experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

After quantization-aware training launch: documentation updates.

Browse Source 
PiperOrigin-RevId: 305804204
Change-Id: I4860198347ed3135128ec9b17d9153e70a4e81ee
This commit is contained in:
Alan Chiao 2020-04-09 18:41:33 -07:00 committed by TensorFlower Gardener
parent 993a6e4f0e
commit 734594bee9
1 changed files with 7 additions and 9 deletions

8
tensorflow/lite/g3doc/performance/model_optimization.md
View File

@ -87,11 +87,11 @@ a smaller model size and faster computation.
The following types of quantization are available in TensorFlow Lite:
Technique | Data requirements | Size reduction | Accuracy | Supported hardware
-------------------------------------------------------------------------------------------------------------- | -------------------------------- | -------------- | --------------------------- | ------------------
------------------------------------------------------------------------------------------------------- | -------------------------------- | -------------- | --------------------------- | ------------------
[Post-training float16 quantization](post_training_float16_quant.ipynb) | No data | Up to 50% | Insignificant accuracy loss | CPU, GPU
[Post-training dynamic range quantization](post_training_quant.ipynb) | No data | Up to 75% | Accuracy loss | CPU
[Post-training integer quantization](post_training_integer_quant.ipynb) | Unlabelled representative sample | Up to 75% | Smaller accuracy loss | CPU, EdgeTPU, Hexagon DSP
[Quantization-aware training](https://github.com/tensorflow/tensorflow/tree/r1.13/tensorflow/contrib/quantize) | Labelled training data | Up to 75% | Smallest accuracy loss | CPU, EdgeTPU, Hexagon DSP
[Quantization-aware training](http://www.tensorflow.org/model_optimization/guide/quantization/training) | Labelled training data | Up to 75% | Smallest accuracy loss | CPU, EdgeTPU, Hexagon DSP
Below are the latency and accuracy results for post-training quantization and
quantization-aware training on a few models. All latency numbers are measured on
@ -144,11 +144,9 @@ broadly applicable and does not require training data.
For cases where the accuracy and latency targets are not met, or hardware
accelerator support is important,
[quantization-aware training](https://github.com/tensorflow/tensorflow/tree/r1.13/tensorflow/contrib/quantize){:.external}
[quantization-aware training](https://www.tensorflow.org/model_optimization/guide/quantization/training){:.external}
is the better option. See additional optimization techniques under the
[Tensorflow Model Optimization Toolkit](https://www.tensorflow.org/model_optimization).
Note: Quantization-aware training supports a subset of convolutional neural network architectures.
If you want to further reduce your model size, you can try [pruning](#pruning)
prior to quantizing your models.