def load_params(self, model):
self.W = sharedX(model[0])
self.U = sharedX(model[1])
self.b = sharedX(model[2])
self.Wpc = sharedX(model[3])
self.Uph = sharedX(model[4])
self.bc = sharedX(model[5])
self.Ua = sharedX(model[6])
self.Wc = sharedX(model[7])
if self.selector:
self.Wsel = sharedX(model[8])
self.bsel = sharedX(model[9])
self.pack_params()
def orthogonal(shape, scale=1.1):
''' From Lasagne
'''
flat_shape = (shape[0], np.prod(shape[1:]))
a = np.random.normal(0.0, 1.0, flat_shape)
u, _, v = np.linalg.svd(a, full_matrices=False)
q = u if u.shape == flat_shape else v # pick the one with the correct shape
q = q.reshape(shape)
return sharedX(scale * q[:shape[0], :shape[1]])
def orthogonal(shape, scale=1.1):
''' From Lasagne
'''
flat_shape = (shape[0], np.prod(shape[1:]))
a = np.random.normal(0.0, 1.0, flat_shape)
u, _, v = np.linalg.svd(a, full_matrices=False)
q = u if u.shape == flat_shape else v # pick the one with the correct shape
q = q.reshape(shape)
return sharedX(scale * q[:shape[0], :shape[1]])
def orthogonal(shape, scale=1.1):
''' From Lasagne. Reference: Saxe et al., http://arxiv.org/abs/1312.6120
'''
flat_shape = (shape[0], np.prod(shape[1:]))
a = np.random.normal(0.0, 1.0, flat_shape)
u, _, v = np.linalg.svd(a, full_matrices=False)
# pick the one with the correct shape
q = u if u.shape == flat_shape else v
q = q.reshape(shape)
return sharedX(scale * q[:shape[0], :shape[1]])
def init_params(self):
W = self.init((self.in_dim, self.h_dim))
self.W = np.concatenate([
ortho_weight((self.in_dim, self.h_dim)),
ortho_weight((self.in_dim, self.h_dim)),
ortho_weight((self.in_dim, self.h_dim)),
ortho_weight((self.in_dim, self.h_dim))
],
axis=1)
self.W = sharedX(self.W)
self.U = np.concatenate([
ortho_weight((self.h_dim, self.h_dim)),
ortho_weight((self.h_dim, self.h_dim)),
ortho_weight((self.h_dim, self.h_dim)),
ortho_weight((self.h_dim, self.h_dim))
],
axis=1)
self.U = sharedX(self.U)
self.b = shared_zeros((4 * self.h_dim, ))
self.pack_params()
def init_params(self):
W = self.init((self.in_dim, self.h_dim))
self.W = np.concatenate([
ortho_weight((self.in_dim, self.h_dim)),
ortho_weight((self.in_dim, self.h_dim)),
ortho_weight((self.in_dim, self.h_dim)),
ortho_weight((self.in_dim, self.h_dim))
],
axis=1)
self.W = sharedX(self.W)
self.U = np.concatenate([
ortho_weight((self.h_dim, self.h_dim)),
ortho_weight((self.h_dim, self.h_dim)),
ortho_weight((self.h_dim, self.h_dim)),
ortho_weight((self.h_dim, self.h_dim))
],
axis=1)
self.U = sharedX(self.U)
self.b = shared_zeros((4 * self.h_dim, ))
# attention params
# e^i = Ua(tanh(Wctx.dot(context) + Uctx.dot(h_tm1) + bctx))
self.Wpc = self.init((self.ctx_dim, self.pctx_dim))
self.Uph = self.init((self.h_dim, self.pctx_dim))
self.bc = shared_zeros((self.pctx_dim, ))
self.Ua = self.init((self.pctx_dim, 1))
self.ba = shared_zeros((1, ))
self.Wc = self.init((self.ctx_dim, self.h_dim * 4))
if self.selector:
self.Wsel = self.init(
(self.h_dim, 1)
) # if Wsel=h_dim*h_dim what will happen, is it mean that it could select different feature for different sample?
self.bsel = shared_zeros((1, ))
self.pack_params()
def normal(shape, scale=0.05):
return sharedX(np.random.randn(*shape) * scale)
def uniform(shape, scale=0.05):
return sharedX(np.random.uniform(low=-scale, high=scale, size=shape))
def load_params(self,model):
self.W = sharedX(model[0])
self.pack_params()
def xavier(shape, scale=None):
var_w = 2. / (shape[0] + shape[1])
return sharedX(np.random.normal(0., np.sqrt(var_w), size=shape))
def normal(shape, scale=0.05):
return sharedX(np.random.randn(*shape) * scale)
def uniform(shape, scale=0.05):
return sharedX(np.random.uniform(low=-scale, high=scale, size=shape))