CODEWITHSUNDEEP
pythontensorflow
BugKiller
BugKiller

Reputation: 1488

what's the difference between tf.constant and tf.convert_to_tensor

tf.to_float(tf.convert_to_tensor(python_object)) used many times in Tensorflow object detection api like grid_anchor_generator. normaly I'll use tf.constant(python_object, dtype=tf.float32). I'm wondering the difference between them. Thanks

Upvotes: 18

Views: 8657

Answers (1)

suharshs
suharshs

Reputation: 1088

For tf.constant, the input value must be a static non-tensor type. For example a numpy array.

For tf.convert_to_tensor, the value "an object whose type has a registered Tensor conversion function." This means input types like Tensors or tf.Variables can also be provided as inputs. For example, see the tensor conversion function for Variables here: https://github.com/tensorflow/tensorflow/blob/r1.8/tensorflow/python/ops/variables.py#L762

Upvotes: 14

Related Questions