Khadas Docs

Amazing Khadas, always amazes you!

User Tools

Site Tools

Home / products / sbc / vim3 / npu / ksnn / ksnn-convert
products:sbc:vim3:npu:ksnn:ksnn-convert

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision 		Previous revision
products:sbc:vim3:npu:ksnn:ksnn-convert [2022/09/17 02:46]
frank created 		products:sbc:vim3:npu:ksnn:ksnn-convert [2025/01/09 20:33] (current)
louis
Line 1: Line 1:
 ====== Instructions for KSNN conversion tool ====== ====== Instructions for KSNN conversion tool ======
  
-===== Introduction =====+Introduction and guide on how to use the KSNN conversion tool.
  
-This document will introduce how to use the KSNN conversion tool.+===== Get the conversion tool =====
  
-===== Get convert tool ===== +The conversion tool is integrated in the NPU SDK.
- +
-The tool is integrated in the NPU conversion tool warehouse of VIM3.+
  
 ```shell ```shell
-$ git clone --recursive https://github.com/khadas/aml_npu_sdk.git+$ git lfs install 
 +$ git lfs clone https://github.com/khadas/aml_npu_sdk.git
 ``` ```
 The KSNN conversion tool is under ''acuity-toolkit/python'', The KSNN conversion tool is under ''acuity-toolkit/python'',
Line 19: Line 18:
 ``` ```
  
-===== Example for Convert =====+===== Conversion example =====
  
-Choose tensorflow Inception V3 as a exmple.+Choose tensorflow MobileNet SSD as an example.
  
-1. Get forzen model,+1. Get the frozen model,
  
 ```shell ```shell
 $ cd aml_npu_sdk/acuity-toolkit/python $ cd aml_npu_sdk/acuity-toolkit/python
-$ wget https://github.com/yan-wyb/models-zoo/raw/master/tensonrflow/inception/inception_v3_2016_08_28_frozen.pb+$ wget https://github.com/yan-wyb/models-zoo/raw/master/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb
 ``` ```
  
Line 33: Line 32:
  
 ```shell ```shell
-$ ./convert --model-name inception \+# uint8 
 +$ ./convert --model-name mobilenet_ssd \
 >           --platform tensorflow \ >           --platform tensorflow \
->           --model /home/yan/yan/Yan/models-zoo/tensorflow/inception/inception_v3_2016_08_28_frozen.pb \ +>           --model /home/yan/yan/Yan/models-zoo/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb \ 
->           --input-size-list '299,299,3' \ +>           --input-size-list '300,300,3' \ 
->           --inputs input \ +>           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \ 
->           --outputs InceptionV3/Predictions/Reshape_1 \ +>           --outputs "'concat concat_1'" \ 
->           --mean-values '128 128 128 0.0078125' \+>           --mean-values '127.5 127.5 127.5 0.007843137' \
 >           --quantized-dtype asymmetric_affine \ >           --quantized-dtype asymmetric_affine \
 +>           --source-files ./data/dataset/dataset0.txt \
 +>           --kboard VIM3 --print-level 0
 +
 +# int8
 +$ ./convert --model-name mobilenet_ssd \
 +>           --platform tensorflow \
 +>           --model /home/yan/yan/Yan/models-zoo/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb \
 +>           --input-size-list '300,300,3' \
 +>           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \
 +>           --outputs "'concat concat_1'" \
 +>           --mean-values '127.5 127.5 127.5 0.007843137' \
 +>           --quantized-dtype dynamic_fixed_point \
 +>           --qtype int8 \
 +>           --source-files ./data/dataset/dataset0.txt \
 +>           --kboard VIM3 --print-level 0
 +
 +# int16
 +$ ./convert --model-name mobilenet_ssd \
 +>           --platform tensorflow \
 +>           --model /home/yan/yan/Yan/models-zoo/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb \
 +>           --input-size-list '300,300,3' \
 +>           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \
 +>           --outputs "'concat concat_1'" \
 +>           --mean-values '127.5 127.5 127.5 0.007843137' \
 +>           --quantized-dtype dynamic_fixed_point \
 +>           --qtype int16 \
 >           --source-files ./data/dataset/dataset0.txt \ >           --source-files ./data/dataset/dataset0.txt \
 >           --kboard VIM3 --print-level 0 >           --kboard VIM3 --print-level 0
Line 47: Line 73:
 During conversion, if you need to view detailed information, you can modify ''--print-level 0'' to ''--print-level 1''. During conversion, if you need to view detailed information, you can modify ''--print-level 0'' to ''--print-level 1''.
  
-3. File generated after conversion.+3. Model file generated after conversion.
  
 ```shell ```shell
 $ cd aml_npu_sdk/acuity-toolkit/python $ cd aml_npu_sdk/acuity-toolkit/python
-$ ls outputs/inception/ +$ ls outputs/mobilenet_ssd/ 
-inception.nb  libnn_inception.so+mobilenet_ssd.nb  libnn_mobilenet_ssd.so
 ``` ```
  
Last modified: 2022/09/17 02:46 by frank

Page Tools

Khadas Site

Khadas Community

Khadas GitHub

Khadas Downloads