Join us at TensorFlow World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tf.contrib.gan.eval.run_image_classifier

View source on GitHub

Runs a network from a frozen graph.

Aliases:

  • tf.contrib.gan.eval.classifier_metrics.run_image_classifier
tf.contrib.gan.eval.run_image_classifier(
    tensor,
    graph_def,
    input_tensor,
    output_tensor,
    scope='RunClassifier'
)

Args:

  • tensor: An Input tensor.
  • graph_def: A GraphDef proto.
  • input_tensor: Name of input tensor in graph def.
  • output_tensor: A tensor name or list of tensor names in graph def.
  • scope: Name scope for classifier.

Returns:

Classifier output if output_tensor is a string, or a list of outputs if output_tensor is a list.

Raises:

  • ValueError: If input_tensor or output_tensor aren't in the graph_def.