def __init__(self, HPARAMS):
super().__init__()
# HPARAMS
self.save_hyperparameters()
self.model = Wav2VecLSTM(HPARAMS['model_hidden_size'])
self.classification_criterion = MSE()
self.regression_criterion = MSE()
self.mae_criterion = MAE()
self.rmse_criterion = RMSELoss()
self.accuracy = Accuracy()
self.alpha = HPARAMS['model_alpha']
self.beta = HPARAMS['model_beta']
self.gamma = HPARAMS['model_gamma']
self.lr = HPARAMS['training_lr']
self.csv_path = HPARAMS['speaker_csv_path']
self.df = pd.read_csv(self.csv_path, sep=' ')
self.h_mean = self.df['Height'].mean()
self.h_std = self.df['Height'].std()
self.a_mean = self.df['Age'].mean()
self.a_std = self.df['Age'].std()
print(f"Model Details: #Params = {self.count_total_parameters()}\t#Trainable Params = {self.count_trainable_parameters()}")
def __init__(self, HPARAMS):
super().__init__()
# HPARAMS
self.save_hyperparameters()
self.models = {
'wav2vecLSTMAttn': Wav2VecLSTM,
'spectralCNNLSTM': SpectralCNNLSTM,
'MultiScale': SpectralMultiScale,
}
self.model = self.models[HPARAMS['model_type']](HPARAMS['hidden_size'])
self.classification_criterion = MSE()
self.regression_criterion = MSE()
self.mae_criterion = MAE()
self.rmse_criterion = RMSELoss()
self.accuracy = Accuracy()
self.alpha = HPARAMS['alpha']
self.beta = HPARAMS['beta']
self.gamma = HPARAMS['gamma']
self.lr = HPARAMS['lr']
self.csv_path = HPARAMS['speaker_csv_path']
self.df = pd.read_csv(self.csv_path)
self.h_mean = self.df['height'].mean()
self.h_std = self.df['height'].std()
self.a_mean = self.df['age'].mean()
self.a_std = self.df['age'].std()
print(
f"Model Details: #Params = {self.count_total_parameters()}\t#Trainable Params = {self.count_trainable_parameters()}"
)
def inference(model, loader, label_name, logger, log_path, save_model_file):
m, M = (144.78, 203.2)
model.load_state_dict(torch.load(log_path + save_model_file))
true_labels = []
predictions = []
model.eval() # evaluation mode
with torch.no_grad(): # no gradients/back propagation for evaluation
for batch in loader:
batch_x, batch_y = batch
batch_x, batch_y = batch_x.float().to(device), batch_y.float().to(
device)
y_hat = model(batch_x) # forward pass throough model
predictions += y_hat.cpu().detach().view(-1)
true_labels += batch_y.cpu().detach().view(-1)
prediction = torch.Tensor(predictions) * (M - m) + m
label = torch.Tensor(true_labels) * (M - m) + m
mse = MSE()(prediction, label)
mae = MAE()(prediction, label)
rmse = RMSE()(prediction, label)
print(f'\n{label_name} Dataset :\tMSE : {mse}\tMAE : {mae}\tRMSE: {rmse}')
logger.info(
f'\n{label_name} Dataset :\tMSE : {mse}\tMAE : {mae}\tRMSE: {rmse}')
def test_mse(pred, target, exp):
mse = MSE()
assert mse.name == 'mse'
score = mse(pred=torch.tensor(pred), target=torch.tensor(target))
assert isinstance(score, torch.Tensor)
assert score.item() == exp
def test_mse():
mse = MSE()
assert mse.name == 'mse'
pred = torch.tensor([0., 1, 2, 3])
target = torch.tensor([0., 1, 2, 2])
score = mse(pred, target)
assert isinstance(score, torch.Tensor)
def __init__(self, HPARAMS):
super().__init__()
# HPARAMS
self.save_hyperparameters()
lstm_inp=512
lstm_h = HPARAMS['model_hidden_size']
alpha = HPARAMS['model_alpha']
beta = HPARAMS['model_beta']
gamma = HPARAMS['model_gamma']
csv_path = HPARAMS['speaker_csv_path']
self.encoder = Wav2Vec(pretrained=True)
for param in self.encoder.parameters():
param.requires_grad = False
for param in self.encoder.feature_extractor.conv_layers[5:].parameters():
param.requires_grad = True
self.lstm = nn.LSTM(lstm_inp, lstm_h, batch_first=True)
self.attention = Attention(lstm_h)
self.height_regressor = nn.Linear(lstm_h, 1)
self.age_regressor = nn.Linear(lstm_h, 1)
self.gender_classifier = nn.Linear(lstm_h, 1)
self.classification_criterion = MSE()
self.regression_criterion = MSE()
self.mae_criterion = MAE()
self.rmse_criterion = RMSELoss()
self.accuracy = Accuracy()
self.alpha = alpha
self.beta = beta
self.gamma = gamma
self.lr = HPARAMS['training_lr']
self.csv_path = csv_path
self.df = pd.read_csv(self.csv_path, sep=' ')
self.h_mean = self.df['Height'].mean()
self.h_std = self.df['Height'].std()
self.a_mean = self.df['Age'].mean()
self.a_std = self.df['Age'].std()
print(f"Model Details: #Params = {self.count_total_parameters()}\t#Trainable Params = {self.count_trainable_parameters()}")
def __init__(
self,
regression_task,
classification_task,
input_size,
hidden_size,
learning_rate,
classifier_lambda,
tanh_loss,
fill_missing_regression,
regressor_activation,
classifier_loss_weights=None,
**kwargs
):
super().__init__()
self.save_hyperparameters()
# Sanity checks
assert 0 <= classifier_lambda <= 1
# Layers
self.hidden_fc = nn.Linear(
in_features=input_size, out_features=hidden_size, bias=True
)
if classification_task:
self.classifier_hidden_fc = nn.Linear(
in_features=hidden_size,
out_features=hidden_size,
bias=True
)
self.classifier_fc = nn.Linear(
in_features=hidden_size,
out_features=2, # It's a binary classification
bias=True,
)
self._build_classifier_loss_weigths(classifier_loss_weights)
if regression_task:
self.regressor_hidden_fc = nn.Linear(
in_features=hidden_size,
out_features=hidden_size,
bias=True,
)
self.regressor_fc = nn.Linear(
in_features=hidden_size, out_features=1, bias=True # It's a regression
)
# Metrics
if classification_task:
self.f1 = F1()
self.precision= Precision()
self.recall = Recall()
if regression_task:
self.mse = MSE()