def loss(self, predict, y):
# Add L2 regularization for all the weights.
reg_loss = 0.0
for name, weight in self.params.items():
reg_loss += np.sum(weight**2) * 0.5
return layers.softmax_cross_entropy(predict,
y) + weight_decay * reg_loss
def loss(self, predict, y):
return layers.softmax_cross_entropy(predict, y)
def loss(self, predict, y):
# Compute softmax loss between the output and the label.
return layers.softmax_cross_entropy(predict, y)
def loss(self, predict, y):
return layers.softmax_cross_entropy(predict, y)
def check_fn(weights):
return layers.softmax_cross_entropy(
f(x=x, softmax_label=fake_y, fc_weight=weights),
fake_y)
def loss(self, predict, y):
# Add L2 regularization for all the weights.
reg_loss = 0.0
for name, weight in self.params.items():
reg_loss += np.sum(weight ** 2)
return layers.softmax_cross_entropy(predict, y) + 0.5 * weight_decay * reg_loss
def check_fn(weights):
return layers.softmax_cross_entropy(
f(x=x, softmax_label=fake_y, fc_weight=weights), fake_y)
def loss(self, predict, y):
# Compute softmax loss between the output and the label.
return layers.softmax_cross_entropy(predict, y)
