Koby_n_Code

Пікірлер

@user-qc1mx2ob6v 2 күн бұрын

nice video~

@xinloongfoo2951 3 күн бұрын

is it possible if i use ESP32-cam as the live camera?

@irfanhakim4369 6 күн бұрын

thank you so much, man. you helped me a lot :)

@JoeNassar-og3qe 9 күн бұрын

Hello Koby..Thanks for this video...I just bought dual edge coral TPU but in pci case for raspberry pi 5. . Can not this be used with this library?

@samoo6931 17 күн бұрын

Please help me in that , i have a rpi 4 with 64 bit os , and i want to use camera module ip , with script ultrlytics

@ConsultingjoeOnline 18 күн бұрын

Great video. Thanks!

@rekomarie8779 22 күн бұрын

Hello Koby, i have a problem when i run the code like you did at 28:41 my RP4 reboot, i do not know why i have tried many time and it reboot again , i need to finish your tutorial so i could use my usb web cam to for live object detection, thank you in advance Edit: the RP does not reboot it closed remotely

@maksp6208 22 күн бұрын

Hello Koby. Can you help me pls? I want to run an object detection model on my raspberry pi 4 with a Coral USB accelerator and a model 3 wide camera. But I am having big problems with FPS currently only 3-4fps. Can you recommend me the best approach? I need to detect objects at a long distance but I have only class 1. I have been using mobilenet ssd fpn lite 320 and 640. I need to have minimum 25fps to close my project. I would appreciate any help. Thank you.

@user-ed4yp6eq5k 2 күн бұрын

Same with steam deck 6fps 9 classes I had to resize to 240x240 2 classes now I get 22fps. I need 45fps min

@alimohsen7071 28 күн бұрын

Can I create my own model using yolov8? How do I convert it to tflite?

@samoo6931 28 күн бұрын

can i get ur number in wasup app please i need ur brain

@joshuajohn2220 Ай бұрын

/.venv/lib/python3.7/site-packages/edge_tpu_silva/silva/silva_detect.py", line 34, in process_detection model=model_path, task="detect", verbose=False TypeError: __init__() got an unexpected keyword argument 'verbose' getting this error when trying to run cli. additionally can you give some definitive example on formatting camera input. specifically using camera 0 on rpi5. thanks

@davidnyarko7300 Ай бұрын

What was the CLI command you executed?

@joshuajohn2220 Ай бұрын

@@davidnyarko7300 silvatpu -p det -m /home/josh/silva/240_yolov8n_full_integer_quant_edgetpu.tflite -i 0 -z 240 -t 0.5 -v true /home/josh/.venv/lib/python3.7/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: warn(f"Failed to load image Python extension: {e}") Traceback (most recent call last): File "/home/josh/.venv/bin/silvatpu", line 8, in <module> sys.exit(silvatpu()) File "/home/josh/.venv/lib/python3.7/site-packages/edge_tpu_silva/__main__.py", line 97, in silvatpu for _, _ in outs: File "/home/josh/.venv/lib/python3.7/site-packages/edge_tpu_silva/silva/silva_detect.py", line 34, in process_detection model=model_path, task="detect", verbose=False TypeError: __init__() got an unexpected keyword argument 'verbose'

@joshuajohn2220 Ай бұрын

@@davidnyarko7300 silvatpu -p det -m /home/josh/silva/240_yolov8n_full_integer_quant_edgetpu.tflite -i 0 -z 240 -t 0.5 -v true

@joshuajohn2220 Ай бұрын

/home/josh/.venv/lib/python3.7/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: warn(f"Failed to load image Python extension: {e}") Traceback (most recent call last): File "/home/josh/.venv/bin/silvatpu", line 8, in <module> sys.exit(silvatpu())

@joshuajohn2220 28 күн бұрын

@@davidnyarko7300 ?

@maxamed19ib Ай бұрын

What name command you write

@davidnyarko7300 Ай бұрын

Could you please let me know which specific command you are referring to? I'll be happy to help you with it.

@music_love21 Ай бұрын

Hi! We are creating a system that classifies tomato ripeness levels using image processing in CNN architecture with the YOLOv8 model. We are using Raspberry Pi 4 OS with 4GB RAM and we have encountered a problem - the system has 2-3 minute delay/lag in classifying the ripeness level. Would you happen to have any recommendation/suggestion sir on this problem?

@davidnyarko7300 Ай бұрын

Sure, my first recommendation to you is this video, you could get the Edge Tpu USB accelerator to help you speed up the process.

@music_love21 Ай бұрын

@davidnyarko7300 Ай бұрын

My first recommendation to you is this video, you could get the edge tpu USB accelerator to help you speed up the process.

@shahriarahmadfahim6457 Ай бұрын

Thank you for your video. How much FPS did you get for YOLOv8 and YOLOv9 respectively?

@davidnyarko7300 Ай бұрын

We did get several FPS in this video depending on the process type and model size. Some combinations gave the peek 60FPS, and 30FPS for the most part.

@alimohsen7071 Ай бұрын

‏‪35:24‬‏ Thank you. The explanation was very good. But I have one problem. At this time 35:24 , I keep getting the same error. I could not solve it.

@davidnyarko7300 Ай бұрын

Thanks for the comment. The mentioned error occurs when the USB accelerator is connected to your Raspberry Pi when the code is executed. If it was connected then there is a loose contact just like in my case while working with pi5. You can change the port/ make sure you have firm USB contact.

@alimohsen7071 Ай бұрын

Thank you, the problem has been solved❤

@werangalakshitha9800 Ай бұрын

github link is not working can u reply with the link ? thank you...!

@davidnyarko7300 Ай бұрын

Sure… github.com/DAVIDNYARKO123/yolov8-silva

@andrei1916dtz Ай бұрын

Thank you so much for this amazing tutorial, it helped a lot with my project! Could you please help me with some informations about how I could use this setup for an USB webcam live inference object detection? Instead of being on .mp4 video files. I tried using the ultralytics script, but it didn’t work. Thanks again!

@davidnyarko7300 Ай бұрын

Hey! For a USB webcam, you can specify 0 or 1 or (your USB camera index) as the input and everything works the same with your camera.

@davidnyarko7300 Ай бұрын

Please provide context for the Ultralytics script and error.

@samoo6931 17 күн бұрын

@davidyarko7300 please help me

@PenguinYan Ай бұрын

Thank for your tutorial maybe it's have possible to deploy YOLOv7 model on TPU with RPI4 I will try it when i'm get some time

@davidnyarko7300 Ай бұрын

You are most welcome.

@muthannaso Ай бұрын

Thank you for this amazing tutorial

@davidnyarko7300 Ай бұрын

Glad it was helpful!

@somyadeepshrivastava1447 Ай бұрын

A great tutorial to get you started

@davidnyarko7300 Ай бұрын

Thank you

@oliverexcellent Ай бұрын

Thank you, thank you, thank you! I've been struggling to get my YOLOv8 + RPi 4 + Coral TPU up and running. I'm going to follow your tutorial this weekend and see if I can get everything working. Exciting!!

@davidnyarko7300 Ай бұрын

That sounds great. Post here if you facing any issues.

@PoojaKumari-ey9wg Ай бұрын

Hey I would like to know how we get the output on another terminal as you get as when I'm running the code it only giving the index and array as the output

@davidnyarko7300 Ай бұрын

You can set the show param to True.

@yoshimochii 2 ай бұрын

tysm for this tutorial! I just have a question, if I add a valid object that's not in the coco.txt file say "paper", can the model now detect paper?

@davidnyarko7300 Ай бұрын

No. you will need to train a new model on your custom dataset

@elasriabdelfettah815 2 ай бұрын

i have intel i5 and ram =8 G. but the video running slowly . and i have raspberry pi 3 cant running this program because the yolo algorithm need a more performance the CPU and RAM. Is my analysis correct? Thank you very much for your excellent explanation.

@davidnyarko7300 Ай бұрын

Sure, other factors might cause your model to be slow. You can check my new video on how to get realtime speed on Raspberry Pi.

@usamasherazi4598 3 ай бұрын

can you help me in detection with voicefeedback how i can do this? thanks waiting

@davidnyarko7300 Ай бұрын

Sure, but can you explain a bit further.

@user-pw3im1gx9v 4 ай бұрын

hey brother no matter what i do its howing no module named 'torch' even though i am trying to install that it says no matching dist found for torch what should i do somebody help me

@davidnyarko7300 Ай бұрын

What system are you running on?

@mayakrishna2955 5 ай бұрын

Hi there, thanks much. This is very useful. When is the next video coming up?

@davidnyarko7300 Ай бұрын

Thank you. I am starting a playlist for Object Detection and Segmentation this weekend.

@CyberneticEagle 7 ай бұрын

if i have a video that shows only a hand moving, how can i set a class hand to te model? The hand is classificated as 'person'

@davidnyarko7300 Ай бұрын

Currently, you can try the YOLO world model, you can set hand as a class.

@anupamsingh2943 7 ай бұрын

What should I do if I want to create an output video at the end?

@davidnyarko7300 7 ай бұрын

You will need to set “save” to True

@archana0342 8 ай бұрын

thank you brooo

@davidnyarko7300 8 ай бұрын

You are welcome

@barnacode 9 ай бұрын

Very helpful video, great work. Is there any way I could do this with a url to a video stream?

@davidnyarko7300 9 ай бұрын

Sure, just provide a KZbin video link and it will work with it.

@germancruz6618 9 ай бұрын

Dear Koby, How could I use the GPU instead of the CPU?

@davidnyarko7300 9 ай бұрын

Set device = [0], or device = “gpu”. Be sure you have GPU capacity on your system.

@YigalBZ 10 ай бұрын

Great video. You mentioned you will release similar video with training for custom class. Are you going to release it? I am waiting for it.

@davidnyarko7300 9 ай бұрын

Sure, I am constantly going to be releasing from this week

@timjobs9072 10 ай бұрын

Please comes out more videos like this!

@davidnyarko7300 10 ай бұрын

Thanks, will do 🙏

@MichaelChenAdventures 11 ай бұрын

good stufff mate thx

@davidnyarko7300 11 ай бұрын

Thanks

@khenpahilanga9596 11 ай бұрын

Hello, do u happen to know how to perform transfer learning and freezing?

@davidnyarko7300 9 ай бұрын

Sure, but with which architecture are you looking at.

@khenpahilanga9596 9 ай бұрын

@@davidnyarko7300 like with the yolov8, is there like a certain command i just type into the command line so it executes freezing and like i can improve to my custom trained model?

@anupamsingh2943 11 ай бұрын

What if we JUST want it to detect PERSON? And no other object?

@dependent-wafer-177 11 ай бұрын

Your class list should contain only "person"

@jordiwang Жыл бұрын

By the way, I live the way you teach, are you interested for particular classes? We can talk about the price

@davidnyarko7300 11 ай бұрын

Sure! you can contact me at [email protected]

@jordiwang Жыл бұрын

so far im in the minute 11 and it looks like the thing i am truly looking for. Thanks a lot man, love you so much, you're the only who teaches how to use the yolo model in python . PLease, let me spread your genes :D thanks

@davidnyarko7300 11 ай бұрын

You are very much welcome.