Tensorflow 2.0 Samples

Concepts

  • Tensor

A Tensor is a multi-dimensional array. Similar to NumPy ndarray objects, tf.Tensor objects have a data type and shape. Additionally, tf.Tensor s can reside in acelerator memory (like GPU). TensorFlow offers a rich library of operations (tf.add, tf.matmul, tf.linalg.inv etc) that consume and produce tf.Tensor s. These operations autonatically convert native Python types.

References

https://www.tensorflow.org/tutorials/customization/basics