
window=window)
test_set = musicnet.MusicNet(root=root, train=False, window=window)
train_loader = torch.utils.data.DataLoader(dataset=train_set,
batch_size=batch_size,
**kwargs)
test_loader = torch.utils.data.DataLoader(dataset=test_set,
batch_size=batch_size,
**kwargs)
print('data loaded ')
model = NADE(input_dim=128, hidden_dim=50).to(device)
loss_function = nn.BCELoss(reduction="sum")
optimizer = optim.Adam(model.parameters())
scheduler = optim.lr_scheduler.StepLR(optimizer, 15, gamma=0.1)
result_dict['parameters']['train_size'] = train_size
result_dict['parameters']['test_size'] = test_size
result_dict['parameters']['lr'] = lr
result_dict['parameters']['pitch_shift'] = pitch_shift
result_dict['parameters']['jitter'] = jitter
result_dict['parameters']['window'] = window
# Preparing Dataset
start = time()
root = './data/'
train_set = musicnet.MusicNet(root=root,
epoch_size=train_size,
sequence=sequence,
train=True,
download=True,
refresh_cache=False,
window=window,
mmap=False,
pitch_shift=pitch_shift,
jitter=jitter)
test_set = musicnet.MusicNet(root=root,
train=False,
download=True,
sequence=sequence,
refresh_cache=False,
window=window,
epoch_size=test_size,
mmap=False)
print("Data loaded, time used = {:2.2f} seconds".format(time() - start))
train_loader = torch.utils.data.DataLoader(dataset=train_set,
def main():
ids = musicnet.MusicNet().ids
# pool = Pool(cpu_count())
for id in ids:
processdata(id)