Slide 10.6: Tensor data types

TensorFlow.js Tutorial (Cont.)

Retrieving Tensor Values (Cont.)
You can get the shape of a tensor using tensor.shape() method:


<html> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs"></script> <body> <div id="demo" /> <script type="text/javascript"> const myArr = [1, 2, 3, 4]; const shape = [2, 2]; const tensorA = tf.tensor(myArr, shape); document.getElementById("demo").innerHTML = tensorA.shape; </script> </body> </html>

You can get the datatype of a tensor using tensor.dtype() method:


<html> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs"></script> <body> <div id="demo" /> <script type="text/javascript"> const myArr = [1, 2, 3, 4]; const shape = [2, 2]; const tensorA = tf.tensor(myArr, shape); document.getElementById("demo").innerHTML = tensorA.dtype; </script> </body> </html>

Tensor Data Types
A tensor can have the following data types: (i) bool, (ii) int32, (iii) float32 (default), (iv) complex64, and (v) string. When you create a tensor, you can specify the data type as the third parameter:


<html> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs"></script> <body> <div id="demo" /> <script type="text/javascript"> const myArr = [1, 2, 3, 4]; const shape = [2, 2]; const tensorA = tf.tensor(myArr, shape, "int32"); document.getElementById("demo").innerHTML = tensorA.dtype; </script> </body> </html>