def encoder(emb_sentence, params, name='encoded'):
"""
@param emb_sentence:
@param params:
@return:
"""
conv_num_features = utils.get_dict_value(params, 'conv_num_features')
conv_widths = utils.get_dict_value(params, 'conv_widths')
conv_keep_probs = utils.get_dict_value(params, 'conv_keep_probs')
mlp_config = utils.get_dict_value(params, 'mlp_config')
bipass_conv = utils.get_dict_value(params, 'bipass_conv')
mlp_activations = utils.get_dict_value(params, 'mlp_activations')
mlp_dropout_keep_probs = utils.get_dict_value(params, 'mlp_keep_probs')
use_no_conv_path = utils.get_dict_value(params, 'use_no_conv_path')
weight_wd_regularization = utils.get_dict_value(
params, 'weight_wd_regularization', 0.0)
bias_wd_regularization = utils.get_dict_value(params,
'bias_wd_regularization',
0.0)
if bipass_conv:
conv_group = [emb_sentence]
else:
if use_no_conv_path:
conv_group = [emb_sentence]
else:
conv_group = []
for i, (conv_num_feature,
conv_width) in enumerate(zip(conv_num_features, conv_widths)):
conv_out = nlp.conv1d_array(emb_sentence,
conv_num_feature,
conv_width,
name='conv%s' % (str(i)),
w_wds=weight_wd_regularization,
b_wds=bias_wd_regularization,
keep_probs=conv_keep_probs)
conv_group.append(conv_out)
conv_out, _ = misc.concat(conv_group)
mlp_out, _ = mlp.fully_connected_network(
conv_out,
mlp_config,
layer_activations=mlp_activations,
dropout_keep_probs=mlp_dropout_keep_probs)
return [tf.identity(mlp_out[0], name=name)], {}
def sentence_encoder(emb_sentence, params, name='encoded_sentence'):
"""
@param emb_sentence:
@param params:
@return:
"""
conv_num_features = utils.get_dict_value(params, 'conv_num_features',
[[100, 100, 100], [100]])
conv_widths = utils.get_dict_value(params, 'conv_widths', [[2, 3, 4], [3]])
conv_keep_probs = utils.get_dict_value(params, 'conv_keep_probs', 0.5)
mlp_config = utils.get_dict_value(params, 'mlp_config', [512])
bipass_conv = utils.get_dict_value(params, 'bipass_conv', False)
mlp_activations = utils.get_dict_value(params, 'mlp_activations',
'sigmoid')
mlp_dropout_keep_probs = utils.get_dict_value(params, 'mlp_keep_probs',
0.9)
use_no_conv_path = utils.get_dict_value(params, 'use_no_conv_path', False)
if bipass_conv:
conv_group = [emb_sentence]
else:
if use_no_conv_path:
conv_group = [emb_sentence]
else:
conv_group = []
for i, (conv_num_feature,
conv_width) in enumerate(zip(conv_num_features, conv_widths)):
conv_out = nlp.conv1d_array(emb_sentence,
conv_num_feature,
conv_width,
name='conv%s' % (str(i)),
w_wds=0.000,
b_wds=0.000,
keep_probs=conv_keep_probs)
conv_group.append(conv_out)
conv_out, _ = misc.concat(conv_group)
mlp_out, _ = mlp.fully_connected_network(
conv_out,
mlp_config,
layer_activations=mlp_activations,
dropout_keep_probs=mlp_dropout_keep_probs)
return [tf.identity(mlp_out[0], name=name)], {}