model_dir = logDir + model_name_B + '.pt'
print("Saving model at {} epoch to {}".format(epoch, model_dir))
max_val_acc_B = val_accuracy_B
torch.save(model_B.state_dict(), model_dir)
if max_val_acc_I <= val_accuracy_I:
model_dir = logDir + model_name_I + '.pt'
print("Saving model at {} epoch to {}".format(epoch, model_dir))
max_val_acc_I = val_accuracy_I
torch.save(model_I.state_dict(), model_dir)
training_end = datetime.now()
training_time = training_end - training_start
print("RAE training takes time {}".format(training_time))
model_B.is_fitted = True
model_I.is_fitted = True
model_B.eval()
model_I.eval()
# TEST
correct_B = 0
correct_I = 0
test_num = 0
for i, (XI, XB, y) in enumerate(test_loader):
XI, XB, y = XI.to(device), XB.to(device), y.long().to(device)
if XI.size()[0] != batch_size:
break
# choose model
if max_val_acc <= val_accuracy:
model_dir = logDir + model_name + '.pt'
print('Saving model at {} epoch to{}'.format(epoch, model_dir))
max_val_acc = val_accuracy
torch.save(model.state_dict(), model_dir)
training_end = datetime.now()
training_time = training_end -training_start
print("training takes time {}".format(training_time))
# In[9]:
model.is_fitted = True
model.eval()
# In[10]:
# testing set check
net_trained = VRAEC(num_class=num_class,
sequence_length=sequence_length,
number_of_features = number_of_features,
hidden_size = hidden_size,
hidden_layer_depth = hidden_layer_depth,
latent_length = latent_length,
batch_size = batch_size,
learning_rate = learning_rate,
max_val_acc_B = val_accuracy_B
torch.save(model_B.state_dict(), model_dir)
if max_val_acc_I <= val_accuracy_I:
model_dir = logDir + model_name_I + '.pt'
print("Saving model at {} epoch to {}".format(epoch, model_dir))
max_val_acc_I = val_accuracy_I
torch.save(model_I.state_dict(), model_dir)
training_end = datetime.now()
training_time = training_end - training_start
print("RAE training takes time {}".format(training_time))
# In[ ]:
model_B.is_fitted = True
model_I.is_fitted = True
model_B.eval()
model_I.eval()
# model_B_trained = VRAEC(num_class=num_class,
# sequence_length=sequence_length_B,
# number_of_features = number_of_features_B,
# hidden_size = hidden_size,
# hidden_layer_depth = hidden_layer_depth,
# latent_length = latent_length,
# batch_size = batch_size,
# learning_rate = learning_rate,
# n_epochs = n_epochs,
# dropout_rate = dropout_rate,
# max_val_acc_B = val_accuracy_B
# torch.save(model_B.state_dict(), model_dir)
if max_val_acc_I <= val_accuracy_I:
model_dir = logDir + model_name_I + '.pt'
print("Saving model at {} epoch to {}".format(epoch, model_dir))
max_val_acc_I = val_accuracy_I
torch.save(model_I.state_dict(), model_dir)
training_end = datetime.now()
training_time = training_end - training_start
print("RAE training takes time {}".format(training_time))
# In[8]:
model_B_pretrained.is_fitted = True
model_I.is_fitted = True
model_B_pretrained.eval()
model_I.eval()
# In[9]:
# TEST
correct_B = 0
correct_I = 0
test_num = 0
for i, (XI, XB, y) in enumerate(test_loader):
XI, XB, y = XI.to(device), XB.to(device), y.long().to(device)
# TODO: not save at the same time, may have bad common representation
if max_val_acc_B <= val_accuracy_B:
model_dir = logDir + model_name_B + '.pt'
print("Saving model at {} epoch to {}".format(epoch, model_dir))
max_val_acc_B = val_accuracy_B
torch.save(model_B.state_dict(), model_dir)
if max_val_acc_I <= val_accuracy_I:
model_dir = logDir + model_name_I + '.pt'
print("Saving model at {} epoch to {}".format(epoch, model_dir))
max_val_acc_I = val_accuracy_I
torch.save(model_I.state_dict(), model_dir)
# In[10]:
model_B.is_fitted = True
model_I.is_fitted = True
model_B.eval()
model_I.eval()
# model_B_trained = VRAEC(num_class=num_class,
# sequence_length=sequence_length_B,
# number_of_features = number_of_features_B,
# hidden_size = hidden_size,
# hidden_layer_depth = hidden_layer_depth,
# latent_length = latent_length,
# batch_size = batch_size,
# learning_rate = learning_rate,
# n_epochs = n_epochs,
# dropout_rate = dropout_rate,