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

Update README regarding Metal delegate instructions.

Browse Source 
PiperOrigin-RevId: 320880762
Change-Id: I6b36930f9b946b1f798c335326af182be49fedb2
This commit is contained in:
Taehee Jeong 2020-07-12 19:16:08 -07:00 committed by TensorFlower Gardener
parent d91193d641
commit 7b14d48d8a
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
tensorflow/lite/delegates/gpu/README.md
View File

@ -51,6 +51,10 @@ TFLite on GPU supports the following ops in 16-bit and 32-bit float precision:
## Basic Usage ## Basic Usage
**Note:** Following section describes the example usage for Android GPU delegate
with C++. For other languages and platforms, please see
[the documentation](https://www.tensorflow.org/lite/performance/gpu).
Using TFLite on GPU is as simple as getting the GPU delegate via Using TFLite on GPU is as simple as getting the GPU delegate via
`TfLiteGpuDelegateV2Create()` and then passing it to `TfLiteGpuDelegateV2Create()` and then passing it to
`Interpreter::ModifyGraphWithDelegate()` instead of calling `Interpreter::ModifyGraphWithDelegate()` instead of calling
@ -99,13 +103,13 @@ Metal shaders are used for iOS, which were introduced with iOS 8. Thus,
compilation flags should look like: compilation flags should look like:
```sh ```sh
bazel build --config ios_arm64 //path/to/your:project bazel build --config ios_fat //path/to/your:project
``` ```
## Advanced Usage: Delegate Options ## Advanced Usage: Delegate Options
There are GPU options that can be set and passed on to There are GPU options that can be set and passed on to
`TfLiteGpuDelegateCreate()`. When option is set to `nullptr` as shown in the `TfLiteGpuDelegateV2Create()`. When option is set to `nullptr` as shown in the
Basic Usage, it translates to: Basic Usage, it translates to:
```c++ ```c++
@ -113,12 +117,13 @@ const TfLiteGpuDelegateOptionsV2 kDefaultOptions =
TfLiteGpuDelegateOptionsV2Default(); TfLiteGpuDelegateOptionsV2Default();
``` ```
Similar for `NewTfLiteMetalDelegate()`: Similar for `TFLGpuDelegateCreate()`:
```c++ ```c++
const TfLiteMetalDelegateOptions kDefaultOptions = { const TFLGpuDelegateOptions kDefaultOptions = {
.precision_loss_allowed = 0, // false .allow_precision_loss = false,
.wait_type = TFLITE_METAL_WAIT_TYPE_SLEEP, .wait_type = TFLGpuDelegateWaitTypePassive,
.enable_quantization = false,
}; };
``` ```
@ -126,9 +131,10 @@ While it is convenient to just supply `nullptr`, it is recommended to explicitly
set the options to avoid any unexpected artifacts in case default values are set the options to avoid any unexpected artifacts in case default values are
changed. changed.
*IMPORTANT:* Note that the default option does not allow precision loss, and *IMPORTANT:* Note that the default option may not be the fastest. For faster
thus may not be the fastest. For faster execution, you may want to set execution, you may want to set `allow_precision_loss` to `true` so that the GPU
`precision_loss_allowed` to `1` for FP16 execution. performs FP16 calculation internally, and set `wait_type` to
`TFLGpuDelegateWaitTypeAggressive` to avoid GPU sleep mode.
## Tips and Tricks ## Tips and Tricks