def get_gradients(self, loss, params):
grads = K.gradients(loss, params)
if hasattr(self, 'clipnorm') and self.clipnorm > 0:
norm = K.sqrt(sum([K.sum(K.square(g)) for g in grads]))
grads = [clip_norm(g, self.clipnorm, norm) for g in grads]
if hasattr(self, 'clipvalue') and self.clipvalue > 0:
grads = [K.clip(g, -self.clipvalue, self.clipvalue) for g in grads]
return grads
def get_gradients(self, loss, params):
grads = K.gradients(loss, params)
if hasattr(self, 'clipnorm') and self.clipnorm > 0:
norm = K.sqrt(sum([K.sum(K.square(g)) for g in grads]))
grads = [clip_norm(g, self.clipnorm, norm) for g in grads]
if hasattr(self, 'clipvalue') and self.clipvalue > 0:
grads = [K.clip(g, -self.clipvalue, self.clipvalue) for g in grads]
return grads
def output(self, train=False):
X = self.get_input('input')(train)
if self.mode == 'ave':
s = K.mean(X, axis=1)
return s
if self.mode == 'sum':
s = K.sum(X, axis=1)
return s
elif self.mode == 'mul':
s = K.prod(X, axis=1)
return s
else:
raise Exception('Unknown merge mode')
def output(self, train=False):
X = self.get_input('input')(train)
if self.mode == 'ave':
s = K.mean(X, axis=1)
return s
if self.mode == 'sum':
s = K.sum(X, axis=1)
return s
elif self.mode == 'mul':
s = K.prod(X, axis=1)
return s
else:
raise Exception('Unknown merge mode')
def __call__(self, p):
return p / K.sqrt(K.sum(K.square(p), axis=-1, keepdims=True))
def __call__(self, p):
norms = K.sqrt(K.sum(K.square(p), axis=0))
desired = K.clip(norms, 0, self.m)
p = p * (desired / (1e-7 + norms))
return p
def __call__(self, p):
return p / K.sqrt(K.sum(K.square(p), axis=-1, keepdims=True))
def __call__(self, p):
norms = K.sqrt(K.sum(K.square(p), axis=0))
desired = K.clip(norms, 0, self.m)
p = p * (desired / (1e-7 + norms))
return p