Edit Hexagon documentation to reflect new supported models
PiperOrigin-RevId: 312144610
Change-Id: I9c8b0d9ad6ea4b745b4bb985ca143cca660a5b14
diff --git a/tensorflow/lite/g3doc/performance/hexagon_delegate.md b/tensorflow/lite/g3doc/performance/hexagon_delegate.md
index 60fe946..0e947d1 100644
--- a/tensorflow/lite/g3doc/performance/hexagon_delegate.md
+++ b/tensorflow/lite/g3doc/performance/hexagon_delegate.md
@@ -22,15 +22,15 @@
**Supported models:**
-The Hexagon delegate currently supports quantized models generated using
-[quantization-aware training](https://github.com/tensorflow/tensorflow/tree/r1.13/tensorflow/contrib/quantize),
-e.g.,
-[these quantized models](https://www.tensorflow.org/lite/guide/hosted_models#quantized_models)
-hosted on the TensorFlow Lite repo. It does not (yet) support models with
-[8-bit symmetric quantization spec](https://www.tensorflow.org/lite/performance/quantization_spec).
-Sample models include
-[MobileNet V1](https://storage.googleapis.com/download.tensorflow.org/models/mobilenet_v1_2018_08_02/mobilenet_v1_1.0_224_quant.tgz),
-[SSD Mobilenet](https://storage.googleapis.com/download.tensorflow.org/models/tflite/coco_ssd_mobilenet_v1_1.0_quant_2018_06_29.zip).
+The Hexagon delegate supports all models that conform to our
+[8-bit symmetric quantization spec](https://www.tensorflow.org/lite/performance/quantization_spec),
+including those generated using
+[post-training integer quantization](https://www.tensorflow.org/lite/performance/post_training_integer_quant).
+UInt8 models trained with the legacy
+[quantization-aware training](https://github.com/tensorflow/tensorflow/tree/r1.13/tensorflow/contrib/quantize)
+path are also supported, for e.g.,
+[these quantized versions](https://www.tensorflow.org/lite/guide/hosted_models#quantized_models)
+on our Hosted Models page.
## Hexagon Delegate Java API
@@ -254,10 +254,6 @@
## FAQ
-* Will the delegate support models created using
- [post-training quantization](https://www.tensorflow.org/lite/performance/post_training_quantization)?
- * This is tentatively planned for a future release, though there is no
- concrete timeline.
* Which ops are supported by the delegate?
* See the current list of [supported ops and constraints](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/experimental/delegates/hexagon/README.md)
* How can I tell that the model is using the DSP when I enable the delegate?
