bn_flag=False,
device=device)
z_dim = 128
generator_hidden_units = (256, 512)
tanh_scale = 20
label_eps = 0.1
L2_regularization_discriminator = 0
elif datasource in ['miniImageNet_embedding', 'tieredImageNet_embedding']:
from FC640 import FC640
from WGenerator2 import WeightDiscriminator, WeightGenerator
net = FC640(dim_output=num_classes_per_task,
num_hidden_units=(128, 32),
device=device)
z_dim = 128
encoder = FC640(dim_output=z_dim,
num_hidden_units=(256, 128),
device=device)
generator_hidden_units = (256, 512)
tanh_scale = 20
L2_regularization_discriminator = 0
label_eps = 0.1
# set the clipping value
clip_grad_value = args.clip_grad_value
device=device)
elif (datasource == 'miniImageNet') or (datasource == 'tieredImageNet'):
from ConvNet import ConvNet
net = ConvNet(dim_input=(3, 84, 84),
dim_output=num_classes_per_task,
num_filters=(32, 32, 32, 32),
filter_size=(3, 3),
device=device)
elif (datasource
== 'miniImageNet_embedding') or (datasource
== 'tieredImageNet_embedding'):
from FC640 import FC640
net = FC640(dim_output=num_classes_per_task,
num_hidden_units=(256, 64),
device=device)
else:
sys.exit('Unknown dataset')
# endregion
w_shape = net.get_weight_shape()
# print(w_shape)
num_weights = get_num_weights(net)
print('Number of parameters of base model = {0:d}'.format(num_weights))
num_val_tasks = args.num_val_tasks
p_dropout_base = args.p_dropout_base
sm = torch.nn.Softmax(dim=1)
if datasource in ['omniglot', 'miniImageNet']:
from ConvNet import ConvNet
DIM_INPUT = {'omniglot': (1, 28, 28), 'miniImageNet': (3, 84, 84)}
net = ConvNet(dim_input=DIM_INPUT[datasource],
dim_output=None,
num_filters=(32, 32, 32, 32),
filter_size=(3, 3),
device=device)
elif datasource in ['miniImageNet_640', 'tieredImageNet_640']:
import pickle
from FC640 import FC640
net = FC640(num_hidden_units=(128, 32), dim_output=None, device=device)
else:
sys.exit('Unknown dataset!')
weight_shape = net.get_weight_shape()
# -------------------------------------------------------------------------------------------------
# Parse training parameters
# -------------------------------------------------------------------------------------------------
meta_lr = args.meta_lr
print('Meta learning rate = {0}'.format(meta_lr))
num_tasks_per_minibatch = args.minibatch_size
print('Number of tasks per minibatch = {0:d}'.format(num_tasks_per_minibatch))
num_meta_updates_print = int(1000 / num_tasks_per_minibatch)
num_epochs_save = 1