Видео

This has been a very interesting series. I just stumbled on the series, followed and built the examples. I would have to say that initially I was kind of lost about the approach - it seemed kind of slow and tedious. But after following all of the episodes, each built on the previous and the examples were clear. However,, I'm a bit confused about this 7th installment and have a question and would like some clarification. In all of the installments, the examples were based on a single neuron. So the 3 by 3 horizontal and vertical images resulted in 9 input values feeding the single neuron with its own unique set of weights. But if we add another neuron, isn't it the case that the new neuron will have its own weights. In other words, a layer consists of potentially multiple neurons. And it seems to me that the Layer class in this example is actually a neuron class. I would think that the layer class would contain some number of neurons. I confess I am new to neural networks so I only have a very basic understanding. So if I'm missing something, can you clarify? Thank you.

Hello, I'm curious. From your example, I concluded that I need to manually annotate boxes for each individual digit separately. Is that correct, or is there another option?

Where can I find the yolo_segmentation.py file?

Good and useful video. Thank you very much.

Please create software for online label inspection using Python or provide some hints.

Thanks for sharing, very insightful, I would love to have more information on how to build those PoC and MVPs

Hello, what about camera calibration?

Any newer technology to this? Any newer and higher quality softwares?

That's really Perfect clear! Thank you.

does it work on night time

good

i am facing error in dlib while "pip install face_recognition": Failed to build dlib.. pls help

Excellent tutorial, well documentation, very good thinking and presentation skill for this complication codings

The idea for the video is nice but there is a lot open (or maybe not shown)? Did you calculate camera and lens instrincts first (using some kind of calibration sheet).

Love your tutorials 🥰

Yoooo your blog was so short and accurate! Didn't know that "mps" is the equivalent to cuda to using the mac gpu! My processtimes reduced from 3000ms to 100ms! Lessgo

which sofware are you using'

Can this method be used to measure moving objects via a camera on a conveyor belt?

from simple_facerec import SimpleFacerec can someone tell me why this line not working

thank you, your explanation is easy to understand

How to undo this process in a given photograph. ?

Excellent Video, how I can measure the lengths straight edges and round corners thanks for help

After training no files in google drive are created. Need help 😁

expensive

Thank You.

Thank you for this brief video. Can you please share the detail and specs of the high speed camera used in this project and how many bottles scanned / captured in one secon. Did you just measure the sides length of the label or you also performed the text recognition or color detection etc as well ?

евала баце

Can any other color he used with red ??

Great video!

Thanks Sergio

Hello, for those following the tutorial, a good enough roi can be ```python roi = frame[int(height/3):, int(width/2)-200:int(width/2)+200] ``` Good tutorial btw.

Thanks Sergio. I think I have probably done all 9 incorrectly so far!

Thank you, great video it really helps

Where do i get the four files from?

What if the coordinates I want are not on the picture, but outside the picture

Excuse me Sir, please can I ask you a question: I just decided to pay for the OpenCV certification, its 1500 canadian dollars, and I m pretty convinced that it is a great investment for my future career in CV. Please can you give me your opinion? It will be a great help Thank you in advance :)

Thanks a lot for teaching us to use YOLO for object detection. Thanks a lot.

i think you shoudl have aligned the depth information with the RGB camera

Hell Sir Thanks for your all videos and efforts. I am following your channel, but I request you please upload one detail video on how to finetuning Yolov5 model for custome images classification.

Hell Sir Thanks for your all videos and efforts. I am following your channel, but I request you please upload one detail video on how to finetuning Yolov5 model for custome images classification.

Sir i have to detect the node of the sugarcane on a conveyor can you help?

If anyone want to add class name without parsing classes.txt you can use model.names[cls] instead of str(cls). cv2.putText(frame, str(cls) + ": " + model.names[cls], (x,y-10), cv2.FONT_HERSHEY_PLAIN, 2, (0,0,225), 2) This is super useful video! Thanks!

Hi Sergio, Is it possible to precisely measure distance between any 2 points in the viewing area?

Hi, Would it be possible to detect the speed of vehicles, but with a camera at the same horizontal level as them? That is to say, a view which is not plunging, as in your example. We have a street; we place a camera on a pole about six feet high. We record passing vehicles and later, using Open CV or other programs, we are able to obtain the speed of everything in the camera's field of view. Of course, we took the distances beforehand, for example using a 100-foot measuring tape. Thank you for sharing your knowledge.

Hi, I am developing a system that detects if the object is damaged. This detection is done in an uncontrolled environment, by which I mean under different weather conditions, scales and rotations. As we have little data, and we probably won't be able to obtain more, I'm thinking about using "feature matching" since it's likely that Yolo and similar techniques won't be robust. Have you tried using "feature matching"?

what rotating device are you using? Can you suggest any good rotating device I can buy that can be controlled by computer? Can that mg996r be using on macOS or pc?

Someone can help with the error "no device conect"? My pc does detect the camera, but python doesn't 😢

Hi Sergio. Thank you for your video. I have a question for you. Currently I don't have acces to the camera, but would be the case if we go out of the 2 meters value? Which value would I get? The maximum value, a random distance, 0, null-value? Also I wanted to remark the the link that you provided for the codes is no longer available. Thank you again for your great job explaining this.

Excellent job