此页面由 Cloud Translation API 翻译。
Switch to English

tf.lite.Optimize

TensorFlow 1版 GitHub上查看源代码

枚举定义了优化,以产生tflite图形时适用。

一些优化可能会在精度为代价。

默认默认的优化策略。

 Converter will do its best to improve size and latency based on the
information provided.
Enhanced optimizations are gained by providing a representative_dataset.
This is recommended, and is currently equivalent to the modes below.
Currently, weights will be quantized and if representative_dataset is
provided, activations for quantizable operations will also be quantized.
 

OPTIMIZE_FOR_SIZE已过时。做同样为默认值。

OPTIMIZE_FOR_LATENCY已过时。做同样为默认值。

类变量

  • DEFAULT
  • OPTIMIZE_FOR_LATENCY
  • OPTIMIZE_FOR_SIZE