Keras模型ValueError:无法压缩dim[1]，预期维度为1，得到90

Question

我目前的模型是：

# from tensorflow.keras.layers import InputLayer
model_training = Sequential()
# input_layer = keras.Input(shape=(300,1))
model_training.add(InputLayer(input_shape=(300,1)))
model_training.add(Conv1D(filters=32, kernel_size=3, padding='same', activation='tanh'))
model_training.add(Dropout(0.2))
model_training.add(MaxPooling1D(pool_size=3))
model_training.add(Dropout(0.2))
model_training.add(Conv1D(filters=32, kernel_size=3, padding='same', activation='tanh'))
model_training.add(Dropout(0.2))
model_training.add(MaxPooling1D(pool_size=3))
# model_training.add(Dropout(0.2))
# model_training.add(Conv1D(filters=32, kernel_size=3, padding='same', activation='tanh'))
# model_training.add(Dropout(0.2))
# model_training.add(MaxPooling1D(pool_size=3))
# model_training.add(Dropout(0.2))
# model_training.add(Conv1D(filters=32, kernel_size=3, padding='same', activation='tanh'))
# model_training.add(Dropout(0.2))
# model_training.add(MaxPooling1D(pool_size=3))
# model_training.add(Dropout(0.2))
#model.add(Dropout(0.2))
model_training.add(Flatten())
model_training.add(Dense(90))
model_training.add(Activation('sigmoid'))
model_training.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model_training.summary())

我的拟合函数：

model_training.fit(train_data, train_labels, validation_data=(test_data, test_labels), batch_size=32, epochs=15)

当我运行下面的代码时，我得到了这个错误：

ValueError: Can not squeeze dim[1], expected a dimension of 1, got 90 for '{{node Squeeze}} = Squeeze[T=DT_FLOAT, squeeze_dims=[-1]](remove_squeezable_dimensions/Squeeze)' with input shapes: [?,90].

有什么想法吗？我的输出层有90个，因为总共有90个类可以给出预测。

列车和标签的形状如下：

(7769, 300, 1)
(7769, 90, 1)

我搞不懂这个问题。如有任何帮助，我们不胜感激！部分模型摘要：

​

​

Answer 1

在训练之前挤压标签：

train_labels = tf.squeeze(train_labels, axis=-1)

看起来标签的形状才是问题所在。模型将输出(batch, 90)形状，但您提供的是(batch, 90, 1)。Keras无法压缩维度% 1，因为它的长度为90而不是1。