colin
/
TIM-VX
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README with framework support 

Signed-off-by: Kainan Cha <kainan.cha@verisilicon.com>
This commit is contained in:
Kainan Cha 2021-02-25 17:18:12 +08:00
parent 0dbaae19c5
commit fef9532954
1 changed files with 15 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
README.md
View File

@ -9,6 +9,13 @@ Main Features
- Built-in custom layer extensions
- A set of utility functions for debugging
## Framework Support
[Tensorflow-Lite Delegate](https://github.com/VeriSilicon/tensorflow/tree/dev/vx-delegate) (Unofficial)
[OAID Tegine](https://github.com/OAID/Tengine) (Official)
MLIR Dialect (In development)
TVM (In development)
## Roadmap
Roadmap of TIM-VX will be updated here in the future.
@ -34,6 +41,12 @@ bazel build //samples/lenet:lenet_asymu8_cc
bazel run //samples/lenet:lenet_asymu8_cc
```
### Get familiar with OpenVX spec
To development for TIM-VX, you first need to get familiar with [OpenVX API](https://www.khronos.org/openvx/) and [OpenVX NN Extension API](https://www.khronos.org/registry/vx). Please head over to [Khronos](https://www.khronos.org/) to read the spec.
To build and run Tensorflow-Lite delegate on A311D platform
```shell
# clone and cross build VeriSilicon tensorflow fork with TFlite delegate support
git clone --single-branch --branch dev/vx-delegate git@github.com:VeriSilicon/tensorflow.git vx-delegate; cd vx-delegate
bazel build --config A311D //tensorflow/lite/tools/benchmark:benchmark_model
# push benchmark_model onto device and run
./benchmark_model --graph=mobilenet_v1_1.0_224_quant.tflite --use_vxdelegate=true
```