Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions README.md → Signed-off-by: oksanaphmn
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# VSI NPU Android Support Library

## 1 How to build
## 1. How to build

with prebuild sdk is not recommend, just for build test.

Expand All @@ -26,7 +26,7 @@ Addition cmake definition added for this purpose -DEXT_TIM_VX=<git remote locati

Addition cmake definition added for this purpose -DTIM_VX_TAG=commit-sha-id, just provide the commit id in TIM-VX github repo.

## 2 Integrate with Android
## 2. Integrate with Android

verified with i.MX 8M Plus and Android 14

Expand Down Expand Up @@ -101,7 +101,7 @@ namespace.default.search.paths += /apex/com.android.os.statsd/${LIB}

### 2.5 Start service by run android.hardware.neuralnetworks-shell-service-sample on Android board

### 2.6. run test with VTS
### 2.6 run test with VTS

```sh
./VtsHalNeuralnetworksTargetTest --gtest_filter=TestGenerated/GeneratedTest.Test/android_hardware_neuralnetworks_IDevice_nnapi_sample_sl_updatable_reshape
Expand All @@ -113,7 +113,7 @@ namespace.default.search.paths += /apex/com.android.os.statsd/${LIB}
./CtsNNAPITestCases64 --gtest_filter=TestGenerated/QuantizationCouplingTest*
```

## 3 Integrate with TfLite
## 3. Integrate with TfLite

### 3.1 Get the source code of TensorFlow

Expand Down