Respected Sir,
while executing today this error is coming after yesterday modification

# killall rkipc
killall: rkipc: no process killed
# chmod a+x luckfox_retinaface_facenet_spi_demo_test
# ./luckfox_retinaface_facenet_spi_demo_test ./model/RetinaFace.rknn. /model/mob
ilefacenet.rknn ./test.jpg
this device is not whitelisted for jpeg decoder cvi
.........
this device is not whitelisted for capture cvi
this device is not whitelisted for capture cvi
The device model is Luckfox Pico Pro/Max.
OUT Pin = 48
OUT Pin = 57
OUT Pin = 73
OUT Pin = 72
OUT Pin = 68
OUT Pin = 70
IN Pin = 69
lcd_id = ff
Use LCD_3_5
init retinaface
E RKNN: failed to open model: ./model/RetinaFace.rknn.
init facenet
E RKNN: failed to open model: /model/mobilefacenet.rknn
Retinaface Info
rknn_query fail! ret=-7
Segmentation fault (core dumped)
# ls
Please help......
Your this device is good and your support also but co operation is required Sir
thank you

Sir, I have taken screenshots of all the steps I performed. Please compare them to see if there are any differences:
1. Open the link https://wiki.luckfox.com/Luckfox-Pico/L ... sTouch-LCD and download the corresponding image. 2. Use a download tool to rewrite the image. 3. Confirm the machine's operational status and shut down the rkipc program. 4. Upload files from Windows to the root directory (/) of luckfox-pico. 5. Upload a facial image to the root directory of luckfox-pico (you can choose any image you like). 6. Execute the program. Since my image is placed in the root directory, I use /002.jpg. Finally, this demo may be too complex for you. I sincerely suggest that you start with simpler experiments. There are many interesting and simple experiments provided on the wiki.When you have sufficient Linux development experience, using this demo may yield greater rewards.

With all due respect sir,
I have followed each of the above steps very seriously and minutely.
I want thank for your extreme support
But this Luckfox pico was brought for Face Recognition purpose for our company,



Our team is working on it,but very limited resource for memory problem arises therefore i would suggest to resolve my to go further.otherwise this product will be waste.

Please atleast give me a code for Capturing camera video and transfering to 3.5 ResTouch LCD
or otherwise we have to move to other development board

input_attrs[0].size_with_stride=76800
output mem [0] = 128
Init success
devpath = /dev/video11
driver = rkisp_v7
card = rkisp_mainpath
bus_info = platform:rkisp-vir0
version = 20000
capabilities = 84201000
device_caps = 4201000
fmt = UYVY 4:2:2 59565955
fmt = Y/CbCr 4:2:2 3631564e
fmt = Y/CrCb 4:2:2 3136564e
fmt = Y/CrCb 4:2:0 3132564e
size = 32 x 16 ~ 2304 x 1296 (+8 +8)
fmt = Y/CbCr 4:2:0 3231564e
fmt = Y/CrCb 4:2:0 (N-C) 31324d4e
fmt = Y/CbCr 4:2:0 (N-C) 32314d4e
rkaiq log level ff0

Sir i have sorted previous issue,
But problem is coming i have executed "Killall rkipc" but compliation is struck over here
the camera is working well in VLC network
please suggest a solution

Crocodile wrote: ↑2024-03-22 6:42

rajadey150@gmail.com wrote: ↑2024-03-22 6:24 //LCD Init
if(DEV_ModuleInit() != 0){
DEV_ModuleExit();
exit(0);
}
SD_Init();
LCD_SCAN_DIR lcd_scan_dir = SCAN_DIR_DFT;
LCD_Init(lcd_scan_dir,800);
Paint_CreatImage();

//Show Image(This needs to be self-implemented)
i have tried this code but the library file is missing please give a proper library file structure for 3.5 LCD to excute this code in retina_face it will higly helpful

Thank you for your efforts. Due to the focus on utilizing RKNN during development, compatibility with screens was not a priority, and only the Framebuffer environment was tested. Currently, I am working on writing a demo that directly communicates with an LCD via SPI to display face recognition results. Once completed, I will upload it to GitHub and notify you immediately.

Hello, our engineers have already explained our plan to you. Currently, we do not have an example program for RKNN streaming to this 3.5-inch LCD. If you want to stream, please use the screen from our tutorial. With the foundation of lighting up the 3.5-inch LCD screen and RKNN, the rest will need to be developed on your own. Thank you for your support for LuckFox.

Respected Sir,
If you could please provide me the sample code for 3.5 LCD restouch and camera interface,in which the image of the camera will be shown in the LCD.
That will be good enough for us.
Meanwhile if could rectify the sample for LCD touch then it would be very helpful

We have all the relevant tutorials and code on our Wiki. If you are looking for specific code that is not currently available, you can follow our official Wiki. When our engineers have time, I will promptly provide feedback to you. We strive to serve every customer well, but our engineers have limited time and energy. Moreover, embedded system knowledge is extensive and diverse, so we cannot guarantee that we can address every issue. Writing code, modifying source code, and understanding source code are not within the scope of technical support and need to be done independently. Understanding is paramount.

With all due respect,
thank you providing such a support,
I request if could only provide a code in which the image of camera is directly shown in lcd only this much will be enough for us.

Both instances utilize the opencv-mobile driver to capture images from the sc3336 camera, process the images, and display the results on an LCD screen. The object recognition routine uses the Yolov5 convolutional neural network model, capable of recognizing 80 types of objects and displaying confidence levels.


The instance displays the results of model inference on the Pico-LCD-1.3 screen, requiring the screen to be treated as a Framebuffer device driver.

**only convert the Pico-LCD 1.3 screen to 3.5 ResTouch LCD for our facial purpose