TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now


View source on GitHub

Rewrites an eval input_graph in place for simulated quantization.


Variables added by the rewrite get added to the global variables collection.

This function has additional experimental options not (yet) available to create_eval_graph. The resulting behavior may be undefined.

The graph has fake quantization ops inserted to simulate the error introduced by quantization. Since the graph is transformed in place, the expected behavior of previously held references to nodes and tensors may change.


  • input_graph: The tf.Graph to be transformed, if None then defaults to the default graph.
  • weight_bits: Number of bits to use for quantizing weights.
  • activation_bits: Number of bits to use for quantizing activations.
  • symmetric: If true, use symmetric quantization limits instead of training the minimum and maximum of each quantization range separately.
  • quant_delay: Number of steps after which weights and activations are quantized during eval.
  • scope: The scope to be transformed. If it's not None, only the ops which are in this scope will be transformed.


  • ValueError: If elements contains an element that isn't a tf.Tensor or tf.Operation.