1、tf.concattf.concat的作用主要是将向量按指定维连起来,其余维度不变;而1.0版本以后,函数的用法变成:import tensorflow as tft1 = [[1, 2, 3],...R+1维张量。...tf.squeeze(arr)).shape)输出:----------------(3, 4, 1, 6, 1)(3, 4, 6, 1)(3, 4, 6)(3, 4, 6)----------------3、张量切片...tf.sliceslice(input_, begin, size, name=None)从张量中提取一个切片。...import tensorflow as tfinput = [[[1, 1, 1], [2, 2, 2]], [[3, 3, 3], [4, 4, 4]], [[5, 5, 5], [6, 6, 6]