def call(self, inputs, mask=None, **kwargs):
input, key_masks = inputs
querys, keys, values = input, input, input
align = self.attention([querys, keys])
output = self.softmax_weight_sum([align, values, key_masks])
if self.use_layer_norm:
output = self.layer_norm(output)
return reduce_mean(output, 1, keep_dims=True)
def call(self, inputs, mask=None, **kwargs):
user_query, keys, keys_length = inputs
hist_len = keys.get_shape()[1]
key_masks = tf.sequence_mask(keys_length, hist_len)
query = self.dense(user_query)
align = self.attention([query, keys])
output = self.softmax_weight_sum([align, keys, key_masks])
if self.use_res:
output += keys
return reduce_mean(output, 1, keep_dims=True)
def call(self, seq_value_len_list, mask=None, **kwargs):
if not isinstance(seq_value_len_list, list):
seq_value_len_list = [seq_value_len_list]
if len(seq_value_len_list) == 1:
return seq_value_len_list[0]
expand_seq_value_len_list = list(map(lambda x: tf.expand_dims(x, axis=-1), seq_value_len_list))
a = concat_func(expand_seq_value_len_list)
if self.mode == "mean":
hist = reduce_mean(a, axis=-1, )
if self.mode == "sum":
hist = reduce_sum(a, axis=-1, )
if self.mode == "max":
hist = reduce_max(a, axis=-1, )
return hist