Hi,
I'm Sergio. I'm a Computer Vision consultant, developer and course instructor.
Pysource was founded in 2017 to help companies improve their process efficiency, reliability and scalability with the user of computer vision software.
In this channel I share informative videos about computer vision and cutting-edge AI solutions.
Пікірлер
This is magnificent, Thanks for sharing! Currently i am working on a project in this related topic (Human Face Recognition).
Thank you sir, you help me:)
how can i store the output in an excel file? thnx!
Thank you so much, i really learned a lot from your channel only from this video. I would be grateful if you made a longer video with some implementations
Hi. Please I need the solution you implemented for your optimization (processing more frames). Kindly share your optimization technique. Thank you.
Hi Elnasir, The optimization is a complex operation and often more complex then the entire project itself. I can give you here some guidelines on what to look for. Mainly there are 4 things to look into: - python code must be optimized, avoid using python loops and instead use operation on the array with numpy library - you can use libraries like timeit , to check the speed of every chunk of your code on python and try to optimize it as much as possible. - the deep learning model must be converted into tensorRT format, optimised for the size of the data you need to pass into it (number of images per batch and size of image), tailored to the specific GPU you're using. - you need to leverage multiprocessing and split the task of your software into multiple process to leverage the power of the CPU
Is this the best possible way? What do you think about FairMOT?
Is this the best way possible for Person ReID? What do you think about FairMOT?
is this a different method that we approach object tracking by using different functions in opencv, do you find it yourself?
Where is the source code please??
when I want to download the python files I can't register the website using my google account ,is there some that have download the python files successfully ,can someone help me to download files and send to me
i cant find simple_facerec file
Hey Mr Sergio I want to pay on study online course of video surveillance How much Mr Sergio could I pay for studying
hello @Pysource. I can not download the ZIP file
Hellow Mr Sergio can I learn from scratch Traffic survey of detection plate number of over speed vehicles?
Thank you for your amazing tutotrial video .Wath software do you use to do this
I installed pip install object_detector it becomes error how to install this library please tell me sir
Nice video. Thanks. Please I am working on malaria parasite detection from microscope slide images. Please how do I contact you?
Awesome presentation, Appreciate and admire you from my heart ... god bless ..... Expecting many more tutorial videos like this...
how to upload pygame to website?
Am i the only one who is not able to find the dnn module source code !?🥲.Help me guys
what if I am using yolov5, Nvidia tx1
How can we get the file?
Thank you
i want buy code
Hello Sir, Can you guide me on code for warping the face in such a way to convert that face to its old version?
requested the .py files but did not receive email
Why is my face capture only 3fps?
Thank you it worked after 2 days trying to install that 3.3mb thing🩷
thank you..
can you please make the video to predict trajectory of multiple objects in different polygon?? i will be thankful to you
can you please make the video to predict multiple objects in different polygon?? i will be thankful to you
Great Vid! Im trying to use this with Contacam. When i try to connect to the IP given by IP webcam its askes for s username and passwords tot he camera. where can i set this within IP webcam?
what if i want to use saturation???
sergio eu te amo
Where have you defined the "display_image_samples", "load_image_dataset" and "extract_images" functions? You are just calling those functions here.
I'm starting my journey into computer vision and Ai. Would it be possible for me to train a raspberry pi to count the number of cars from a video, models made by Honda for example? Am I barking up the wrong tree? I don't know Python but know C/C++ very well and the migration will be a walk in the park. Does Pi3B+ and Camera have the power to do that or do I need much better hardware which I don't have? Thanks for any guidance.
Hi, does anybody know how to measure size of rectangular box that can be rotated? Imagine same example as in the video, but instead of bolt nuts, it is packages and they can lay in any orientation on the conveyor belt. How would you approach that?
i want the source video of bottle without detection can you provide me the link please
Thanks a lot sir, I'm currently working on the project which is about preventing students from cheating. I'm already broke the problems down into some areas: 1. Eye gazing to check if the students are looking outside. 2. Eye blinking the keep track of the abnormal behaviors. 3. Mouth opening to check if they are speaking or not. 4. Object detection to check whether there are many people on the camera and whether they use untrustworthy devices. 5. Noise detection to check whether a abnormal sound. 6. Head pose estimation to check whether they looking outside, maybe I should combine this with the eye gazing, if there's no eyes, there will be abnormal behaviors. 7. Face spoofing to check whether the face on the screen is real face or not. I don't really know which parts should I put more into the project or should I remove something, because it's quite a challenge for me to get into the intern place in the project. I'm already done with the first three and planning to finish all the stuffs. Pls let me know your opinion about the idea and other question is how many features are good for me to show my effort to the project manager? Again, thank you sir and have a nice day!
Is there a big difference in performance and speed in AI tasks like stable diffusion & video rendering etc between RTX 4080 super and RTX 4090?Which one should i buy as I seldom play games or should i wait for 5090 at the end of the year?I am not a video editor or hold any jobs related to designing or editing,just a casual home user.
Yes, there is quite a big difference from the 4080 super and the 4090 in terms of speed and also memory. If you're not tight on budget I would definitely go for the 4090
where is the link for simple_facerec?????
I just tried this and it works perfectly! Thank you so much!
Very helpful. Thanks a lot.
I am looking for blister inspection in pharma industry. The feature we looking to inspect like 1. Empty blister 2. Double tablet in one cavity 3.wrong or mixed tablet 4.broken tablet 5.to identify and distinguish between same colour of capsule and its blister backgrounds.
Thank🎉 from Thailand.
can this code be used to detect rgb boxes on the conveyor?
why didn't you drop the link to download the data (DNN MODEL)?
which of the link can help me get the file you downloaded because i can't find it to download
i wanted to thank you for all the efforts you have put in all of your videos ❤❤ i really have learned a lot from your videos especially neural networks series i am a student in the faculty of computer engineering and i am currently in my bachelor thesis semester and it is about vehicle counting and classification now there are ton of models and detection algorithms can you recommend the best and easiest to work with models or algorithms out there for example there are 8 or 9 versions of yolo but i do not know what would be the most stable or best one out there thank you in advance
Thank you for the feedback, I'm glad the neural network series were useful to you ;) About your question, for vehicle tracking and classification, YOLOv8 by Ultralytics is a good choice.
@@pysource-com THANK YOU SO MUCH FOR YOUR REPLY ive been reading about YOLOv9 lately and the technologies used like PGI or the new architecture GELAN are outperforming YOLO v8 so i wanted ask if you have tried YOLOv9 and if yes do you find it easy to work with and stable
Amazing video, I'm waiting for new episodes. I'm working on a project to detect counterfeit products, for example airpods boxes, where we have a high level of quality in counterfeiting, making it difficult for a human to analyze without having an original box to compare. But I can see differences in the font used, the spacing between lines and the product photo has slightly less contrast than an original. I intend to do classification using YOLO, but the dataset has few images and they will all be very similar, leading me to try to use Siamese neural networks, few shot learning, to find the most similar one and classify it. My question, is there some approach I'm missing? thanks!
Thanks for the feedback. The project you're working on it's a bit complex as you'll be identifying details that require very high precision, so it's not easy to have reliable results. You're approach is a good starting point to make a study, get benchmarks and see how it performs, then you can evaluate the next steps of you projects. best of luck with your projet