Khadas Docs

Amazing Khadas, always amazes you!

User Tools

Site Tools

Home / products / sbc / vim4 / npu / demos / vgg16
products:sbc:vim4:npu:demos:vgg16

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:vim4:npu:demos:vgg16 [2024/01/04 05:01]
louis 		products:sbc:vim4:npu:demos:vgg16 [2025/06/11 21:50] (current)
louis
Line 1: Line 1:
 ~~tag>NPU VGG16 VIM4 Tensorflow Keras ~~ ~~tag>NPU VGG16 VIM4 Tensorflow Keras ~~
 +
 +**Doc for version ddk-3.4.7.7**
  
 ====== VGG16 TensorFlow Keras VIM4 Demo 4 ====== ====== VGG16 TensorFlow Keras VIM4 Demo 4 ======
  
 {{indexmenu_n>4}} {{indexmenu_n>4}}
 +
 +===== Introduction =====
 +
 +VGG16 is a classification model. It can assign a single label to an entire image.
 +
 +Image and inference results on VIM4.
 +
 +{{:products:sbc:vim4:npu:demos:airplane.webp?400|}}
 +
 +{{:products:sbc:vim4:npu:demos:vgg16-demo-output.webp?400|}}
  
 [[https://www.google.com/search?q=VGG16|VGG16]] is a convolution neural net architecture that’s used for image recognition. It utilizes 16 layers with weights and is considered one of the best vision model architectures to date. [[https://www.google.com/search?q=VGG16|VGG16]] is a convolution neural net architecture that’s used for image recognition. It utilizes 16 layers with weights and is considered one of the best vision model architectures to date.
Line 22: Line 34:
 Follow Docker official documentation to install Docker: [[https://docs.docker.com/engine/install/ubuntu/|Install Docker Engine on Ubuntu]]. Follow Docker official documentation to install Docker: [[https://docs.docker.com/engine/install/ubuntu/|Install Docker Engine on Ubuntu]].
  
-Then fetch the prebuilt NPU Docker container and run it.+Follow the script below to get Docker image:
  
 ```shell ```shell
-$ docker pull yanwyb/npu:v1 +docker pull numbqq/npu-vim4
-$ docker run -it --name vim4-npu1 -v $(pwd):/home/khadas/npu \ +
- -v /etc/localtime:/etc/localtime:ro \ +
- -v /etc/timezone:/etc/timezone:ro \ +
- yanwyb/npu:v1+
 ``` ```
  
 ==== Get convert tool ==== ==== Get convert tool ====
  
-Download Tool from [[gl>khadas/vim4_npu_sdk]].+Download Tool from [[gh>khadas/vim4_npu_sdk]].
  
 ```shell ```shell
-$ git clone https://gitlab.com/khadas/vim4_npu_sdk+$ git lfs install 
 +$ git lfs clone https://github.com/khadas/vim4_npu_sdk 
 +$ cd vim4_npu_sdk 
 +$ ls 
 +adla-toolkit-binary  adla-toolkit-binary-1.2.0.9  convert-in-docker.sh  Dockerfile  docs  README.md
 ``` ```
 +
 +  * ''adla-toolkit-binary/docs'' - SDK documentations
 +  * ''adla-toolkit-binary/bin'' - SDK tools required for model conversion
 +  * ''adla-toolkit-binary/demo'' - Conversion examples
 +
 +<WRAP important>
 +If your kernel is older than 241129, please use branch npu-ddk-1.7.5.5.
 +</WRAP>
  
 ==== Convert ==== ==== Convert ====
Line 69: Line 89:
         --outputs dense_2/Softmax \         --outputs dense_2/Softmax \
         --inference-input-type float32 \         --inference-input-type float32 \
- --inference-output-type float32 \+ --inference-output-type float32 \
         --quantize-dtype int8 --outdir tensorflow_output \         --quantize-dtype int8 --outdir tensorflow_output \
         --channel-mean-value "0,0,0,255" \         --channel-mean-value "0,0,0,255" \
 +        --inference-input-type "float32" \
 +        --inference-output-type "float32" \
         --source-file vgg16_dataset.txt \         --source-file vgg16_dataset.txt \
         --iterations 500 \         --iterations 500 \
Line 77: Line 99:
         --target-platform PRODUCT_PID0XA003         --target-platform PRODUCT_PID0XA003
 ``` ```
- 
-<WRAP important > 
-Please prepare about 500 pictures for quantification. If the pictures size is smaller than model input size, please resize pictures to input size before quantification. 
-</WRAP> 
  
 Run ''convert_adla.sh'' to generate the VIM4 model. The converted model is ''xxx.adla'' in ''tensorflow_output''. Run ''convert_adla.sh'' to generate the VIM4 model. The converted model is ''xxx.adla'' in ''tensorflow_output''.
Line 98: Line 116:
 ``` ```
  
-<WRAP important > +<WRAP important> 
-If your kernel version is 5.4 or earlier, please use tag ''ddk-1.7.5.5''. Tag ''ddk-2.3.6.7'' is for 5.15.+If your kernel is older than 241129, please use version before tag ddk-3.4.7.7.
 </WRAP> </WRAP>
  
Line 124: Line 142:
  
 # Run # Run
-$ sudo ./vgg16 -m ../data/vgg16_int8.adla -p ../data/airplane.jpeg+$ ./vgg16 -m ../data/vgg16_int8.adla -p ../data/airplane.jpeg
 ``` ```
  
Last modified: 2024/01/04 05:01 by louis

Page Tools

Khadas Site

Khadas Community

Khadas GitHub

Khadas Downloads