Date: Fri, 29 Mar 2024 14:48:02 +0000 (UTC) Message-ID: <380972454.9207.1711723682302@aws-us-west-2-dlf-confluence-1.web.codeaurora.org> Subject: Exported From Confluence MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_Part_9206_1239132481.1711723682302" ------=_Part_9206_1239132481.1711723682302 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Content-Location: file:///C:/exported.html
Introduction of Adlik release 0.1.0: A= dlik-=E5=8A=A0=E9=80=9FAI=E5=BA=94=E7=94=A8=E8=90=BD=E5=9C=B0=E7=9A=84=E7= =AB=AF=E5=88=B0=E7=AB=AF=E5=B7=A5=E5=85=B7=E9=93=BE.pptx
Below are the key features delivered in Adlik Release 0.1.0, see= chinese version here = Feature List=E4=B8=AD=E6=96=87=E7=89=88.
Training = framework |
Model for= mat |
Target ru= ntime |
compiled = format |
Keras |
h5= p> |
Tf Serving<= /span> |
SavedModel<= /span> |
|
|
OpenVINO |
IR= p> |
|
|
TensorRT |
Plan= |
|
|
TF-Lite |
tflite |
TensorFlow<= /span> |
Ckpt/pb |
Tf Serving<= /span> |
SavedModel<= /span> |
|
|
OpenVINO |
IR= p> |
|
|
TensorRT |
Plan= |
|
|
TF-Lite |
tflite |
PyTorch |
pth<= /p> |
OpenVINO |
IR= p> |
|
|
TensorRT |
Plan= |
Training fra= mework | Inference en= gine | hardware = environment |
|
TensorFlow = Serving-1.14 |
CPU/GPU |
|
TensorFlow = Serving-2.2 |
CPU/GPU |
|
OpenVINO-20= 19 |
CPU<= /p> |
|
TensorRT-6<= /span> |
GPU<= /p> |
|
TensorRT-7<= /span> |
GPU<= /p> |
|
TF Lite-2.1= |
CPU(X86/ARM= ) |
TensorFlow<= /span> |
TensorFlow = Serving-1.14 |
CPU/GPU |
|
TensorFlow = Serving-2.2 |
CPU/GPU |
|
OpenVINO-20= 19 |
CPU<= /p> |
|
TensorRT-6<= /span> |
GPU<= /p> |
|
TensorRT-7<= /span> |
GPU<= /p> |
|
TF Lite-2.1= |
CPU(X86/ARM= ) |
PyTorch |
OpenVINO-20= 19 |
CPU<= /p> |
|
TensorRT-6<= /span> |
GPU<= /p> |
Integration of multiple DL inference ru= ntime, including TensorFlow Serving, OpenVINO, Tens= orRT and TF Lite.
Integrate= d Inference engine |
Hardware = environment |
TensorFlow = Serving-1.14 |
CPU/GPU |
TensorFlow = Serving-2.2 |
CPU/GPU |
OpenVINO-20= 19 |
CPU<= /p> |
TensorRT-6<= /span> |
GPU<= /p> |
TensorRT-7<= /span> |
GPU<= /p> |
TF Lite-2.1= |
CPU(X86/ARM= ) |
Benchmark Test Framework for Deep Learning Model