Python ValueError:Layer sequential_2需要1个输入,但收到9个输入张量
我是Tensorflow和Tensorflow输入数据管道的新用户。我使用以下python代码从csv文件读取数据并训练神经网络:Python ValueError:Layer sequential_2需要1个输入,但收到9个输入张量,python,tensorflow,keras,tensorflow2.0,tensorflow-datasets,Python,Tensorflow,Keras,Tensorflow2.0,Tensorflow Datasets,我是Tensorflow和Tensorflow输入数据管道的新用户。我使用以下python代码从csv文件读取数据并训练神经网络: train_data = tf.data.experimental.make_csv_dataset(file_path,batch_size=64, label_name=LABEL_COLUMN, num_epochs=1, num_rows_for_inference=32,ignore_errors=True) model = tf.keras.Sequen
train_data = tf.data.experimental.make_csv_dataset(file_path,batch_size=64, label_name=LABEL_COLUMN, num_epochs=1, num_rows_for_inference=32,ignore_errors=True)
model = tf.keras.Sequential([Dense(128, activation='relu'),Dense(128, activation='relu'),Dense(1, activation='sigmoid'),])
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
model.fit(train_data, epochs=20)
但是,我没有看到培训过程,而是得到了以下输出:
ValueError: Layer sequential_2 expects 1 inputs, but it received 9 input tensors. Inputs received: [<tf.Tensor 'ExpandDims:0' shape=(None, 1) dtype=float32>, <tf.Tensor 'ExpandDims_1:0' shape=(None, 1) dtype=string>,
<tf.Tensor 'ExpandDims_2:0' shape=(None, 1) dtype=string>, <tf.Tensor 'ExpandDims_3:0' shape=(None, 1) dtype=string>, <tf.Tensor 'ExpandDims_4:0' shape=(None, 1) dtype=string>, <tf.Tensor 'ExpandDims_5:0' shape=(None, 1) dtype=float32>,
<tf.Tensor 'ExpandDims_6:0' shape=(None, 1) dtype=int32>, <tf.Tensor 'ExpandDims_7:0' shape=(None, 1) dtype=int32>, <tf.Tensor 'ExpandDims_8:0' shape=(None, 1) dtype=string>]
ValueError:Layer sequential_2需要1个输入,但收到9个输入张量。收到的投入:[,
, ,
, ]
我不知道是什么问题。任何指导都将不胜感激 你有你的数据样本吗?