A general quantization scheme is being developed in tf.contrib.quantize. (deprecated)
tf.compat.v1.train.do_quantize_training_on_graphdef(
input_graph, num_bits
)
Consider using that instead, though since it is in the tf.contrib namespace, it is not subject to backward compatibility guarantees.
| Args | |
|---|---|
input_graph | A GraphDef. |
num_bits | The number of bits for quantize training. |
| Returns | |
|---|---|
| The graph with quantize training done. |
© 2020 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/versions/r2.3/api_docs/python/tf/compat/v1/train/do_quantize_training_on_graphdef