def __init__(self, rng, n_in, n_out, W=None, b=None,
activation=T.tanh,hidden_size=100):
self.W = theano.shared(value=ortho_weight(hidden_size), name='W', borrow=True)
self.activation = activation
self.hidden_layer = HiddenLayer2(rng,2*5*n_in,n_out)
self.params = [self.W] + self.hidden_layer.params
def __init__(self, rng, n_in, n_out, tensor_num=3, activation=T.tanh):
self.tensor_num = tensor_num
self.W = []
for i in range(tensor_num):
self.W.append(theano.shared(value=ortho_weight(100), borrow=True))
self.activation = activation
self.hidden_layer = HiddenLayer2(rng, tensor_num * 5 * n_in, n_out)
self.params = self.W + self.hidden_layer.params
def __init__(self, rng, n_in, n_out, W=None, b=None,
activation=T.tanh,hidden_size=100):
self.W = theano.shared(value=ortho_weight(hidden_size), borrow=True)
self.activation = activation
self.conv_layer = LeNetConvPoolLayer2(rng,filter_shape=(8,2,3,3),
image_shape=(200,2,50,50)
,poolsize=(3,3),non_linear='relu')
self.hidden_layer = HiddenLayer2(rng,2048,n_out)
self.params = [self.W,] + self.conv_layer.params + self.hidden_layer.params