当前位置:   article > 正文

[Tensorflow] tensor张量基础(dtype,shape,variable,slice and join)_tensor dtype

tensor dtype

一、tensor属性:tf.DType和tf.TensorShape

(1)tensor类型:tf.DType

  1. #部分类型
  2. tf.float16: 16-bit half-precision floating-point.
  3. tf.float32: 32-bit single-precision floating-point.
  4. tf.float64: 64-bit double-precision floating-point.
  5. tf.int8: 8-bit signed integer.
  6. tf.uint8: 8-bit unsigned integer.
  7. tf.uint16: 16-bit unsigned integer.
  8. tf.int16: 16-bit signed integer.
  9. tf.int32: 32-bit signed integer.
  10. tf.int64: 64-bit signed integer.
  11. tf.bool: Boolean.
  12. tf.string: String.
  13. tf.resource: Handle to a mutable resource.

(2)tensor形状:shape

    三种类型:
  • Fully-known shape: 维度确定,每一维长度确定。  如:[768,100]
  • Partially-known shape: 维度确定ÿ
声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/繁依Fanyi0/article/detail/95285
推荐阅读
相关标签
  

闽ICP备14008679号