Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings


TensorFlow 1 version View source on GitHub

Instantiates a placeholder tensor and returns it.

    shape=None, ndim=None, dtype=None, sparse=False, name=None, ragged=False


  • shape: Shape of the placeholder (integer tuple, may include None entries).
  • ndim: Number of axes of the tensor. At least one of {shape, ndim} must be specified. If both are specified, shape is used.
  • dtype: Placeholder type.
  • sparse: Boolean, whether the placeholder should have a sparse type.
  • name: Optional name string for the placeholder.
  • ragged: Boolean, whether the placeholder should have a ragged type. In this case, values of 'None' in the 'shape' argument represent ragged dimensions. For more information about RaggedTensors, see this guide.


  • ValueError: If called with eager execution
  • ValueError: If called with sparse = True and ragged = True.


Tensor instance (with Keras metadata included).


input_ph = tf.keras.backend.placeholder(shape=(2, 4, 5)) 
<tf.Tensor 'Placeholder_...' shape=(2, 4, 5) dtype=float32>