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

Both sides previous revision Previous revision
Next revision 		Previous revision
products:sbc:vim3:npu:ksnn:ksnn-convert [2024/05/27 22:15]
louis 		products:sbc:vim3:npu:ksnn:ksnn-convert [2025/09/14 23:42] (current)
nick
Line 5: Line 5:
 ===== Get the conversion tool ===== ===== Get the conversion tool =====
  
-The conversion tool is integrated in the NPU SDK.+The conversion tool is integrated in the NPU SDK. You can download it from [[dl>products/vim3/tools/npu-sdk/| aml_npu_sdk]]
  
 ```shell ```shell
-$ git lfs install +$ wget https://dl.khadas.com/products/vim3/tools/npu-sdk/aml_npu_sdk-ddk-6.4.8.7-250427.tgz 
-$ git lfs clone --recursive https://github.com/khadas/aml_npu_sdk.git+$ tar xvzf aml_npu_sdk-ddk-6.4.8.7-250427.tgz 
 +$ ln -fs aml_npu_sdk-ddk-6.4.8.7-250427 aml_npu_sdk
 ``` ```
 +
 The KSNN conversion tool is under ''acuity-toolkit/python'', The KSNN conversion tool is under ''acuity-toolkit/python'',
  
Line 26: Line 28:
 ```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/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb+$ wget https://github.com/numbqq/models-zoo/raw/master/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb
 ``` ```
  
Line 34: Line 36:
 # uint8 # uint8
 $ ./convert --model-name mobilenet_ssd \ $ ./convert --model-name mobilenet_ssd \
->           --platform tensorflow \ +           --platform tensorflow \ 
->           --model /home/yan/yan/Yan/models-zoo/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb \ +           --model ./ssd_mobilenet_v1_coco_2017_11_17.pb \ 
->           --input-size-list '300,300,3' \ +           --input-size-list '300,300,3' \ 
->           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \ +           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \ 
->           --outputs "'concat concat_1'" \ +           --outputs "'concat concat_1'" \ 
->           --mean-values '127.5 127.5 127.5 0.007843137' \ +           --mean-values '127.5 127.5 127.5 0.007843137' \ 
->           --quantized-dtype asymmetric_affine \ +           --quantized-dtype asymmetric_affine \ 
->           --source-files ./data/dataset/dataset0.txt \ +           --source-files ./data/dataset/dataset0.txt \ 
->           --kboard VIM3 --print-level 0+           --kboard VIM3 --print-level 0
  
 # int8 # int8
 $ ./convert --model-name mobilenet_ssd \ $ ./convert --model-name mobilenet_ssd \
->           --platform tensorflow \ +           --platform tensorflow \ 
->           --model /home/yan/yan/Yan/models-zoo/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb \ +           --model ./ssd_mobilenet_v1_coco_2017_11_17.pb \ 
->           --input-size-list '300,300,3' \ +           --input-size-list '300,300,3' \ 
->           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \ +           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \ 
->           --outputs "'concat concat_1'" \ +           --outputs "'concat concat_1'" \ 
->           --mean-values '127.5 127.5 127.5 0.007843137' \ +           --mean-values '127.5 127.5 127.5 0.007843137' \ 
->           --quantized-dtype dynamic_fixed_point \ +           --quantized-dtype dynamic_fixed_point \ 
->           --qtype int8 \ +           --qtype int8 \ 
->           --source-files ./data/dataset/dataset0.txt \ +           --source-files ./data/dataset/dataset0.txt \ 
->           --kboard VIM3 --print-level 0+           --kboard VIM3 --print-level 0
  
 # int16 # int16
 $ ./convert --model-name mobilenet_ssd \ $ ./convert --model-name mobilenet_ssd \
->           --platform tensorflow \ +           --platform tensorflow \ 
->           --model /home/yan/yan/Yan/models-zoo/tensorflow/mobilenet_ssd/ssd_mobilenet_v1_coco_2017_11_17.pb \ +           --model ./ssd_mobilenet_v1_coco_2017_11_17.pb \ 
->           --input-size-list '300,300,3' \ +           --input-size-list '300,300,3' \ 
->           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \ +           --inputs FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/BatchNorm/batchnorm/mul_1 \ 
->           --outputs "'concat concat_1'" \ +           --outputs "'concat concat_1'" \ 
->           --mean-values '127.5 127.5 127.5 0.007843137' \ +           --mean-values '127.5 127.5 127.5 0.007843137' \ 
->           --quantized-dtype dynamic_fixed_point \ +           --quantized-dtype dynamic_fixed_point \ 
->           --qtype int16 \ +           --qtype int16 \ 
->           --source-files ./data/dataset/dataset0.txt \ +           --source-files ./data/dataset/dataset0.txt \ 
->           --kboard VIM3 --print-level 0+           --kboard VIM3 --print-level 0
 ``` ```
  
Last modified: 2024/05/27 22:15 by louis

Page Tools

Khadas Site

Khadas Community

Khadas GitHub

Khadas Downloads