1

我在用维度 x_tr=(43163, 50) 和 y_tr= (43163, 50, 1) 的训练集拟合 elmo 嵌入模型时出错：

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？

我试图通过使训练样本可被批量大小整除来解决。

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)

制作模型：

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])  # residual connection to the first biLSTM
out = 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)]]

Expected result could be:
Train on 38816 samples, validate on 4320 samples
Epoch 1/5
38816/38816 [==============================] - 433s 11ms/step - loss: 0.0625 - acc: 0.9818 - val_loss: 0.0459 - val_acc: 0.9858
Epoch 2/5
38816/38816 [==============================] - 430s 11ms/step - loss: 0.0404 - acc: 0.9869 - val_loss: 0.0421 - val_acc: 0.9865
Epoch 3/5
38816/38816 [==============================] - 429s 11ms/step - loss: 0.0334 - acc: 0.9886 - val_loss: 0.0426 - val_acc: 0.9868
Epoch 4/5
38816/38816 [==============================] - 429s 11ms/step - loss: 0.0275 - acc: 0.9904 - val_loss: 0.0431 - val_acc: 0.9868
Epoch 5/5
38816/38816 [==============================] - 430s 11ms/step - loss: 0.0227 - acc: 0.9920 - val_loss: 0.0461 - val_acc: 0.9867
4

1 回答 1

1

已解决：我已经通过删除 metrics=['accuracy'] 解决了这个问题，但我仍然不知道为什么这个准确性指标游戏错误。如果有人知道，请帮助我

于 2019-02-09T16:24:09.730 回答