W3cubDocs

/TensorFlow Python

hub.get_num_image_channels

hub.get_num_image_channels(
    module_or_spec,
    signature=None,
    input_name=None
)

Returns expected num_channels dimensions of an image input.

This is for advanced users only who expect to handle modules with image inputs that might not have the 3 usual RGB channels.

Args:

  • module_or_spec: a Module or ModuleSpec that accepts image inputs.
  • signature: a string with the key of the signature in question. If None, the default signature is used.
  • input_name: a string with the input name for images. If None, the conventional input name images for the default signature is used.

Returns:

An integer with the number of input channels to the module.

Raises:

  • ValueError: If the channel information is missing or malformed.

© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/hub/get_num_image_channels