回答此问题可获得 20 贡献值,回答如果被采纳可获得 50 分。
<p>我正试图用Colab中的Keras实现一个简单的字级序列到序列模型。我正在使用Keras注意层。以下是模型的定义:</p>
<pre><code>embedding_size=200
UNITS=128
encoder_inputs = Input(shape=(None,), name="encoder_inputs")
encoder_embs=Embedding(num_encoder_tokens, embedding_size, name="encoder_embs")(encoder_inputs)
#encoder lstm
encoder = LSTM(UNITS, return_state=True, name="encoder_LSTM") #(encoder_embs)
encoder_outputs, state_h, state_c = encoder(encoder_embs)
encoder_states = [state_h, state_c]
decoder_inputs = Input(shape=(None,), name="decoder_inputs")
decoder_embs = Embedding(num_decoder_tokens, embedding_size, name="decoder_embs")(decoder_inputs)
#decoder lstm
decoder_lstm = LSTM(UNITS, return_sequences=True, return_state=True, name="decoder_LSTM")
decoder_outputs, _, _ = decoder_lstm(decoder_embs, initial_state=encoder_states)
attention=Attention(name="attention_layer")
attention_out=attention([encoder_outputs, decoder_outputs])
decoder_concatenate=Concatenate(axis=-1, name="concat_layer")([decoder_outputs, attention_out])
decoder_outputs = TimeDistributed(Dense(units=num_decoder_tokens,
activation='softmax', name="decoder_denseoutput"))(decoder_concatenate)
model=Model([encoder_inputs, decoder_inputs], decoder_outputs, name="s2s_model")
model.compile(optimizer='RMSprop', loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()
</code></pre>
<p>模型编译很好,没有任何问题。编码器和解码器的输入和输出形状为:</p>
<pre><code>Encoder training input shape: (4000, 21)
Decoder training input shape: (4000, 12)
Decoder training target shape: (4000, 12, 3106)
--
Encoder test input shape: (385, 21)
</code></pre>
<p>这是model.fit代码:</p>
<pre><code>model.fit([encoder_training_input, decoder_training_input], decoder_training_target,
epochs=100,
batch_size=32,
validation_split=0.2,)
</code></pre>
<p>当我运行拟合阶段时,我从连接层中得到以下错误:</p>
<pre><code>ValueError: Dimension 1 in both shapes must be equal, but are 12 and 32.
Shapes are [32,12] and [32,32]. for '{{node s2s_model/concat_layer/concat}} = ConcatV2[N=2, T=DT_FLOAT, Tidx=DT_INT32](s2s_model/decoder_LSTM/PartitionedCall:1,
s2s_model/attention_layer/MatMul_1, s2s_model/concat_layer/concat/axis)' with input shapes: [32,12,128], [32,32,128], [] and with computed input tensors: input[2] = <2>.
</code></pre>
<p>因此,前32个是<code>batch_size</code>,128个是来自<code>decoder_outputs</code>和<code>attention_out</code>的输出形状,12是解码器输入的令牌数。我不知道如何解决这个错误,我想我不能更改输入令牌的数量,有什么建议吗</p>