def __init__(self, num_classes=31):
super(DeepMEDA, self).__init__()
self.feature_layers = ResNet.resnet50(True)
self.mmd_marginal = mmd.MMD_loss()
if bottle_neck:
self.bottle = nn.Linear(2048, 256)
self.cls_fc = nn.Linear(256, num_classes)
else:
self.cls_fc = nn.Linear(2048, num_classes)
def adapt_loss(self, X, Y, adapt_loss):
"""Compute adaptation loss, currently we support mmd and coral
Arguments:
X {tensor} -- source matrix
Y {tensor} -- target matrix
adapt_loss {string} -- loss type, 'mmd' or 'coral'. You can add your own loss
Returns:
[tensor] -- adaptation loss tensor
"""
if adapt_loss == 'mmd':
mmd_loss = mmd.MMD_loss()
loss = mmd_loss(X, Y)
elif adapt_loss == 'coral':
loss = CORAL(X, Y)
else:
loss = 0
return loss
train_index = permutation[0:num_train]
train_data = all_train_X[train_index, :]
train_label = all_train_y[train_index, :]
x1 = torch.FloatTensor(train_data)
y1 = torch.FloatTensor(train_label)
x1 = Variable(x1)
y1 = Variable(y1)
m1, n1 = train_data.shape
net = Net(n_feature=n1, n_hidden=128, n_out=1)
loss_func = torch.nn.MSELoss()
optimizer = torch.optim.Adam(net.parameters(),
lr=0.001,
weight_decay=0.01)
mmd_loss = mmd.MMD_loss()
epochs = 300
for i in range(epochs):
prediction = net(x1)[0]
# loss = loss_func(prediction, y1)
loss = loss_func(prediction, y1) + mmd_loss(
net(x_all)[1],
net(x1)[1])
optimizer.zero_grad()
loss.backward()
optimizer.step()
print(i + 1, "loss:", loss.data.item())
x_test1 = torch.FloatTensor(test_data)
y_test1 = torch.FloatTensor(test_label)
