ValueError：检查输入时出错：预期input_1具有形状（29606403，）但具有形状（43，）的数组

Question

我想从下一层开始训练深度网络：

df =  df.iloc[:,0:43]
df = np.array(df)
df = df.astype(np.float64)
df[df>=10000000000] = 0
df = m.fit_transform(df)


x_train , x_test , y_train , y_test = train_test_split(df ,lbs ,test_size=0.2)


input_df = Input(shape = (29606403, ))

# "encoded" is the encoded representation of the input
encoded = Dense(2048, activation='relu')(input_df)
encoded = Dense(1024, activation='relu')(encoded)
encoded = Dense(512, activation='relu')(encoded)
encoded = Dense(256, activation='relu')(encoded)
encoded = Dense(128, activation='relu')(encoded)
encoded = Dense(64, activation='relu')(encoded)
encoded = Dense(32, activation='relu')(encoded)




# "decoded" is the lossy reconstruction of the input
decoded = Dense(64, activation='relu')(encoded)
decoded = Dense(128, activation='relu')(decoded)
decoded = Dense(256, activation='relu')(decoded)
decoded = Dense(512, activation='relu')(decoded)
decoded = Dense(1024, activation='relu')(decoded)
decoded = Dense(2048, activation='relu')(decoded)
decoded = Dense(29606403, activation='softmax')(decoded)

autoencoder = Model(input_df, decoded)

autoencoder.compile(optimizer='adam', loss='categorical_crossentropy',metrics=['accuracy'])

n_epochs = 10
autoencoder.fit(x_train, x_train,
                epochs=n_epochs,
                batch_size=256,
                shuffle=True,
                validation_data=(x_test, x_test))

在培训期间，出现错误： ValueError：检查输入时出错：预期input_1具有形状（29606403，）但具有形状（43，）的数组