def inference(params=None):
x, _ = input_data([None, 5], name='x')
y, _ = input_data([None, 5], name='y')
x1, _ = fully_connected_network(x, [5, 1], name='x1')
y1, _ = fully_connected_network(y, [5, 1], name='y1')
d, _ = angle_distance(x1 + y1, name='d')
return d
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)], {}
def sentence_encoder(emb_sentence, word_emb, params, name='encoded_sentence'):
"""
@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')
char_conv_num_features = utils.get_dict_value(params, 'char_conv_num_features')
char_conv_widths = utils.get_dict_value(params, 'char_conv_widths')
char_use_no_conv_path = utils.get_dict_value(params, 'char_use_no_conv_path', False)
char_conv_keep_probs = utils.get_dict_value(params, 'char_conv_keep_probs')
char_weight_wd_regularization = utils.get_dict_value(params, 'char_weight_wd_regularization', 0.0)
char_bias_wd_regularization = utils.get_dict_value(params, 'char_bias_wd_regularization', 0.0)
word_weight_wd_regularization = utils.get_dict_value(params, 'word_weight_wd_regularization', 0.0)
word_bias_wd_regularization = utils.get_dict_value(params, 'word_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=word_weight_wd_regularization,
b_wds=word_bias_wd_regularization, keep_probs=conv_keep_probs)
conv_group.append(conv_out)
# deal with the word path
if (char_conv_widths is not None) and (char_conv_num_features is not None):
if char_use_no_conv_path:
conv_group.append(word_emb)
for i, (char_conv_num_feature, char_conv_width) in enumerate(zip(char_conv_num_features, char_conv_widths)):
conv_out = nlp.conv1d_array(word_emb, char_conv_num_feature, char_conv_width,name='char_conv%s'%(str(i)),
w_wds = char_weight_wd_regularization,
b_wds = char_bias_wd_regularization, keep_probs=char_conv_keep_probs)
conv_group.append(conv_out)
else:
conv_group.append(word_emb)
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 inference(params):
feature_count = utils.get_dict_value(params, 'feature_count')
mlp_config = utils.get_dict_value(params, 'mlp_config')
mlp_activations = utils.get_dict_value(params, 'mlp_activations')
mlp_dropout_keep_probs = utils.get_dict_value(params,
'mlp_dropout_keep_probs')
x = tf.placeholder(tf.float32, [None, feature_count], 'features')
mlp_out, _ = mlp.fully_connected_network(
[x],
mlp_config,
layer_activations=mlp_activations,
dropout_keep_probs=mlp_dropout_keep_probs)
return mlp_out, _