def train(args, i):
'''Training. Model will be saved after several iterations.
Args:
dataset_dir: string, directory of dataset
workspace: string, directory of workspace
holdout_fold: '1' | 'none', set 1 for development and none for training
on all data without validation
model_type: string, e.g. 'Cnn_9layers_AvgPooling'
batch_size: int
cuda: bool
mini_data: bool, set True for debugging on a small part of data
'''
# Arugments & parameters
dataset_dir = args.dataset_dir
workspace = args.workspace
holdout_fold = args.holdout_fold
model_type = args.model_type
batch_size = args.batch_size
cuda = args.cuda and torch.cuda.is_available()
mini_data = args.mini_data
filename = args.filename
audio_num = config.audio_num
mel_bins = config.mel_bins
frames_per_second = config.frames_per_second
max_iteration = None # Number of mini-batches to evaluate on training data
reduce_lr = True
in_domain_classes_num = len(config.labels)
# Paths
if mini_data:
prefix = 'minidata_'
else:
prefix = ''
train_csv = os.path.join(sys.path[0], 'fold' + str(i) + '_train.csv')
validate_csv = os.path.join(sys.path[0], 'fold' + str(i) + '_test.csv')
feature_hdf5_path = os.path.join(
workspace, 'features',
'{}logmel_{}frames_{}melbins.h5'.format(prefix, frames_per_second,
mel_bins))
checkpoints_dir = os.path.join(
workspace, 'checkpoints', filename,
'{}logmel_{}frames_{}melbins.h5'.format(prefix, frames_per_second,
mel_bins),
'holdout_fold={}'.format(holdout_fold), model_type)
create_folder(checkpoints_dir)
validate_statistics_path = os.path.join(
workspace, 'statistics', filename,
'{}logmel_{}frames_{}melbins'.format(prefix, frames_per_second,
mel_bins),
'holdout_fold={}'.format(holdout_fold), model_type,
'validate_statistics.pickle')
create_folder(os.path.dirname(validate_statistics_path))
logs_dir = os.path.join(
workspace, 'logs', filename, args.mode,
'{}logmel_{}frames_{}melbins'.format(prefix, frames_per_second,
mel_bins),
'holdout_fold={}'.format(holdout_fold), model_type)
create_logging(logs_dir, 'w')
logging.info(args)
if cuda:
logging.info('Using GPU.')
else:
logging.info('Using CPU. Set --cuda flag to use GPU.')
# Model
Model = eval(model_type)
model = Model(in_domain_classes_num, activation='logsoftmax')
loss_func = nll_loss
if cuda:
model.cuda()
# Optimizer
optimizer = optim.Adam(model.parameters(),
lr=1e-3,
betas=(0.9, 0.999),
eps=1e-08,
weight_decay=0.,
amsgrad=True)
# optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9, weight_decay=1e-5)
# Data generator
data_generator = DataGenerator(feature_hdf5_path=feature_hdf5_path,
train_csv=train_csv,
validate_csv=validate_csv,
holdout_fold=holdout_fold,
batch_size=batch_size)
# Evaluator
evaluator = Evaluator(model=model,
data_generator=data_generator,
cuda=cuda)
# Statistics
validate_statistics_container = StatisticsContainer(
validate_statistics_path)
train_bgn_time = time.time()
iteration = 0
# Train on mini batches
for batch_data_dict in data_generator.generate_train():
# Evaluate
if iteration % 100 == 0 and iteration >= 1500:
logging.info('------------------------------------')
logging.info('Iteration: {}'.format(iteration))
train_fin_time = time.time()
train_statistics = evaluator.evaluate(data_type='train',
iteration=iteration,
max_iteration=None,
verbose=False)
if holdout_fold != 'none':
validate_statistics = evaluator.evaluate(data_type='validate',
iteration=iteration,
max_iteration=None,
verbose=False)
validate_statistics_container.append_and_dump(
iteration, validate_statistics)
train_time = train_fin_time - train_bgn_time
validate_time = time.time() - train_fin_time
logging.info('Train time: {:.3f} s, validate time: {:.3f} s'
''.format(train_time, validate_time))
train_bgn_time = time.time()
# Save model
if iteration % 100 == 0 and iteration > 0:
checkpoint = {
'iteration': iteration,
'model': model.state_dict(),
'optimizer': optimizer.state_dict()
}
checkpoint_path = os.path.join(
checkpoints_dir, '{}_iterations.pth'.format(iteration))
torch.save(checkpoint, checkpoint_path)
logging.info('Model saved to {}'.format(checkpoint_path))
# Reduce learning rate
if reduce_lr and iteration % 100 == 0 and iteration > 0:
for param_group in optimizer.param_groups:
param_group['lr'] *= 0.9
# Move data to GPU
for key in batch_data_dict.keys():
if key in ['feature', 'target']:
batch_data_dict[key] = move_data_to_gpu(
batch_data_dict[key], cuda)
# Train
for i in range(audio_num):
model.train()
data, target_a, target_b, lam = mixup_data(
x=batch_data_dict['feature'][:, i, :, :],
y=batch_data_dict['target'],
alpha=0.2)
batch_output = model(data)
# batch_output = model(batch_data_dict['feature'])
# loss
loss = loss_func(batch_output, batch_data_dict['target'])
loss = mixup_criterion(loss_func, batch_output, target_a, target_b,
lam)
# Backward
optimizer.zero_grad()
loss.backward()
optimizer.step()
# Stop learning
if iteration == 4000:
break
iteration += 1
def inference_validation(args):
'''Inference and calculate metrics on validation data.
Args:
dataset_dir: string, directory of dataset
workspace: string, directory of workspace
model_type: string, e.g. 'Cnn_9layers'
iteration: int
batch_size: int
cuda: bool
mini_data: bool, set True for debugging on a small part of data
visualize: bool
'''
# Arugments & parameters
dataset_dir = args.dataset_dir
workspace = args.workspace
model_type = args.model_type
holdout_fold = args.holdout_fold
iteration = args.iteration
batch_size = args.batch_size
cuda = args.cuda and torch.cuda.is_available()
mini_data = args.mini_data
visualize = args.visualize
filename = args.filename
data_length = args.data_length
mel_bins = config.mel_bins
frames_per_second = config.frames_per_second
in_domain_classes_num = len(config.labels)
# Paths
if mini_data:
prefix = 'minidata_'
else:
prefix = ''
train_csv = 'fold1_train.csv'
validate_csv = 'fold1_test.csv'
feature_hdf5_path = os.path.join(
workspace, 'features',
'{}logmel_{}frames_{}melbins.h5'.format(prefix, frames_per_second,
mel_bins))
scalar_path = os.path.join(
workspace, 'scalars',
'{}logmel_{}frames_{}melbins.h5'.format(prefix, frames_per_second,
mel_bins))
checkpoint_path = os.path.join(
workspace, 'checkpoints', filename,
'{}logmel_{}frames_{}melbins'.format(prefix, frames_per_second,
mel_bins),
'holdout_fold={}'.format(holdout_fold), model_type,
'{}_iterations.pth'.format(iteration))
logs_dir = os.path.join(
workspace, 'logs', filename, args.mode,
'{}logmel_{}frames_{}melbins'.format(prefix, frames_per_second,
mel_bins),
'holdout_fold={}'.format(holdout_fold), model_type)
create_logging(logs_dir, 'w')
logging.info(args)
# Load scalar
scalar = load_scalar(scalar_path)
# Load model
Model = eval(model_type)
model = Model(in_domain_classes_num, activation='logsoftmax')
loss_func = nll_loss
checkpoint = torch.load(checkpoint_path)
model.load_state_dict(checkpoint['model'])
if cuda:
model.cuda()
# Data generator
data_generator = DataGenerator(feature_hdf5_path=feature_hdf5_path,
train_csv=train_csv,
validate_csv=validate_csv,
holdout_fold=holdout_fold,
scalar=scalar,
batch_size=batch_size)
# Evaluator
evaluator = Evaluator(model=model,
data_generator=data_generator,
cuda=cuda)
if subtask in ['a', 'c']:
evaluator.evaluate(data_type='validate', verbose=True)
elif subtask == 'b':
evaluator.evaluate(data_type='validate', verbose=True)
evaluator.evaluate(data_type='validate', verbose=True)
evaluator.evaluate(data_type='validate', verbose=True)
# Visualize log mel spectrogram
if visualize:
evaluator.visualize(data_type='validate')
parser.add_argument("-data_parallel", "--data_parallel", type = int, help="1 if model is to be distributed across multiple GPUs")
parser.add_argument("-model_type", "--model_type", type = str, choices=["MTL_SEDNetwork","GMP", "GAP", "GWRP", "AttrousCNN_2DAttention"])
parser.add_argument("-val_fold", "--val_fold", required=True, type=int, help="holdout fold between 1,2,3,4")
parser.add_argument("-snr", "--snr", required=True, type=int, help="SNR between 0, 10, 20")
parser.add_argument("-alpha", "--alpha", required=True, type=float, help="Alpha (weightage) for reconstruction loss")
args = parser.parse_args()
# Setting up experiments
data_parallel = args.data_parallel == 1
MTL = args.model_type == "MTL_SEDNetwork" # if true use auxillary task MTL loss
cuda = torch.cuda.is_available()
create_folder('experiments')
base_path = os.path.join('experiments', args.exp_name)
model_path = os.path.join(base_path, 'best.pth')
create_folder(base_path)
create_logging(base_path, filemode = 'w')
logging.info(f'logging started for experiment = {args.exp_name} and validation fold = {args.val_fold}')
# Data and yaml path
data_path = os.path.join(args.data_dir, f'logmel/logmel_snr_{args.snr}.h5')
yaml_path = os.path.join(args.data_dir, 'mixture.yaml')
with open(yaml_path, 'r') as f:
meta = yaml.load(f, Loader=yaml.FullLoader)
f.close()
# Dataset and Dataloader
data_container = get_dataloader(data_path, yaml_path, args, cuda)
# model and dataparallel
Model = get_model(args.model_type)
model = Model(config.classes_num, config.seq_len, config.mel_bins, cuda)
import time
import microbit
import utils
import logging
from envirobit import sound
utils.create_logging('.')
def show_txt(txt):
microbit.display.show(txt)
if __name__ == "__main__":
logger = logging.getLogger()
for i in range(0, 100):
got_clap = sound.wait_for_clap()
#logger.info('the temperature is %s degrees celsius' % temp)
logger.info('I got a clap now, that is %s' % got_clap)
time.sleep(1)
for i in range(len(pred)):
# first second
if pred[i] == 0 and start == -1:
start = i
end = i+3
if pred[i] == 0 and start != -1:
end = i+3
if start != -1:
return True, start, end
else :
return False, -1, -1
if __name__ == '__main__':
logs_dir = '.logs/'
create_logging(logs_dir, 'w')
test_bgn_time = time.time()
checkpoint_path = '/home/cdd/code/cry_sound_detection/FPNet/workspace/checkpoints/main/logmel_50frames_64melbins.h5/holdout_fold=1/Cnns/2000_iterations.pth'
model_type = 'Cnns'
test_fold = '/home/cdd/code/cry_sound_detection/FPNet/util/test_babycry'
# test_wav = 'mixture_devtest_babycry_000_c02f92b79f2bbefa98d008f3c2d9b704.wav'
# test_wav = 'mixture_devtest_babycry_004_19c4bcb10576524449c83b01fae0b731.wav'
for root, dirs, files in os.walk(test_fold):
file = files
logging.info('------------------------------------')
for f in file:
test_wav = f
logging.info('Test: {}'.format(test_wav))
res, start, end = test_one(checkpoint_path=checkpoint_path, model_type=model_type, cuda=True, test_fold=test_fold, test_wav=test_wav, test_segment= False)
if res == True:
logging.info('Test result: Babycry! ({}~{}s)'.format(start, end))
