我正在 Keras 中实现所描述的 LSTM 架构here http://nlp.cs.rpi.edu/paper/multilingualmultitask.pdf。我认为我已经非常接近了,尽管我在共享层和特定语言层的组合方面仍然存在问题。这是公式(大约):y = g * y^s + (1 - g) * y^u
这是我尝试过的代码:
### Linear Layers ###
univ_linear = Dense(50, activation=None, name='univ_linear')
univ_linear_en = univ_linear(en_encoded)
univ_linear_es = univ_linear(es_encoded)
print(univ_linear_en)
# Gate >> g
gate_en = Dense(50, activation='sigmoid', name='gate_en')(en_encoded)
gate_es = Dense(50, activation='sigmoid', name='gate_es')(es_encoded)
print(gate_en)
print(gate_es)
# EN >> y^s
spec_linear_en = Dense(50, activation=None, name='spec_linear_en') (en_encoded)
print(spec_linear_en)
# g * y^s
gated_spec_linear_en = Multiply()([gate_en, spec_linear_en])
print(gated_spec_linear_en)
# ES >> y^s
spec_linear_es = Dense(50, activation=None, name='spec_linear_es')(es_encoded)
print(spec_linear_es)
# g * y^s
gated_spec_linear_es = Multiply()([gate_es, spec_linear_es])
print(gated_spec_linear_es)
# 1 - Gate >> (1 - g)
only_ones_en = K.ones(gate_en.shape)
univ_gate_en = Subtract()([only_ones_en, gate_en])
print(univ_gate_en)
only_ones_es = K.ones(gate_es.shape)
univ_gate_es = Subtract()([only_ones_es, gate_es])
print(univ_gate_es)
# (1 - g) * y^u
gated_univ_linear_en = Multiply()([univ_gate_en, univ_linear_en])
print(gated_univ_linear_en)
gated_univ_linear_es = Multiply()([univ_gate_es, univ_linear_es])
print(gated_univ_linear_es)
out_en = Add()([gated_spec_linear_en, gated_univ_linear_en])
print(out_en)
out_es = Add()([gated_spec_linear_es, gated_univ_linear_es])
print(out_es)
当我编译模型时,出现以下错误:
AttributeError: 'NoneType' object has no attribute '_inbound_nodes'
不过,当我替换时,我的模型编译没有错误(1 - g) * y^u
by g * y^u
:
# (1 - g) * y^u
gated_univ_linear_en = Multiply()([gate_en, univ_linear_en])
print(gated_univ_linear_en)
gated_univ_linear_es = Multiply()([gate_es, univ_linear_es])
print(gated_univ_linear_es)
因此,我认为问题出在注释下的代码上# 1 - Gate >> (1 - g)
,更准确地说是减法(1 - g)
.
有谁知道问题到底是什么以及我如何解决它?