def validate_and_save(global_step, valid_set, listener, speller, optimizer, tf_rate):
# Validation
val_loss = []
val_ler = []
for batch_data, batch_label in valid_set:
batch_loss, batch_ler = batch_iterator(batch_data, batch_label, listener, speller, optimizer,
tf_rate, idx2char, is_training=False, data='libri', **conf['model_parameter'])
val_loss.append(batch_loss)
val_ler.extend(batch_ler)
val_loss = np.array([sum(val_loss)/len(val_loss)])
val_ler = np.array([sum(val_ler)/len(val_ler)])
print("Step:", global_step)
print("Loss:", sum(val_loss)/len(val_loss))
print("CER:", sum(val_ler)/len(val_ler))
torch.save(listener, listener_model_path+str(global_step))
torch.save(speller, speller_model_path+str(global_step))
for category in categories:
data[category] = {}
for ratio in tir:
global_step = 0
total = 0
conf['meta_variable']['data_path'] = 'TIMIT/timit_mfcc_39_{}_{}.pkl'.format(ratio, category)
X_test, y_test = load_dataset(**conf['meta_variable'])
test_set = create_dataloader(X_test, y_test, **conf['model_parameter'], **conf['training_parameter'], shuffle=False)
listener = torch.load(conf['training_parameter']['pretrained_listener_path'], map_location=lambda storage, loc: storage)
speller = torch.load(conf['training_parameter']['pretrained_speller_path'], map_location=lambda storage, loc: storage)
optimizer = torch.optim.Adam([{'params':listener.parameters()}, {'params':speller.parameters()}], lr=conf['training_parameter']['learning_rate'])
for batch_index,(batch_data,batch_label) in enumerate(test_set):
batch_loss, batch_ler = batch_iterator(batch_data, batch_label, listener, speller, optimizer, 0, is_training=False, **conf['model_parameter'])
total += np.array(batch_ler).mean()
global_step += 1
print('PER for {} {}: {}'.format(ratio, category, total / global_step), end='\r', flush=True)
data[category][ratio] = total / global_step
print()
df = pd.DataFrame(data)
df.to_csv('per_data.csv')
print()
df = pd.DataFrame(data)
df.to_csv('per_data.csv')
print(df)
batch_limit_counter = 0
for batch_data, batch_label in train_set:
print('batch step :', batch_step, end='\r', flush=True)
if emp_normalize:
batch_data = (batch_data - emp_mean) / emp_std
#print("Batch_lable", torch.argmax(batch_label, dim=-1), flush = True)
#print("Batch data min max: ", torch.max(batch_data), torch.min(batch_data), flush = True)
#batch_loss, batch_ler = batch_iterator(batch_data, batch_label, listener, speller, optimizer, tf_rate,
# is_training=True, data='libri', **conf['model_parameter'])
batch_loss, batch_ler = batch_iterator(batch_data,
batch_label,
listener,
speller,
optimizer,
tf_rate,
is_training=True,
data='libri',
**conf['model_parameter'])
#las_module.flatten_parameters()
train_loss.append(batch_loss)
train_ler.extend(batch_ler)
batch_step += 1
batch_limit_counter += 1
# if (global_step) % verbose_step == 0:
# log_writer.add_scalars('loss',{'train':batch_loss}, global_step)
