Khadas Docs

Amazing Khadas, always amazes you!

User Tools

Site Tools

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

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:densenet [2024/10/28 21:11]
louis 		products:sbc:vim4:npu:demos:densenet [2026/04/02 02:46] (current)
nick
Line 1: Line 1:
 ~~tag> NPU Densenet VIM4 ONNX~~ ~~tag> NPU Densenet VIM4 ONNX~~
-====== DenseNet CTC ONNX Keras VIM4 Demo - 3======+ 
 +**Doc for version ddk-3.4.7.7** 
 + 
 +====== DenseNet CTC ONNX Keras VIM4 Demo - 3 ======
  
 {{indexmenu_n>3}} {{indexmenu_n>3}}
 +
 +===== Introduction =====
 +
 +Densenet_CTC is a text recognition model. It only can recognize single line text. Therefore usually, it needs to be used in conjunction with a text detection model.
 +
 +Recognition image and inference results on VIM4.
 +
 +{{:products:sbc:vim4:npu:demos:khadasteam.webp?400|}}  {{:products:sbc:vim4:npu:demos:densenet-demo-output.webp?400|}}
 +
 ===== Get the source code ===== ===== Get the source code =====
  
Line 23: Line 35:
 ``` ```
  
-===== Get Convert Tool =====+==== Get the conversion tool ==== 
 + 
 +You can find the SDK here: [[dl>products/vim4/tools/npu-sdk/]]
  
 ```shell ```shell
-$ git lfs install +$ wget https://dl.khadas.com/products/vim4/tools/npu-sdk/vim4_npu_sdk-ddk-3.4.7.7-250508.tgz 
-$ git lfs clone https://gitlab.com/khadas/vim4_npu_sdk.git +$ tar xvzf vim4_npu_sdk-ddk-3.4.7.7-250508.tgz 
-$ cd vim4_npu_sdk+$ cd vim4_npu_sdk-ddk-3.4.7.7-250508
 $ ls $ ls
-adla-toolkit-binary  adla-toolkit-binary-1.2.0.9  convert-in-docker.sh  Dockerfile  docs  README.md+adla-toolkit-binary  adla-toolkit-binary-3.1.7.4  convert-in-docker.sh  Dockerfile  docs  README.md
 ``` ```
  
-  * ''adla-toolkit-binary/docs'' - SDK documentations+  * ''docs'' - SDK documentations
   * ''adla-toolkit-binary/bin'' - SDK tools required for model conversion   * ''adla-toolkit-binary/bin'' - SDK tools required for model conversion
   * ''adla-toolkit-binary/demo'' - Conversion examples   * ''adla-toolkit-binary/demo'' - Conversion examples
 +  * ''adla-toolkit-binary/python'' - KSNN conversion examples
  
-==== Get the conversion tool ==== +<WRAP important> 
- +If your kernel is older than 241129, please use branch npu-ddk-1.7.5.5. 
-Download The conversion tool from [[gl>khadas/vim4_npu_sdk]]. +</WRAP> 
- +==== Convert ====
-```shell +
-$ git clone https://gitlab.com/khadas/vim4_npu_sdk +
-```+
  
 After training the model, run the scripts as follows to modify net input and output and convert the model to ONNX. After training the model, run the scripts as follows to modify net input and output and convert the model to ONNX.
Line 72: Line 84:
 ``` ```
  
-Enter ''vim4_npu_sdk/demo'' and modify ''convert_adla.sh'' as follows. We should quantize the model to **int16** because it is very inaccurate with **int8**.+Enter ''vim4_npu_sdk/demo'' and modify ''convert_adla.sh'' as follows.
  
 ```bash convert_adla.sh ```bash convert_adla.sh
Line 92: Line 104:
         --dtypes "float32" \         --dtypes "float32" \
         --inference-input-type float32 \         --inference-input-type float32 \
- --inference-output-type float32 \ + --inference-output-type float32 \ 
-        --quantize-dtype int16 --outdir onnx_output  \+        --quantize-dtype int8 --outdir onnx_output  \
         --channel-mean-value "0,0,0,255"  \         --channel-mean-value "0,0,0,255"  \
         --source-file ./densenet_ctc_dataset.txt  \         --source-file ./densenet_ctc_dataset.txt  \
Line 116: Line 128:
 $ git clone https://github.com/khadas/vim4_npu_applications $ git clone https://github.com/khadas/vim4_npu_applications
 ``` ```
 +
 +<WRAP important>
 +If your kernel is older than 241129, please use version before tag ddk-3.4.7.7.
 +</WRAP>
  
 ==== Install dependencies ==== ==== Install dependencies ====
Line 128: Line 144:
 === Picture input demo === === Picture input demo ===
  
-Put ''densenet_ctc_int16.adla'' in ''vim4_npu_applications/densenet_ctc/data/''.+Put ''densenet_ctc_int8.adla'' in ''vim4_npu_applications/densenet_ctc/data/''.
  
 ```shell ```shell
Line 139: Line 155:
  
 # Run # Run
-$ sudo ./densenet_ctc -m ../data/densenet_ctc_int16.adla -p ../data/KhadasTeam.png+$ ./densenet_ctc -m ../data/densenet_ctc_int8.adla -p ../data/KhadasTeam.png
 ``` ```
  
-<WRAP tip >+{{:products:sbc:vim4:npu:demos:khadasteam.webp?400|}} 
 + 
 +{{:products:sbc:vim4:npu:demos:densenet-demo-output.webp?400|}} 
 + 
 +<WRAP tip>
 If your ''densenet_ctc'' - **DenseNet-CTC** model classes are not the same, please change ''data/class_str.txt'' and the ''OBJ_CLASS_NUM'' in ''include/postprocess.h''. If your ''densenet_ctc'' - **DenseNet-CTC** model classes are not the same, please change ''data/class_str.txt'' and the ''OBJ_CLASS_NUM'' in ''include/postprocess.h''.
 </WRAP> </WRAP>
  
Last modified: 2024/10/28 21:11 by louis

Page Tools

Khadas Site

Khadas Community

Khadas GitHub

Khadas Downloads