我在使用维度为x_tr=(43163, 50)和y_tr=(43163, 50, 1)的训练集拟合ELMO嵌入模型时遇到了错误，如下所示：
InvalidArgumentError: Incompatible shapes: [1600] vs. [32,50] [[{{node metrics/acc/Equal}} = Equal[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](metrics/acc/Reshape, metrics/acc/Cast)]].如何解决这个错误？
我尝试通过使训练样本可被批量大小整除来解决这个问题。
用于拟合模型的训练集：
X_tr=np.array(X_tr)print(X_tr.shape)y_tr = np.array(y_tr).reshape(len(y_tr), max_len, 1)print(y_tr.shape)(43163, 50)(43163, 50, 1)构建模型：
input_text = Input(shape=(max_len,), dtype=tf.string)embedding = Lambda(ElmoEmbedding, output_shape=(None, 1024))(input_text)x = Bidirectional(LSTM(units=512, return_sequences=True, recurrent_dropout=0.2, dropout=0.2))(embedding)x_rnn = Bidirectional(LSTM(units=512, return_sequences=True, recurrent_dropout=0.2, dropout=0.2))(x)x = add([x, x_rnn]) # 残差连接到第一个双向LSTMout = TimeDistributed(Dense(n_tags, activation="softmax"))(x)model = Model(input_text, out)编译模型：
model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"])拟合模型：
fit_model = model.fit(np.array(X_tr), np.array(y_tr).reshape(len(y_tr), max_len, 1), validation_split=0.1, batch_size=batch_size, epochs=5, verbose=1)错误：
InvalidArgumentError: Incompatible shapes: [1600] vs. [32,50] [[{{node metrics/acc/Equal}} = Equal[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](metrics/acc/Reshape, metrics/acc/Cast)]]预期结果可能是：在38816个样本上训练，在4320个样本上验证Epoch 1/538816/38816 [==============================] - 433s 11ms/step - loss: 0.0625 - acc: 0.9818 - val_loss: 0.0459 - val_acc: 0.9858Epoch 2/538816/38816 [==============================] - 430s 11ms/step - loss: 0.0404 - acc: 0.9869 - val_loss: 0.0421 - val_acc: 0.9865Epoch 3/538816/38816 [==============================] - 429s 11ms/step - loss: 0.0334 - acc: 0.9886 - val_loss: 0.0426 - val_acc: 0.9868Epoch 4/538816/38816 [==============================] - 429s 11ms/step - loss: 0.0275 - acc: 0.9904 - val_loss: 0.0431 - val_acc: 0.9868Epoch 5/538816/38816 [==============================] - 430s 11ms/step - loss: 0.0227 - acc: 0.9920 - val_loss: 0.0461 - val_acc: 0.9867回答：
已解决：我通过移除metrics=[‘accuracy’]解决了这个问题，但为什么这个准确率指标会导致错误我仍然不清楚。如果有人知道，请帮助我解答。
