Beginners Guide: Import Yolov3 or Yolov3-tiny Models to Your VIM3

[goenjoy]

Preface:

By going through the Beginners Guide: darknet-yolov3 or yolov3-tiny Model Training document, we now have our own trained Yolov3 or Yolov3-tiny model. Next, we will demonstrate step by step how to transform and adapt our model to the “Khadas Android NPU App” that will run on a Khadas VIM3 with Android OS installed.

Please refer to this document if you wish to run your model on a VIM3 with Ubuntu OS installed.

1. Transform Your Model

Model transformation flow chart：

1.1 Import Model

The current model transformation process is carried out in the “acuity-toolkit” directory:

cd {workspace}/aml_npu_sdk/acuity-toolkit
cp {workspace}/yolov3-khadas_ai.cfg_train demo/model/
cp {workspace}/yolov3-khadas_ai_last.weights demo/model/
cp {workspace}/test.jpg demo/model/

Modified as follows：

hlm@Server:/users/hlm/npu/aml_npu_sdk/acuity-toolkit/demo$ git diff
diff --git a/acuity-toolkit/demo/0_import_model.sh b/acuity-toolkit/demo/0_import_model.sh
index 3198810..4671c9f 100755
--- a/acuity-toolkit/demo/0_import_model.sh
+++ b/acuity-toolkit/demo/0_import_model.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-NAME=mobilenet_tf
+NAME=yolov3
 ACUITY_PATH=../bin/
 
 convert_caffe=${ACUITY_PATH}convertcaffe
@@ -11,13 +11,13 @@ convert_onnx=${ACUITY_PATH}convertonnx
 convert_keras=${ACUITY_PATH}convertkeras
 convert_pytorch=${ACUITY_PATH}convertpytorch
 
-$convert_tf \
-    --tf-pb ./model/mobilenet_v1.pb \
-    --inputs input \
-    --input-size-list '224,224,3' \
-    --outputs MobilenetV1/Predictions/Softmax \
-    --net-output ${NAME}.json \
-    --data-output ${NAME}.data 
+#$convert_tf \
+#    --tf-pb ./model/mobilenet_v1.pb \
+#    --inputs input \
+#    --input-size-list '224,224,3' \
+#    --outputs MobilenetV1/Predictions/Softmax \
+#    --net-output ${NAME}.json \
+#    --data-output ${NAME}.data 
        
 #$convert_caffe \
 #    --caffe-model xx.prototxt   \
@@ -30,11 +30,11 @@ $convert_tf \
 #    --net-output ${NAME}.json \
 #    --data-output ${NAME}.data 
 
-#$convert_darknet \
-#    --net-input xxx.cfg \
-#      --weight-input xxx.weights \
-#    --net-output ${NAME}.json \
-#    --data-output ${NAME}.data 
+$convert_darknet \
+    --net-input ./model/yolov3-khadas_ai.cfg_train \
+    --weight-input ./model/yolov3-khadas_ai_last.weights \
+    --net-output ${NAME}.json \
+    --data-output ${NAME}.data 

--- a/acuity-toolkit/demo/data/validation_tf.txt
+++ b/acuity-toolkit/demo/data/validation_tf.txt
@@ -1 +1 @@
-./space_shuttle_224.jpg, 813
+./test.jpg

Execute the corresponding script：

bash 0_import_model.sh 

1.2 Quantify the Model

hlm@Server:/users/hlm/npu/aml_npu_sdk/acuity-toolkit/demo$ git diff
diff --git a/acuity-toolkit/demo/1_quantize_model.sh b/acuity-toolkit/demo/1_quantize_model.sh
index 630ea7f..ee7bd00 100755
--- a/acuity-toolkit/demo/1_quantize_model.sh
+++ b/acuity-toolkit/demo/1_quantize_model.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-NAME=mobilenet_tf
+NAME=yolov3
 ACUITY_PATH=../bin/
 
 tensorzone=${ACUITY_PATH}tensorzonex
@@ -11,12 +11,12 @@ $tensorzone \
     --dtype float32 \
     --source text \
     --source-file data/validation_tf.txt \
-    --channel-mean-value '128 128 128 128' \
-    --reorder-channel '0 1 2' \
+    --channel-mean-value '0 0 0 256' \
+    --reorder-channel '2 1 0' \
     --model-input ${NAME}.json \
     --model-data ${NAME}.data \
     --model-quantize ${NAME}.quantize \
-    --quantized-dtype asymmetric_affine-u8 \
+    --quantized-dtype dynamic_fixed_point-i8 \

Note that the - -quantized-dtype here is different for Ubuntu OS. Execute the corresponding script:

bash 1_quantize_model.sh

1.3 Generate Case Code

hlm@Server:/users/hlm/npu/aml_npu_sdk/acuity-toolkit/demo$ git diff
diff --git a/acuity-toolkit/demo/2_export_case_code.sh b/acuity-toolkit/demo/2_export_case_code.sh
index 85b101b..867c5b9 100755
--- a/acuity-toolkit/demo/2_export_case_code.sh
+++ b/acuity-toolkit/demo/2_export_case_code.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-NAME=mobilenet_tf
+NAME=yolov3
 ACUITY_PATH=../bin/
 
 export_ovxlib=${ACUITY_PATH}ovxgenerator
@@ -8,8 +8,8 @@ export_ovxlib=${ACUITY_PATH}ovxgenerator
 $export_ovxlib \
     --model-input ${NAME}.json \
     --data-input ${NAME}.data \
-    --reorder-channel '0 1 2' \
-    --channel-mean-value '128 128 128 128' \
+    --reorder-channel '2 1 0' \
+    --channel-mean-value '0 0 0 256' \

Execute the corresponding script：

bash 2_export_case_code.sh

Of course, as long as there is no error whilst running the script, you can execute the script with just one line after the above modifications are completed：

bash 0_import_model.sh && bash 1_quantize_model.sh  && bash 2_export_case_code.sh

Finally, an “nbg_unify_yolov3” directory will be generated：

2. Import the Demo Application to Your VIM3 Running Android OS

2.1 Install the NDK Compilation Environment

wget https://dl.google.com/android/repository/android-ndk-r17-linux-x86_64.zip
unzip android-ndk-r17-linux-x86_64.zip
vim ~/.bashrc
##Add the following two lines of code to the end of the file
##export NDKROOT=/path/to/android-ndk-r17
##export PATH=$NDKROOT:$PATH

As shown in the figure：

Then execute this command via your SSH terminal:

source ~/.bashrc

2.2 Compile the Related Libraries

1. Download the khadas_android_npu_library

git clone https://github.com/khadas/khadas_android_npu_library -b khadas_ai

2. Move the files vnn_pre_process.h，vnn_post_process.h，vnn_yolov3.h，and vnn_yolov3.c from the “nbg_unify_yolov3” directory to the following corresponding directories.

cp {workspace}/nbg_unify_yolov3/vnn_pre_process.h {workspace}/khadas_android_npu_library/model_code/detect_yolo_v3/jni/include/
cp {workspace}/nbg_unify_yolov3/vnn_post_process.h {workspace}/khadas_android_npu_library/model_code/detect_yolo_v3/jni/include/
cp {workspace}/nbg_unify_yolov3/vnn_yolov3.h {workspace}/khadas_android_npu_library/model_code/detect_yolo_v3/jni/include/
cp {workspace}/nbg_unify_yolov3/vnn_yolov3.c {workspace}/khadas_android_npu_library/model_code/detect_yolo_v3/jni/

3. Modify yolov3_process.c. Our demo contains two classes (KuLi, DuLanTe), modify the class array, num_class and LISTSIZE

static char *coco_names[] = {"KuLi","DuLanTe"};

LISTSIZE = (num_class + 5 ) = 2+5 = 7

4. Compile libnn_yolo_v3.so

cd {workspace}/khadas_android_npu_library/model_code/detect_yolo_v3
ndk-build

3. Import Relevant Libraries into the Demo App

1. Download the Demo App

git clone https://github.com/khadas/khadas_android_npu_app -b khadas_ai

2. Replace libnn_yolo_v3.so

cp {workspace}/khadas_android_npu_library/model_code/detect_yolo_v3/libs/armeabi-v7a/libnn_yolo_v3.so {workspace}/khadas_android_npu_app/app/libs/armeabi-v7a/

3. Replace the yolov3.nb file

cp {workspace}/acuity-toolkit/demo/nbg_unify_yolov3/yolov3.nb {workspace}/khadas_android_npu_app/app/src/main/assets/yolov3_88.nb

4. When you’re done, import the ‘khadas_android_npu_app’ project code into Android Studio, compile and run it on your VIM3 single board computer.

Supplemental Information：Yolov3-tiny

1. Import Model

The current model transformation process is carried out within the “acuity-toolkit” directory:

cd {workspace}/aml_npu_sdk/acuity-toolkit
cp {workspace}/yolov3-khadas_ai_tiny.cfg_train demo/model/
cp {workspace}/yolov3-khadas_ai_tiny_last.weights demo/model/
cp {workspace}/test.jpg demo/model/

Modified as follows：

hlm@Server:/users/hlm/npu/aml_npu_sdk/acuity-toolkit/demo$ git diff
diff --git a/acuity-toolkit/demo/0_import_model.sh b/acuity-toolkit/demo/0_import_model.sh
index 3198810..3b4efd3 100755
--- a/acuity-toolkit/demo/0_import_model.sh
+++ b/acuity-toolkit/demo/0_import_model.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-NAME=mobilenet_tf
+NAME=yolotiny
 ACUITY_PATH=../bin/
 
 convert_caffe=${ACUITY_PATH}convertcaffe
@@ -11,13 +11,13 @@ convert_onnx=${ACUITY_PATH}convertonnx
 convert_keras=${ACUITY_PATH}convertkeras
 convert_pytorch=${ACUITY_PATH}convertpytorch
 
-$convert_tf \
-    --tf-pb ./model/mobilenet_v1.pb \
-    --inputs input \
-    --input-size-list '224,224,3' \
-    --outputs MobilenetV1/Predictions/Softmax \
-    --net-output ${NAME}.json \
-    --data-output ${NAME}.data 
+#$convert_tf \
+#    --tf-pb ./model/mobilenet_v1.pb \
+#    --inputs input \
+#    --input-size-list '224,224,3' \
+#    --outputs MobilenetV1/Predictions/Softmax \
+#    --net-output ${NAME}.json \
+#    --data-output ${NAME}.data 
        
 #$convert_caffe \
 #    --caffe-model xx.prototxt   \
@@ -30,11 +30,11 @@ $convert_tf \
 #    --net-output ${NAME}.json \
 #    --data-output ${NAME}.data 
 
-#$convert_darknet \
-#    --net-input xxx.cfg \
-#      --weight-input xxx.weights \
-#    --net-output ${NAME}.json \
-#    --data-output ${NAME}.data 
+$convert_darknet \
+    --net-input ./model/yolov3-khadas_ai_tiny.cfg_train \
+       --weight-input ./model/yolov3-khadas_ai_tiny_last.weights \
+    --net-output ${NAME}.json \
+    --data-output ${NAME}.data 

--- a/acuity-toolkit/demo/data/validation_tf.txt
+++ b/acuity-toolkit/demo/data/validation_tf.txt
@@ -1 +1 @@
-./space_shuttle_224.jpg, 813
+./test.jpg

2. Quantify Your Model

hlm@Server:/users/hlm/npu/aml_npu_sdk/acuity-toolkit/demo$ git diff
diff --git a/acuity-toolkit/demo/1_quantize_model.sh b/acuity-toolkit/demo/1_quantize_model.sh
index 630ea7f..ee7bd00 100755
--- a/acuity-toolkit/demo/1_quantize_model.sh
+++ b/acuity-toolkit/demo/1_quantize_model.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-NAME=mobilenet_tf
+NAME=yolotiny
 ACUITY_PATH=../bin/
 
 tensorzone=${ACUITY_PATH}tensorzonex
@@ -11,12 +11,12 @@ $tensorzone \
     --dtype float32 \
     --source text \
     --source-file data/validation_tf.txt \
-    --channel-mean-value '128 128 128 128' \
-    --reorder-channel '0 1 2' \
+    --channel-mean-value '0 0 0 256' \
+    --reorder-channel '2 1 0' \
     --model-input ${NAME}.json \
     --model-data ${NAME}.data \
     --model-quantize ${NAME}.quantize \
-    --quantized-dtype asymmetric_affine-u8 \
+    --quantized-dtype dynamic_fixed_point-i8 \

Note that the - -quantized-dtype here is different on Ubuntu OS.

3. Generate Case Code

hlm@Server:/users/hlm/npu/aml_npu_sdk/acuity-toolkit/demo$ git diff
diff --git a/acuity-toolkit/demo/2_export_case_code.sh b/acuity-toolkit/demo/2_export_case_code.sh
index 85b101b..867c5b9 100755
--- a/acuity-toolkit/demo/2_export_case_code.sh
+++ b/acuity-toolkit/demo/2_export_case_code.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 
-NAME=mobilenet_tf
+NAME=yolotiny
 ACUITY_PATH=../bin/
 
 export_ovxlib=${ACUITY_PATH}ovxgenerator
@@ -8,8 +8,8 @@ export_ovxlib=${ACUITY_PATH}ovxgenerator
 $export_ovxlib \
     --model-input ${NAME}.json \
     --data-input ${NAME}.data \
-    --reorder-channel '0 1 2' \
-    --channel-mean-value '128 128 128 128' \
+    --reorder-channel '2 1 0' \
+    --channel-mean-value '0 0 0 256' \

After the above modification, you can execute the script with just one line:

bash 0_import_model.sh && bash 1_quantize_model.sh  && bash 2_export_case_code.sh

Finally, a “nbg_unify_yolotiny” directory will be generated：

2. Import Demo Application into your VIM3 Android OS

2.1 Install the NDK Compilation Environment

wget https://dl.google.com/android/repository/android-ndk-r17-linux-x86_64.zip
unzip android-ndk-r17-linux-x86_64.zip
vim ~/.bashrc
##Add the following two lines of code to the end of the file
##export NDKROOT=/path/to/android-ndk-r17
##export PATH=$NDKROOT:$PATH

As shown in the figure：

Then execute this command from within your SSH terminal:

source ~/.bashrc

2.2 Compile Related Libraries

1. Download the khadas_android_npu_library

git clone https://github.com/khadas/khadas_android_npu_library -b khadas_ai

2. Add the “khadas_android_npu_library/model_code/detect_yolo_tiny/” directory and related codes

The specific differences can be compared with Yolov3. The main differences are in the *_process.c file, as shown in the following figure:

3. Move the files vnn_pre_process.h，vnn_post_process.h，vnn_yolotiny.h，and vnn_yolotiny.c from the “detect_yolo_tiny” directory to the following corresponding directories:

cp {workspace}/nbg_unify_yolotiny/vnn_pre_process.h {workspace}/khadas_android_npu_library/model_code/detect_yolo_tiny/jni/include/
cp {workspace}/nbg_unify_yolotiny/vnn_post_process.h {workspace}/khadas_android_npu_library/model_code/detect_yolo_tiny/jni/include/
cp {workspace}/nbg_unify_yolotiny/vnn_yolotiny.h {workspace}/khadas_android_npu_library/model_code/detect_yolo_tiny/jni/include/
cp {workspace}/nbg_unify_yolotiny/vnn_yolotiny.c {workspace}/khadas_android_npu_library/model_code/detect_yolo_tiny/jni/

4. Modify yolo_tiny_process.c
   Our demo contains two classes (KuLi, DuLanTe), modify the class array, num_class and LISTSIZE:

static char *coco_names[] = {"KuLi","DuLanTe"};

LISTSIZE = (num_class + 5 ) = 2+5 = 7

4. Compile libnn_yolo_tiny.so

cd {workspace}/khadas_android_npu_library/model_code/detect_yolo_tiny
ndk-build

5. Compile libkhadas_npu_jni.so

First add the following code:

hlm@Server:/users/hlm/npu/khadas_android_npu_library/detect_code$ git diff
diff --git a/detect_code/jni/khadas_npu_det.cpp b/detect_code/jni/khadas_npu_det.cpp
index 7db2632..f90862e
--- a/detect_code/jni/khadas_npu_det.cpp
+++ b/detect_code/jni/khadas_npu_det.cpp
@@ -159,6 +159,9 @@ static jint npu_det_set_model(JNIEnv *env, jclass clazz __unused,jint modelType)
                case 2:
                type = DET_YOLO_V3;
                break;
+               case 3:
+               type = DET_YOLO_TINY;
+               break;          
                default:
                type = DET_FACENET;
                break;
@@ -201,6 +204,9 @@ static jint npu_det_get_result(JNIEnv *env, jclass clazz __unused,jobject detres
                case 2:
                type = DET_YOLO_V3;
                break;
+               case 3:
+               type = DET_YOLO_TINY;
+               break;                  
                default:
                type = DET_FACENET;
                break;
@@ -311,6 +317,9 @@ static jint npu_det_set_input(JNIEnv *env, jclass clazz __unused,jbyteArray imgb
                case 2:
                type = DET_YOLO_V3;
                break;
+               case 3:
+               type = DET_YOLO_TINY;
+               break;                  

Compile:

hlm@Server:/users/hlm/npu/khadas_android_npu_library/detect_code$ ndk-build 

2.3 Import Relevant Libraries to the Demo App

1. Download the Demo App

git clone https://github.com/khadas/khadas_android_npu_app -b khadas_ai

2. Replace libnn_yolo_tiny.so

cp {workspace}/khadas_android_npu_library/model_code/detect_yolo_tiny/libs/armeabi-v7a/libnn_yolo_tiny.so {workspace}/khadas_android_npu_app/app/libs/armeabi-v7a/

3. Replace libkhadas_npu_jni.so

cp {workspace}/khadas_android_npu_library/detect_code/libs/armeabi-v7a/libkhadas_npu_jni.so {workspace}/khadas_android_npu_app/app/libs/armeabi-v7a/

4. Replace the yolotiny.nb file

cp {workspace}/acuity-toolkit/demo/nbg_unify_yolotiny/yolotiny.nb {workspace}/khadas_android_npu_app/app/src/main/assets/yolotiny_88.nb

5. Add Yolov3-tiny buttons to your app
   The code is modified as follows:

hlm@Server:/users/hlm/npu/khadas_android_npu_app$ git diff app/src/
diff --git a/app/src/main/java/com/khadas/npudemo/CameraActivity.java b/app/src/main/java/com/khadas/npudemo/CameraActivity.java
index 20f3e8d..dc91f60
--- a/app/src/main/java/com/khadas/npudemo/CameraActivity.java
+++ b/app/src/main/java/com/khadas/npudemo/CameraActivity.java
@@ -111,7 +111,8 @@ public abstract class CameraActivity extends AppCompatActivity implements Camera
     public enum ModeType {
         DET_YOLOFACE_V2,
         DET_YOLO_V2,
-        DET_YOLO_V3
+        DET_YOLO_V3,
+        DET_YOLO_TINY
     }
     static ModeType mode_type;
 
@@ -162,6 +163,12 @@ public abstract class CameraActivity extends AppCompatActivity implements Camera
                 } else {
                     in = assmgr.open("yolov3_99.nb");
                 }
+            }  if(mode_type == ModeType.DET_YOLO_TINY) {
+                if(mStrboard.equals("kvim3")) {
+                    in = assmgr.open("yolotiny_88.nb");
+                } else {
+                    in = assmgr.open("yolotiny_99.nb");
+                }
             }  if(mode_type == ModeType.DET_YOLOFACE_V2) {
                 if(mStrboard.equals("kvim3")) {
                     in = assmgr.open("yolo_face_88.nb");
@@ -278,7 +285,14 @@ public abstract class CameraActivity extends AppCompatActivity implements Camera
             }
             setmoderesult = inceptionv3.npu_det_set_model(mode_type.ordinal());
         }
-
+        if(mode_type == ModeType.DET_YOLO_TINY) {
+            if(mStrboard.equals("kvim3")) {
+                copyNbFile(this, "yolotiny_88.nb");
+            } else {
+                copyNbFile(this, "yolotiny_99.nb");
+            }
+            setmoderesult = inceptionv3.npu_det_set_model(mode_type.ordinal());
+        }
         if(mode_type == ModeType.DET_YOLOFACE_V2) {
             if(mStrboard.equals("kvim3")) {
                 copyNbFile(this, "yolo_face_88.nb");
diff --git a/app/src/main/java/com/khadas/npudemo/MainActivity.java b/app/src/main/java/com/khadas/npudemo/MainActivity.java
index e858c2a..e85d6a9
--- a/app/src/main/java/com/khadas/npudemo/MainActivity.java
+++ b/app/src/main/java/com/khadas/npudemo/MainActivity.java
@@ -13,11 +13,13 @@ import android.app.AlertDialog;
 import android.content.DialogInterface;
 
 public class MainActivity extends AppCompatActivity implements View.OnClickListener{
+    private Button button_yolotiny;
     private Button button_yolov3;
     private Button button_yolov2;
     private Button button_yoloface;
     public  static  final String Intent_key="modetype";
     private static final String TAG = "MainActivity";
+    AlertDialog.Builder alertDialog0;
     AlertDialog.Builder alertDialog;
     AlertDialog.Builder alertDialog2;
     AlertDialog.Builder alertDialog3;
@@ -25,7 +27,8 @@ public class MainActivity extends AppCompatActivity implements View.OnClickListe
     public enum ModeType {
         DET_YOLOFACE_V2,
         DET_YOLO_V2,
-        DET_YOLO_V3
+        DET_YOLO_V3,
+        DET_YOLO_TINY
     }
 
 
@@ -38,15 +41,35 @@ public class MainActivity extends AppCompatActivity implements View.OnClickListe
         TextView textView = (TextView)findViewById(R.id.title);
         textView.setText("model selection");
 
-
+        button_yolotiny = (Button) findViewById(R.id.button_yolotiny);
         button_yolov3 = (Button) findViewById(R.id.button_yolov3);
         button_yolov2 = (Button) findViewById(R.id.button_yolov2);
         button_yoloface = (Button) findViewById(R.id.button_yoloface);
 
+        button_yolotiny.setOnClickListener(this);
         button_yolov3.setOnClickListener(this);
         button_yolov2.setOnClickListener(this);
         button_yoloface.setOnClickListener(this);
 
+        alertDialog0 = new AlertDialog.Builder(MainActivity.this);
+        alertDialog0.setTitle("prompt");
+        alertDialog0.setMessage("yolotiny image recognition model will run");
+        alertDialog0.setNegativeButton("cancel", new DialogInterface.OnClickListener() {//<E6><B7><BB><E5><8A><A0><E5><8F><96><E6><B6><88>
+                    @Override
+                    public void onClick(DialogInterface dialogInterface, int i) {
+                        Log.e(TAG, "AlertDialog cancel");
+                        //onClickNo();
+                    }
+                })
+                .setPositiveButton("ok", new DialogInterface.OnClickListener() {//<E6><B7><BB><E5><8A><A0>"Yes"<E6><8C><89><E9><92><AE>
+                    @Override
+                    public void onClick(DialogInterface dialogInterface, int i) {
+                        Log.e(TAG, "AlertDialog ok");
+                        onClickYolovTiny();
+                    }
+                })
+                .create();
+
         alertDialog = new AlertDialog.Builder(MainActivity.this);
         alertDialog.setTitle("prompt");
         alertDialog.setMessage("yolov3 image recognition model will run");
@@ -112,6 +135,13 @@ public class MainActivity extends AppCompatActivity implements View.OnClickListe
     public void onClick(View v) {
         //Log.e(TAG,"OnClickListener");
         switch (v.getId()) {
+            case R.id.button_yolotiny:
+                Log.e(TAG, "button_yolotiny");
+                //onClickButton1(v);
+                alertDialog.setCancelable(false);//<E7><82><B9><E5><87><BB><E7><A9><BA><E7><99><BD><E5><A4><84><E4><B9><8B><E5><90><8E><E5><BC><B9><E5><87><BA><E6><A1><86><E4><B8><8D><E4><BC><9A>
<E6><B6><88><E5><A4><B1>
+                alertDialog.show();
+                buttonSetFocus(v);
+                break;
             case R.id.button_yolov3:
                 Log.e(TAG, "button_yolov3");
                 //onClickButton1(v);
@@ -146,7 +176,14 @@ public class MainActivity extends AppCompatActivity implements View.OnClickListe
         button.requestFocusFromTouch();
 
     }
-
+       
+    private void onClickYolovTiny() {
+        //<E5><A4><84><E7><90><86><E9><80><BB><E8><BE><91>
+        Log.e(TAG, "button_yolovtiny enter ");
+        Intent intent = new Intent(this,ClassifierActivity.class);
+        intent.putExtra(Intent_key,ModeType.DET_YOLO_TINY.ordinal());
+        startActivity(intent);
+    }
 
     private void onClickYolov3() {
         //<E5><A4><84><E7><90><86><E9><80><BB><E8><BE><91>
diff --git a/app/src/main/res/layout/activity_main.xml b/app/src/main/res/layout/activity_main.xml
index 41ba40c..e2216d2
--- a/app/src/main/res/layout/activity_main.xml
+++ b/app/src/main/res/layout/activity_main.xml
@@ -23,6 +23,12 @@
             android:text="model select"/>
 
         <Button
+            android:id="@+id/button_yolotiny"
+            android:layout_width="300dp"
+            android:layout_height="80dp"
+            style="?android:attr/buttonBarButtonStyle"
+            android:text="yolotiny model" />
+        <Button
             android:id="@+id/button_yolov3"
             android:layout_width="300dp"
             android:layout_height="80dp"

6. When you’re done, import the ‘khadas_android_npu_app’ project code into Android Studio, compile and run it on your VIM3 single board computer.