def param_init_gru(options, param, prefix='gru', nin=None, dim=None):
param[prefix + '_W'] = numpy.concatenate(
[
uniform_weight(nin, dim), uniform_weight(nin, dim)
],
axis=1)
param[prefix + '_U'] = numpy.concatenate(
[
ortho_weight(dim), ortho_weight(dim)
],
axis=1)
param[prefix + '_b'] = zero_vector(2 * dim)
param[prefix + '_Wx'] = uniform_weight(nin, dim)
param[prefix + '_Ux'] = ortho_weight(dim)
param[prefix + '_bx'] = zero_vector(dim)
return param
python类uniform_weight()的实例源码
def param_init_encoder(options, params, prefix='lstm_encoder'):
n_x = options['n_x']
n_h = options['n_h']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix, 'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix, 'U')] = U
params[_p(prefix,'b')] = zero_bias(4*n_h)
# It is observed that setting a high initial forget gate bias for LSTMs can
# give slighly better results (Le et al., 2015). Hence, the initial forget
# gate bias is set to 3.
params[_p(prefix, 'b')][n_h:2*n_h] = 3*np.ones((n_h,)).astype(theano.config.floatX)
return params
def param_init_encoder(options, params, prefix='gru_encoder'):
n_x = options['n_x']
n_h = options['n_h']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix,'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix,'U')] = U
params[_p(prefix,'b')] = zero_bias(2*n_h)
Wx = uniform_weight(n_x, n_h)
params[_p(prefix,'Wx')] = Wx
Ux = ortho_weight(n_h)
params[_p(prefix,'Ux')] = Ux
params[_p(prefix,'bx')] = zero_bias(n_h)
return params
def init_params(options,W):
params = OrderedDict()
# W is initialized by the pretrained word embedding
params['Wemb'] = W.astype(config.floatX)
# otherwise, W will be initialized randomly
# n_words = options['n_words']
# n_x = options['n_x']
# params['Wemb'] = uniform_weight(n_words,n_x)
length = len(options['filter_shapes'])
for idx in range(length):
params = param_init_encoder(options['filter_shapes'][idx],params,prefix=_p('cnn_encoder',idx))
n_h = options['feature_maps'] * length
params['Wy'] = uniform_weight(n_h,options['n_y'])
params['by'] = zero_bias(options['n_y'])
return params
def init_params(options,W):
n_h = options['n_h']
n_y = options['n_y']
params = OrderedDict()
# W is initialized by the pretrained word embedding
params['Wemb'] = W.astype(config.floatX)
# otherwise, W will be initialized randomly
# n_words = options['n_words']
# n_x = options['n_x']
# params['Wemb'] = uniform_weight(n_words,n_x)
# bidirectional LSTM
params = param_init_encoder(options,params,prefix="gru_encoder")
params = param_init_encoder(options,params,prefix="gru_encoder_rev")
params['Wy'] = uniform_weight(2*n_h,n_y)
params['by'] = zero_bias(n_y)
return params
def init_params(options,W):
n_h = options['n_h']
n_y = options['n_y']
params = OrderedDict()
# W is initialized by the pretrained word embedding
params['Wemb'] = W.astype(config.floatX)
# otherwise, W will be initialized randomly
# n_words = options['n_words']
# n_x = options['n_x']
# params['Wemb'] = uniform_weight(n_words,n_x)
# bidirectional LSTM
params = param_init_encoder(options,params,prefix="lstm_encoder")
params = param_init_encoder(options,params,prefix="lstm_encoder_rev")
params['Wy'] = uniform_weight(2*n_h,n_y)
params['by'] = zero_bias(n_y)
return params
def param_init_encoder(options, params, prefix='encoder'):
n_x = options['n_x']
n_h = options['n_h']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix, 'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix, 'U')] = U
params[_p(prefix,'b')] = zero_bias(4*n_h)
params[_p(prefix, 'b')][n_h:2*n_h] = 3*np.ones((n_h,)).astype(theano.config.floatX)
return params
def param_init_encoder(options, params, prefix='encoder'):
n_x = options['n_x']
n_h = options['n_h']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix, 'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix, 'U')] = U
params[_p(prefix,'b')] = zero_bias(4*n_h)
params[_p(prefix, 'b')][n_h:2*n_h] = 3*np.ones((n_h,)).astype(theano.config.floatX)
return params
def init_params(options,W):
n_words = options['n_words']
n_x = options['n_x']
n_h = options['n_h']
params = OrderedDict()
# word embedding
# params['Wemb'] = uniform_weight(n_words,n_x)
params['Wemb'] = W.astype(config.floatX)
params = param_init_decoder(options,params)
params['Vhid'] = uniform_weight(n_h,n_x)
params['bhid'] = zero_bias(n_words)
return params
def param_init_encoder(options, params, prefix='lstm_encoder'):
n_x = options['n_x']
n_h = options['n_h']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix, 'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix, 'U')] = U
params[_p(prefix,'b')] = zero_bias(4*n_h)
# It is observed that setting a high initial forget gate bias for LSTMs can
# give slighly better results (Le et al., 2015). Hence, the initial forget
# gate bias is set to 3.
params[_p(prefix, 'b')][n_h:2*n_h] = 3*np.ones((n_h,)).astype(theano.config.floatX)
return params
def init_params(options):
n_words = options['n_words']
n_x = options['n_x']
n_h = options['n_h']
params = OrderedDict()
params['Wemb'] = uniform_weight(n_words,n_x)
params = param_init_decoder(options,params,prefix='decoder_h1')
options['n_x'] = n_h
params = param_init_decoder(options,params,prefix='decoder_h2')
options['n_x'] = n_x
params['Vhid'] = uniform_weight(n_h,n_words)
params['bhid'] = zero_bias(n_words)
return params
def init_params(options,W):
n_h = options['n_h']
n_y = options['n_y']
params = OrderedDict()
# W is initialized by the pretrained word embedding
params['Wemb'] = W.astype(config.floatX)
# otherwise, W will be initialized randomly
# n_words = options['n_words']
# n_x = options['n_x']
# params['Wemb'] = uniform_weight(n_words,n_x)
# bidirectional LSTM
params = param_init_encoder(options,params,prefix="lstm_encoder")
params = param_init_encoder(options,params,prefix="lstm_encoder_rev")
params['Wy'] = uniform_weight(2*n_h,n_y)
params['by'] = zero_bias(n_y)
return params
def param_init_fflayer(options,
param,
prefix='ff',
nin=None,
nout=None,
ortho=True):
param[prefix + '_W'] = uniform_weight(nin, nout)
param[prefix + '_b'] = zero_vector(nout)
return param
def param_init_decoder(options, params, prefix='decoder_gru'):
n_x = options['n_x']
n_h = options['n_h']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix,'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix,'U')] = U
params[_p(prefix,'b')] = zero_bias(2*n_h)
Wx = uniform_weight(n_x, n_h)
params[_p(prefix,'Wx')] = Wx
Ux = ortho_weight(n_h)
params[_p(prefix,'Ux')] = Ux
params[_p(prefix,'bx')] = zero_bias(n_h)
params[_p(prefix,'b0')] = zero_bias(n_h)
return params
def init_params(options):
n_x = options['n_x']
n_h = options['n_h']
params = OrderedDict()
params = param_init_decoder(options,params)
params['Vhid'] = uniform_weight(n_h,n_x)
params['bhid'] = zero_bias(n_x)
return params
def param_init_decoder(options, params, prefix='decoder'):
n_x = options['n_x']
n_h = options['n_h']
n_z = options['n_z']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix, 'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix, 'U')] = U
C = np.concatenate([uniform_weight(n_z,n_h),
uniform_weight(n_z,n_h),
uniform_weight(n_z,n_h),
uniform_weight(n_z,n_h)], axis=1)
params[_p(prefix,'C')] = C
params[_p(prefix,'b')] = zero_bias(4*n_h)
params[_p(prefix, 'b')][n_h:2*n_h] = 3*np.ones((n_h,)).astype(theano.config.floatX)
C0 = uniform_weight(n_z, n_h)
params[_p(prefix,'C0')] = C0
params[_p(prefix,'b0')] = zero_bias(n_h)
params[_p(prefix,'b_y')] = zero_bias(n_x) # 48
return params
def param_init_decoder(options, params, prefix='decoder'):
n_x = options['n_x']
n_h = options['n_h']
n_z = options['n_z']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix, 'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix, 'U')] = U
C = np.concatenate([uniform_weight(n_z,n_h),
uniform_weight(n_z,n_h),
uniform_weight(n_z,n_h),
uniform_weight(n_z,n_h)], axis=1)
params[_p(prefix,'C')] = C
params[_p(prefix,'b')] = zero_bias(4*n_h)
params[_p(prefix, 'b')][n_h:2*n_h] = 3*np.ones((n_h,)).astype(theano.config.floatX)
C0 = uniform_weight(n_z, n_h)
params[_p(prefix,'C0')] = C0
params[_p(prefix,'b0')] = zero_bias(n_h)
#params[_p(prefix,'b_y')] = zero_bias(n_x) # 48
return params
def param_init_decoder(options, params, prefix='decoder_lstm'):
n_x = options['n_x']
n_h = options['n_h']
n_z = options['n_z']
W = np.concatenate([uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h),
uniform_weight(n_x,n_h)], axis=1)
params[_p(prefix,'W')] = W
U = np.concatenate([ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h),
ortho_weight(n_h)], axis=1)
params[_p(prefix,'U')] = U
#C = np.concatenate([uniform_weight(n_z,n_h),
# uniform_weight(n_z,n_h),
# uniform_weight(n_z,n_h),
# uniform_weight(n_z,n_h)], axis=1)
#params[_p(prefix,'C')] = C
params[_p(prefix,'b')] = zero_bias(4*n_h)
#params[_p(prefix, 'b')][n_h:2*n_h] = 3*np.ones((n_h,)).astype(theano.config.floatX)
C0 = uniform_weight(n_z, n_h)
params[_p(prefix,'C0')] = C0
params[_p(prefix,'b0')] = zero_bias(n_h)
return params
