Видео

Dear Filipe, thank you for your great videos. I just want to inform you that the Discord link says Expired. Thank you.

Great video but How do you do the collecting images part of the code?

i got an error to mounted the google drive but the files are not download and stored can u please prove complete code

Hello Felipe, thanks for sharing the knowledge! Do you think it is possible to be a CV Engineer without a CS degree? if possible, how do you get there without a CS degree?? Thank you so much!!!

Got this error: RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase. This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module: if __name__ == '__main__': freeze_support() ... The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable. lovely.. something I have no idea how to fix myself.

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 finetune Yolov5 model for custome images classification.

Sir you can help me ? What is inside your license_plate_detector.pt from where did you get that..?

can anyone help me how to get the license plate detector.pt because I could not find it ...

Loved the way you explained it. You are just like a COOL PROFESSOR👨‍🏫. Yes, this worked well for me😇. Fan, the way you are saying " many ,many, many , many., many.......🤩🤩😍😅😂🤣😆"

excellent video but while running the code it is showing nothing in the test file any recommendation for that ?

Felipe, do you know if this will work with the YOLOv9 MIT rewrite (made by the same group)? I think a few people would be interested as it has a more permissive license than GPLv3.

Thank you so much for the label creation code!!

from where you got the license_plate_detector.pt?

Hi, I wish the premium course was more affordable. $99 is a bit much for students - which are most probably your main audience. I would really like to take it but don't have the means.

i have downloaded the csv files , now how to convert it to yml or how to use for this model?

hello, thank you for the video! can I use CVAT with OBB for YOLO ? (oriented bounding boxes)

This is very cool, thanks a lot! Could you make a similar video for the SAM?

Resumen del video [00:00:00][^1^][1] - [00:37:03][^2^][2]: Este video proporciona una guía detallada sobre cómo entrenar un detector de objetos Yolov8 en un conjunto de datos personalizado. El proceso incluye la recolección y anotación de datos, estructuración de datos en el formato requerido por Yolov8, y finalmente, el entrenamiento del modelo. **Destacados**: + [00:00:00][^3^][3] **Introducción al entrenamiento de Yolov8** * Presentación del proceso completo de entrenamiento * Importancia de la recolección de datos adecuados + [00:05:06][^4^][4] **Anotación de datos** * Uso de la herramienta de anotación CVAT * Proceso de etiquetado de imágenes con cajas delimitadoras + [00:19:54][^5^][5] **Estructuración de datos para Yolov8** * Formato específico requerido para el entrenamiento * Creación de directorios de imágenes y etiquetas + [00:30:03][^6^][6] **Entrenamiento del modelo Yolov8** * Uso del repositorio oficial de Yolov8 * Métodos para entrenar el modelo en un entorno local o en Google Colab + [00:37:12][^3^][3] **Configuración inicial** * Establecimiento del directorio raíz y especificación de datos de entrenamiento y validación * Uso de los mismos datos para simplificar el tutorial + [00:38:10][^4^][4] **Entrenamiento en Python** * Ejecución del entrenamiento con Yolov8 para un solo epoch como demostración * Observación del proceso de carga de datos y entrenamiento + [00:43:03][^5^][5] **Entrenamiento en Google Colab** * Creación de un cuaderno en Google Colab y montaje de Google Drive * Instalación de la biblioteca ultralytics y configuración del entrenamiento + [00:50:06][^6^][6] **Evaluación del modelo** * Revisión de los resultados del entrenamiento y análisis de la pérdida * Pruebas prácticas con videos de alpacas para evaluar la precisión del modelo

So what is actually role of machine learning here, i don’t get it. In the other hand is only frames/videos where person is being identified on the camera stored in the folder you showed at the end, and by the way you didn’t show you get any notification that intruder entered the “stream” ?

I installed ultralytics in google colab but it is showing No module named 'ultralytics'. what is the solution ? I am Using AMD processor and graphics.

can anyone tell me who to test image on this?

Hello Felipe, super good video, I have some doubts about something that is wrong in the video of license plate detection, I wrote to you by email, but I also write here, everything works for me but the detection when the video comes out "out", what do you recommend I check? Thank you

Hello Felipe, super good video, I have some doubts about something that is wrong, I wrote to you by email, but I also write here, everything works for me but the detection when the video comes out "out", what do you recommend I check? Thank you

does it only recognise A B and L? or all the other letter?

Even after ~ one year this video is still my reference to tackle pose estimate workflow !

hi, is the csv still available? It seems not

Can we get the prediction code ? Thanks in advance!!

Greetings, Felipe! I like to ask for a guidance, if I may. I have a basic Python coding skills. I expect to learn the fundamentals of computer vision / image processing - thanks to you excellent videos! What sparked my interest in computer vision is this: I have a couple of “talk show” old videos that I would like to upscale 2x, not into 4k. Well, the first thing that I realized is that one needs to decompose a video into separate frames, i.e., images and then work with them. Ok. Then I tried some images upscaler on Colab. Results were mediocre. I felt that I need to improve something, but I did not even know where to start or what I can do. What am I thinking of now: I need to decompose the video into frames. It would be about 15_000 frames for 10 min video. Than I need to remove all images with advertisements, since I do not need them. This needs to be done programmatically, because of the number of images. Then I am thinking of cropping images: there is a lot of studio background, with the TV anchor and guests talking. All this background is useless, but the “upscaler” would waste time, trying to process it. It also needs to be done programmatically, but I do not have a slightest idea on how to approach it. I would appreciate if you could tell me if it is possible to do what I am thinking of. Which libraries do I need to use? OpenCV? Scikit-Image? To be honest, I do not need a complete solution, I would appreciate some directions -- i.e. where to begin and how to progress. Thank you!

Cezar?????

How do I know this video is not generated by another generative AI model that's competing with Devin AI 🤔

Hello, how would I take the results of a training (the weights) of the model and then train it again for a certain amount of epoch? I like to train 100 epochs at a time in case my computer shuts down and I lose progress, but I'd like to be able to retrain the same model instead of constantly starting from scratch.

How to add label 0 0 0 for the point which is not vissible in cvat0

Hello sir, just watched your video and it is great in case of a simple query let us take training should we include images which doesnt have ducks also? or is it fine that we use all images with ducks for training which is best for fine tuning the model to detect ducks in the images. In simple words for purpose of training should dataset contain all imgaes with ducks in it or a mixture of images with and without ducks.

Hello, YOLO states on its website that v8 is anchor free. However, in this application, we specify the ground truth bounding box to the system. What exactly does the anchor free mean here?

can i make understand the basic need and make a model just by watching this single video ? or do I have to watch the whole playlist ?

sir i have trained with 20 photos of monkey but its not detecting the of trained monkey also...why?

great work bro👍

🎯 Key points for quick navigation: 00:00 *🔍 Introduction to final year project on face recognition and automatic attendance management system using Python* 00:29 *🤖 Project involves machine learning divided into 3 parts: generator set, trend classifier, details of predefined samples* 01:24 *🛠️ Setting up a login page for the project with options for registration and user login* 02:20 *💬 Asking viewers to like the video and subscribe to the channel for motivation and future Python projects* 03:42 *💡 Demonstrating student details section and creation of an attendance management system, complete with buttons for various functions* 05:32 *📝 Inputting student details like name, gender, DOB, email, phone number, address in the system.* 06:31 *🛡️ Saving student data in the database after entering all required information.* 07:11 *💼 Selecting a photo sample and saving it in the database for each student.* 09:02 *🚀 Training the system with collected data files for face recognition.* 10:15 *💡 Using face detection features to capture student details and validate information.* 11:37 *📂 Saving data, exporting data, and updating files can be done in Python projects.* 12:05 *🔄 Updating details such as names, departments, and timings can be managed in the project.* 13:16 *📊 Excel files can be used to store and view project data, showcasing attendance management system capabilities.* 14:24 *✏️ Developing an automatic attendance management system using face recognition in Python.* 16:27 *📁 Setting up folders and organizing files in Visual Studio Code for a face recognition project.* 17:21 *🖱️ Click on "New File" to start a Python project and write the file name* 17:35 *🛠️ Start by importing needed modules in the Python file* 18:04 *📦 Python Tkinter is powerful for creating graphical applications easily* 18:27 *🛒 Different ways to import modules in Python* 19:14 *🔧 Check Python version and install required packages* 19:58 *🌟 Setting up geometry in Visual Studio Code for project development* 21:05 *🛠 Define construction and use self to import modules* 22:23 *🔲 Set dimensions for window placement for project GUI* [23:46] 🛠️ Using toolkit to call the route in the code [24:13] 📝 Writing classes and connecting them to the root [25:06] 📂 Adding and deleting images in the project [26:57] 🖼 Setting image properties like height and width [28:27] 📄 Setting labels and levels for images [29:43] 💡 Suggesting next steps in the project 30:39 *🔍 Image tweet and height can be set separately by copying and pasting values.* 31:49 *📷 Changing image names for organizing and managing image data.* 34:57 *🖼️ Setting up labels and names for images to maintain data clarity and organization.* 36:44 *💡 Images can be arranged and sorted based on specific criteria for better data management.* 37:10 *🔍 Images need to be adjusted for height and control using CSS.* 37:24 *📐 Titles need to be placed correctly above images for proper alignment.* 38:03 *🖊️ Title text and formatting for images need to be specified.* 39:00 *🖥️ Choosing font styles and sizes for text elements.* 40:05 *🎨 Setting background colors for image elements.* 42:49 *🖲️ Creating buttons from image elements for the user interface.* 43:43 *🖱️ Click on different buttons in the video interface to perform specific actions.* 45:17 *🎨 Customize the appearance of buttons by changing text, color, and position.* 47:26 *💻 Utilize text components to display information like student details and phone numbers.* [50:25] 🖥️ Changing the image name and file number is important before proceeding with any further tasks. [50:51] 🔄 Running and checking controls on the images to ensure proper modifications. [51:31] 🔧 Adding a help desk control for assistance during the image editing process. [53:00] 🎨 Utilizing controls for color adjustments and ensuring proper button configurations. [56:49] 💻 Organizing and managing image changes systematically for an efficient workflow. 57:43 *🔍 The process of training image data and copying it for face recognition is shown.* 58:34 *📸 Images can be pasted and suitable parameters can be set for developers during the development process.* 59:02 *🛠️ An 'OK' button for grouping images together is demonstrated in the interface design.* Made with HARPA AI

Thanks bro 🙏🏼

This is one of the best videos in this topic. But I want to know how I can get your pretrained model for license plate(license-plate-detector.pt)

How can I use laptop camera or any other in sense to test the results instead of videos. Pls advice

Thank you for your explanation, all the topics were clear, I followed and tried all the codes with my own images and videos. Only 1 video wasn't being read by the program for the face anonymization project. Maybe the quality of the video or the number of frames changed but I tried and couldn't make it.

amazing

Thanks a lot!! big thanks for teaching how to do it on a local ide

i wanna do this for s custom dataset and i not really sure how many pcitures do i need and how many epochs should i run? What is the standard ratio for it?

How can I get your pr-trained model which you used in this tutorial?

can a webcam be linked with the system?

very very very very very very very very very importance

model p file is missed on the folder

Hello guys, there is a BIG MISTAKE IN VIDEO - this guy made incorect link to the yaml file. here is the correct linking an yaml: results = model.train(data=os.path.join(ROOT_DIR, "/content/gdrive/My Drive/Datadata/config.yaml"), epochs=20) instead of linking like he - without writing a directory to yaml file, typing only the name of yaml.