我將使用tensorflow.data.experimental.CsvDatasetTensorFlow 2 來(lái)訓(xùn)練小批量。但是 Tensor 的形狀不適合我模型的輸入形狀。請(qǐng)讓我知道通過(guò) TensorFlow 數(shù)據(jù)集進(jìn)行小批量訓(xùn)練的最佳方法是什么。我嘗試如下：# I have a dataset with 4 features and 1 labelfeature = tf.data.experimental.CsvDataset(['C:/data/iris_0.csv'], record_defaults=[.0] * 4, header=True, select_cols=[0,1,2,3])label = tf.data.experimental.CsvDataset(['C:/data/iris_0.csv'], record_defaults=[.0] * 1, header=True, select_cols=[4])dataset = tf.data.Dataset.zip((feature, label))# and I try to minibatch training:model = tf.keras.Sequential([tf.keras.layers.Dense(1, input_shape=(4,))])model.compile(loss='mse', optimizer='sgd')model.fit(dataset.repeat(1).batch(3), epochs=1)我收到一個(gè)錯(cuò)誤：ValueError：檢查輸入時(shí)出錯(cuò)：期望dense_6_input具有形狀（4，）但得到形狀為（1，）的數(shù)組因?yàn)椋篊svDataset()返回形狀的張量(features, batch)，但我需要它是形狀的(batch, features)。參考代碼：for feature, label in dataset.repeat(1).batch(3).take(1):    print(feature)# (<tf.Tensor: id=487, shape=(3,), dtype=float32, numpy=array([5.1, 4.9, 4.7], dtype=float32)>, <tf.Tensor: id=488, shape=(3,), dtype=float32, numpy=array([3.5, 3. , 3.2], dtype=float32)>, <tf.Tensor: id=489, shape=(3,), dtype=float32, numpy=array([1.4, 1.4, 1.3], dtype=float32)>, <tf.Tensor: id=490, shape=(3,), dtype=float32, numpy=array([0.2, 0.2, 0.2], dtype=float32)>)