0

hub.version == 0.1.1 ''' import tensorflow_hub as hub

module_spec = hub.load_module_spec("/home/neo/learn_tf/inception_v3")
height, width = hub.get_expected_image_size(module_spec)
images = ...  # A batch of images with shape [batch_size, height, 
width, 3].
module = hub.Module(module_spec)
features = module(images)   # A batch with shape [batch_size, 
num_features].

'''

I just copy it c'https://tfhub.dev/google/imagenet/inception_v3/feature_vector/1', when I run it but got

Can't convert 'images': Expected float32, got Ellipsis of type 'ellipsis' instead.

HELP ME

Sugan Zhang
  • 233
  • 1
  • 2
  • 12

1 Answers1

0

You are asked to supply some actual code where the example snippets displays the Ellipsis.

By coincidence, three dots are valid Python3 syntax for use in slice notation, and they are parsed into an object of its own helper type Ellipsis (see this question for more). This explains the error message you see.

arnoegw
  • 1,218
  • 6
  • 13