I.MX8M plus AI Robot platform Ubuntu OS

キャンセル
次の結果を表示 
表示  限定  | 次の代わりに検索 
もしかして: 

I.MX8M plus AI Robot platform Ubuntu OS

ソリューションへジャンプ
98,813件の閲覧回数
刘国华
Contributor III

@xiaodong_zhang 

  There are some questions from our customer need your commet :

  1. Does I.MX8M plus support all operator included by tensor flow lite ?   I saw some words in the i.MX_Machine_Learning_User's_Guide.pdf . The TensorFlow Lite library uses the Android NN API implementation from the GPU/NPU driver for running inference using the GPU/NPU hardware accelerator. The implemented NN API version is 1.2, which has limitations in supported tensor data types and operations, compared to the feature set of TensorFlow Lite. Therefore,
    some models may work without acceleration enabled, but may fail when using the NN API. So the answer is NOT ?                                 
  2. Right now the I.MX8M plus support Ubuntu rootfs , does it include ROS and some ML sample ? Our customer is using Jetson Nano , it is base on Ubuntu rootfs , support ROS default . Right now they are evaluating replacing the Jetson nano with I.MX8M plus , they would like to use ubuntu . 
  3. I noted the I.MX8M plus is 2.3 TOPS base on int8 , compare to the Jetson Nano 472 GFLOPS, how to understand the advantage between them ?
  4. Could you help to share some information about the camera using in the AI Robot EVK ?
タグ(1)
1 解決策
98,789件の閲覧回数
xiaodong_zhang
NXP Employee
NXP Employee

According to the below picture

xiaodong_zhang_0-1622019188909.jpeg

472GFLOPS(FP16) = 472*2GOPS(INT8)=472*2%1024TOPS ≈ 0.92TOPS

元の投稿で解決策を見る

0 件の賞賛
返信
21 返答(返信)
98,790件の閲覧回数
xiaodong_zhang
NXP Employee
NXP Employee

According to the below picture

xiaodong_zhang_0-1622019188909.jpeg

472GFLOPS(FP16) = 472*2GOPS(INT8)=472*2%1024TOPS ≈ 0.92TOPS

0 件の賞賛
返信