This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
products:sbc:vim3:npu:npu-prebuilt-demo-usage [2022/09/16 03:23] ivan |
products:sbc:vim3:npu:npu-prebuilt-demo-usage [2023/09/11 09:46] hyphop [Get NPU Demo] |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ~~tag> | ||
+ | |||
====== NPU Prebuilt Demo Usage ====== | ====== NPU Prebuilt Demo Usage ====== | ||
- | <WRAP tip > | + | Prebuilt example demos for interacting with the Amlogic |
- | - Please follow this docs to upgrade | + | |
- | - Just support Opencv4 | + | |
- | </ | + | |
- | + | ||
- | ===== install | + | |
- | ```sh Install-OpenCV4.sh | + | ===== Install OpenCV4 |
- | sudo apt install libopencv-dev python3-opencv | + | Update your system and install the OpenCV packages. |
+ | ```shell | ||
+ | $ sudo apt update | ||
+ | $ sudo apt install libopencv-dev python3-opencv | ||
``` | ``` | ||
===== Get NPU Demo ===== | ===== Get NPU Demo ===== | ||
- | < | + | < |
- | NPU Demo is not installed on the board by default. You need to download it from github | + | The NPU Demo is not installed on the board by default. You need to download it from GitHub |
</ | </ | ||
- | 1) Clone to the board through the git command. | + | Get the demo source: [[gh> |
- | + | ```shell | |
- | ```sh get-npu-demo-from-demo.sh | + | $ git clone --recursive https:// |
- | cd {workspace} | + | |
- | git clone --recursive https:// | + | |
``` | ``` | ||
- | 2) Or download the compressed package directly, and then unzip it to the board. | ||
- | There are three directories in NPU Demo: | + | The NPU demo contains three examples: |
- | < | + | - '' |
- | | + | - '' |
- | < | + | - '' |
- | | + | |
- | < | + | |
- | | + | |
- | </ | + | |
===== Inception Model ===== | ===== Inception Model ===== | ||
+ | The inception model does not have any library dependencies and can be used as is. | ||
- | - The inception model does not need to install any libraries into the system. | + | Enter the '' |
- | - imagenet_slim_labels.txt is a label file. After the result is identified, the label corresponding to the result can be queried in this file. | + | |
+ | ```shell | ||
+ | $ cd aml_npu_demo_binaries/ | ||
+ | $ ls | ||
+ | dog_299x299.jpg | ||
+ | ``` | ||
- | $ cd {workspace}/ | + | '' |
- | $ ls | + | |
- | | + | |
- | < | + | < |
- | If your board is VIM3, enter the VIM3 directory, if it is VIM3L, then enter the VIM3L directory. Here is VIM3 as an example. | + | Depending on your board, enter the VIM3 or VIM3L directory |
</ | </ | ||
- | 1 | + | ```shell |
- | | + | $ ls aml_npu_demo_binaries/ |
- | + | $ inceptionv3 | |
- | | + | $ cd aml_npu_demo_binaries/ |
- | | + | $ ./run.sh |
- | | + | Create Neural Network: 59ms or 59022us |
- | | + | Verify... |
- | | + | Verify Graph: 0ms or 739us |
- | | + | Start run graph [1] times... |
- | | + | Run the 1 time: 20.00ms or 20497.00us |
- | | + | vxProcessGraph execution time: |
- | | + | Total |
- | | + | Average 20.54ms or 20540.00us |
- | | + | --- Top5 --- |
- | | + | 2: 0.833984 |
- | | + | 795: 0.009102 |
- | + | 974: 0.003592 | |
- | 14 974: 0.003592 | + | 408: 0.002207 |
- | | + | 393: 0.002111 |
- | | + | ``` |
- | + | ||
<WRAP Info> | <WRAP Info> | ||
| | ||
- | By querying imagenet_slim_labels.txt, | + | By querying |
</ | </ | ||
Line 80: | Line 76: | ||
===== Yolo Series Model ===== | ===== Yolo Series Model ===== | ||
- | ==== Preparation | + | ==== Install and uninstall libraries |
- | The application of the yolo series | + | The yolo series |
- | + | ||
- | ==== Install | + | |
- | The yolo series models need to install | + | You can follow the steps to either |
- | 1) Install | + | Install |
- | ```sh install-libraries.sh | + | ```shell |
- | cd {workspace}/ | + | $ cd aml_npu_demo_binaries/ |
- | sudo ./INSTALL | + | $ sudo ./INSTALL |
``` | ``` | ||
- | 2) Uninstall | ||
- | ```sh uninstall-libraries.sh | + | Uninstall libraries: |
- | cd {workspace}/ | + | |
- | sudo ./UNINSTALL | + | ```shell |
+ | $ cd aml_npu_demo_binaries/ | ||
+ | $ sudo ./UNINSTALL | ||
``` | ``` | ||
- | ==== type Parameter Description ==== | + | |
+ | ==== Type Parameter Description ==== | ||
<WRAP important > | <WRAP important > | ||
Line 106: | Line 102: | ||
</ | </ | ||
- | 1 | + | ```shell |
- | | + | 0 : yoloface model |
- | | + | 1 : yolov2 model |
- | | + | 2 : yolov3 model |
- | | + | 3 : yolov3_tiny model |
- | + | 4 : yolov4 model | |
- | ==== Operating Environment | + | ``` |
+ | |||
+ | ==== Operating Environment | ||
| | ||
- | NPU Demo can run in X11 or framebuffer mode, just select the corresponding demo to run. | + | NPU Demo can run in X11 Desktop |
- | === X11 / Framebuffer === | + | - The demo with fb is running in framebuffer mode. |
+ | - The demo with x11 is running in X11 mode. | ||
- | - The demo with fb is running in framebuffer mode. | + | ==== Demo examples ==== |
+ | === detect_demo_picture === | ||
- | - The demo with x11 is running in X11 mode. | + | ```shell |
+ | $ cd aml_npu_demo_binaries/ | ||
+ | $ ls | ||
+ | 1080p.bmp detect_demo_x11 | ||
+ | ``` | ||
+ | == Run == | ||
- | ==== Illustrative Example ==== | + | Command format of the picture. |
- | Here is an example of detect_demo_picture, | + | ```shell |
+ | $ cd aml_npu_demo_binaries/ | ||
+ | $ ./ | ||
+ | ``` | ||
+ | Here is an example of using OpenCV4 to call the yolov3 model to recognize pictures under '' | ||
- | ```sh detect-demo-picture-example.sh | + | ```shell |
- | $ cd {workspace}/ | + | $ cd aml_npu_demo_binaries/ |
- | $ ls | + | $ ./ |
- | 1080p.bmp | + | |
``` | ``` | ||
- | <WRAP tip > | ||
- | - detect_demo_fb It is a demo that uses opencv4 recognition pictures running under framebuffer | ||
- | - detect_demo_x11 It is a demo that uses opencv4 recognition pictures running under X11 | ||
- | </ | ||
- | ==== Run ==== | + | The results of the operation are as follows. |
- | Identify the command format of the picture. | + | {{: |
- | $ cd {workspace}/ | + | === detect_demo === |
- | $ ./ | + | |
- | Here is an example | + | <WRAP tip > |
+ | You should use the demo of usb to use the USB camera, and the demo of mipi to use the mipi camera. | ||
+ | </ | ||
- | $ cd {workspace}/ | + | == Run == |
- | | + | Command format for camera dynamic recognition. |
- | The results | + | ```shell |
+ | $ cd aml_npu_demo_binaries/ | ||
+ | $ ./ | ||
+ | ``` | ||
+ | |||
+ | Here is an example | ||
+ | ```shell | ||
+ | $ cd aml_npu_demo_binaries/ | ||
+ | $ ./ | ||
+ | ``` | ||
+ | |||
+ | <WRAP info > | ||
+ | After turning on the camera, the recognition result will be displayed on the screen. | ||
+ | </ | ||
- | {{ : | + | {{: |