# Initialize models
model_B = 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,
cuda=cuda,
model_name=model_name_B,
header=header_B,
device=device)
model_B.to(device)
model_I = VRAEC(num_class=num_class,
sequence_length=sequence_length_I,
number_of_features=number_of_features_I,
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,
cuda=cuda,
model_name=model_name_I,
header=header_I,
device=device)
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,
cuda = cuda,
print_every=print_every,
clip=clip,
max_grad_norm=max_grad_norm,
dload = logDir,
model_name=model_name,
header=header,
device = device)
model.to(device)
# In[7]:
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
cl_loss_fn = nn.NLLLoss()
recon_loss_fn = nn.MSELoss()
# In[8]:
# 1st stage training: with recon_loss
cuda=cuda,
print_every=print_every,
clip=clip,
max_grad_norm=max_grad_norm,
dload=logDir,
model_name=model_name_B,
header=header_B,
device=device)
model_B_pretrained_dir = logDir + model_name_B + '.pt'
if device == torch.device('cpu'):
model_B_pretrained.load_state_dict(
torch.load(model_B_pretrained_dir, map_location=torch.device('cpu')))
else:
model_B_pretrained.load_state_dict(torch.load(model_B_pretrained_dir))
model_B_pretrained.to(device)
model_B_pretrained.eval()
print("load model from")
print(model_name_B)
model_I = VRAEC(num_class=num_class,
sequence_length=sequence_length_I,
number_of_features=number_of_features_I,
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,
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,
cuda=cuda,
print_every=print_every,
clip=clip,
max_grad_norm=max_grad_norm,
dload=logDir,
model_name=model_name_B,
header=header_B,
device=device)
model_B.to(device)
model_I = VRAEC(num_class=num_class,
sequence_length=sequence_length_I,
number_of_features=number_of_features_I,
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,
cuda=cuda,
print_every=print_every,
clip=clip,
max_grad_norm=max_grad_norm,
batch_size=batch_size,
learning_rate=learning_rate,
n_epochs=n_epochs,
dropout_rate=dropout_rate,
cuda=cuda,
print_every=print_every,
clip=clip,
max_grad_norm=max_grad_norm,
dload=logDir,
model_name=model_name_B,
header=header_B,
w_r=w_r,
w_k=w_k,
w_c=w_c,
device=device)
model_B.to(device)
model_I = VRAEC(num_class=num_class,
sequence_length=sequence_length_I,
number_of_features=number_of_features_I,
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,
cuda=cuda,
print_every=print_every,
clip=clip,
max_grad_norm=max_grad_norm,
model_B = 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,
cuda=cuda,
model_name=model_name_B,
header=header_B,
device=device)
model_B.to(device)
model_I_pretrained = VRAEC(num_class=num_class,
sequence_length=sequence_length_I,
number_of_features=number_of_features_I,
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,
cuda=cuda,
model_name=model_name_I,
header=header_I,
device=device)