def setUp(self):
#########
# toy data
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
self.X = torch.tensor([[1, 2], [3, 4]],
dtype=torch.float,
device=device)
self.Y = torch.tensor([0, 1], dtype=torch.int64, device=device)
self.train_loader = torch.utils.data.DataLoader(
torch.utils.data.TensorDataset(self.X, self.Y), batch_size=2)
#########
# base kn
self.kn = greedyFeedforward()
self.kn.add_layer(
kFullyConnected(X=self.X,
n_out=2,
kernel='gaussian',
sigma=3,
bias=True))
self.kn.add_layer(
kFullyConnected(X=self.X,
n_out=2,
kernel='gaussian',
sigma=2,
bias=True))
# manually set some weights
self.kn.layer0.weight.data = torch.Tensor([[.1, .2], [.5, .7]])
self.kn.layer0.bias.data = torch.Tensor([0., 0.])
self.kn.layer1.weight.data = torch.Tensor([[1.2, .3], [.2, 1.7]])
self.kn.layer1.bias.data = torch.Tensor([0.1, 0.2])
self.kn.add_critic(self.kn.layer1.phi)
self.kn.add_loss(torch.nn.CosineSimilarity())
self.kn.add_metric(torch.nn.CosineSimilarity())
self.kn.add_loss(torch.nn.CrossEntropyLoss(reduction='sum'))
self.kn.add_metric(torch.nn.CrossEntropyLoss(reduction='sum'))
#########
# ensemble
self.kn_ensemble = greedyFeedforward()
self.kn_ensemble.add_layer(K.to_ensemble(self.kn.layer0, batch_size=1))
self.kn_ensemble.add_layer(K.to_ensemble(self.kn.layer1, batch_size=1))
self.kn_ensemble.add_critic(self.kn.layer1.phi)
self.kn_ensemble.add_loss(torch.nn.CosineSimilarity())
self.kn_ensemble.add_metric(torch.nn.CosineSimilarity())
self.kn_ensemble.add_loss(torch.nn.CrossEntropyLoss(reduction='sum'))
self.kn_ensemble.add_metric(torch.nn.CrossEntropyLoss(reduction='sum'))
self.kn.to(device)
self.kn_ensemble.to(device)
def to_ensemble_(self, batch_size):
"""
Convert layers in the stack into equivalent ensemble layers.
Note that this is an in-place function.
Parameters
----------
batch_size : int
Size of each component layer in the ensemble. One batch_size for
all layers in the stack.
"""
for i in range(self._comp_counter):
component = getattr(self, 'comp'+str(i))
setattr(self, 'comp'+str(i), K.to_ensemble(component, batch_size))
def to_ensemble(self, batch_size):
return K.to_ensemble(self, batch_size)