Posted On: Feb 22, 2018
Placeholders in TensorFlow is simply a variable that is assigned to the data. It allows to create the operations and build the computational graph without needing the data. Placeholder in Tensorflow is used to feed the actual training data. They can be of integer, float, etc.
labels_placeholder = tf.placeholder(tf.int32, shape=(batch_size))
Never Miss an Articles from us.
Tensors can be thought of as vectors and matrices of higher dimensions. They represent n-dimensional arrays of base data-type. Each element of a tensor is of the same data-type which is always known. ...