ValueError：尺寸必須相等，但對于具有輸入形狀[?,2]、[?,64]的'{{nodebinary

我正在嘗試使用 bi-lstm 模型對文本進行二進制分類，但出現此錯誤： ValueError: Dimensions must be equal, but are 2 and 64 for '{{node binary_crossentropy/mul}} = Mul[T=DT_FLOAT](binary_crossentropy/ Cast, binary_crossentropy/Log)' 輸入形狀：[?,2], [?,64]。我是初學者，請提供一些有價值的解決方案。

text=df['text']
label=df['label']

X = pad_sequences(X, maxlen=max_len,padding=pad_type,truncating=trunc_type)
Y = pd.get_dummies(label).values    
X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size = 0.20)
print(X_train.shape,Y_train.shape)
print(X_test.shape,Y_test.shape)

#model creation
model=tf.keras.Sequential([
 # add an embedding layer
 tf.keras.layers.Embedding(word_count, 16, input_length=max_len),
 tf.keras.layers.Dropout(0.2),
 # add another bi-lstm layer
 tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(2,return_sequences=True)),
 # add a dense layer
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.softmax),
 # add the prediction layer
 tf.keras.layers.Dense(1, activation=tf.keras.activations.sigmoid),
])
model.compile(loss=tf.keras.losses.BinaryCrossentropy(), optimizer=tf.keras.optimizers.Adam(), metrics=['accuracy'])
model.summary()
history = model.fit(X_train,  Y_train, validation_data=(X_test,  Y_test), epochs = 10, batch_size=batch_size, callbacks = [callback_func], verbose=1)

uj5u.com熱心網友回復：

二分類的預測層的輸出維度應該是2：

# add the prediction layer
tf.keras.layers.Dense(2, activation=tf.keras.activations.sigmoid)

展平：

#model creation
model=tf.keras.Sequential([
 # add an embedding layer
 tf.keras.layers.Embedding(word_count, 16, input_length=max_len),
 tf.keras.layers.Dropout(0.2),
 # add another bi-lstm layer
 tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(2,return_sequences=True)),
 # add flatten
 tf.keras.layers.Flatten(),  #<========================
 # add a dense layer
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.relu),
 tf.keras.layers.Dense(32, activation=tf.keras.activations.softmax),
 # add the prediction layer
 tf.keras.layers.Dense(2, activation=tf.keras.activations.sigmoid),
])

轉載請註明出處，本文鏈接：https://www.uj5u.com/shujuku/452266.html

標籤：张量流喀拉斯 nlp 张量流2.0

上一篇：ValueError：形狀(None,)和(None,1)不兼容

下一篇：1維輸入的無效縮減維數1

ValueError：尺寸必須相等，但對于具有輸入形狀[?,2]、[?,64]的'{{nodebinary_crossentropy/mul}}，尺寸必須是2和64