(train_images, train_labels), (val_images, val_labels) = tf.keras.datasets.mnist.load_data() train_loader = tf.data.Dataset.from_tensor_slices((train_images, train_labels)).batch(32) val_loader = tf.data.Dataset.from_tensor_slices((val_images, val_labels)).batch(32)
首先加载Mnist数据集，得到train_images的维度为(60000,32,32)，然后适用from_tensor_slices()将数据集和标签进行打包形成一个迭代器，迭代器每个批次有32个数据
![人工智能创新挑战赛：海洋气象预测Baseline[4]完整版（TensorFlow、torch版本）含数据转化、模型构建、MLP、TCNN+RNN、LSTM模型训练以及预测](https://ucc.alicdn.com/fnj5anauszhew_20230607_83592c071f9241edb19dec6aabfa5f4e.png?x-oss-process=image/resize,h_160,m_lfit)