Thanks for this great tutorial. If I have a real-time traffic video feed coming in from a CCTV, how can I stream it on AWS?

argentina mentioned

Can cars and license plates be annotated in the same image and assigned different classes, or are the datasets for the car and license plate detection models distinct? I have a similar project in mind, but I'm not sure the correct way to annotate images to first detect objects of a class, then detect objects of a different class within the detected object. Any advice is appreciated!

val: WARNING ⚠ /content/gdrive/My Drive/computervision/data/images/val/20220304_100108.jpg: corrupt JPEG restored and saved (I am takin these warning massages for train and val. How can ı solve this?)

In parking classifier I use the same code as you but I am getting 100% accuracy, is that a problem, I thought I was supposed to get acc < 100%

File "D:\project\main.py", line 54, in <module> cv2.imshow('original_crop', license_plate_crop) File "D:\ project\.venv\main\lib\site-packages\ultralytics\utils\patches.py", line 56, in imshow _imshow(winname.encode("unicode_escape").decode(), mat) cv2.error: OpenCV(4.9.0) D:\a\opencv-python\opencv-python\opencv\modules\highgui\src\window.cpp:1272: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvShowImage' hello sir plz give this error solutions ....show error in 29:44

funny thing happened. I paid for your patreon to get the notebooks and suddenly the link to the notebooks does not work.... wtf

Nice tutorial. It's always fun learning with you. Can you create a video to fine tune SAM on custom dataset?

I cannot find which yolo has annotations for a dataset, there are so many versions.

hi, I have a question. if I divide the dataset into training and testing only, is it necessary to run the validation part? and if not, during inference how to find out the mAP? plis help me🙏

Hello, the test.py you are working is not same as in repository. I am facing error. Can you please guide?

great video! just wanna ask, how did you split your data into train and val? is it 70-30?

unfortunely there is an error on step pip install -r requirements.txt and is impossible to continue with the tutorial....

where will i get the images?

First of all, thank you very much for your wonderful work in sharing your knowledge... I confess that I'm a beginner and I've never programmed in my life, I'm suffering a lot, but I see that with each step I learn a little, I still have a lot of doubts, but that's ok, I'm absorbing the knowledge and who knows, I'll improve, but I'm extremely grateful, very thank you great master.

First of all, thank you for your generosity in sharing your knowledge. I discovered you recently while doing research on license plate recognition systems. Do you have an e-mail address? From turkey.

Great 🩵🙌🏻

sir can you help me to solve this problem INFO: Created TensorFlow Lite XNNPACK delegate for CPU. WARNING: All log messages before absl::InitializeLog() is called are written to STDERR W0000 00:00:1715595257.639723 5688 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors. W0000 00:00:1715595257.684985 5688 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.

Your videos are amazing! Clear explanations, easy to follow, and super helpful. Thanks for all you do! Can you please bring a video explaining Anomalib too?

will this work with the base free version available for aws?

Great video. Can I tag people with unique ids as well?

Amazing VIdeo. Gotta see if yolov8 holds up to my data though

Object detection or Semantic segment should i learn first

I tried to run this code in my system with a pretrained-model yolo model for license plate recognition but I'm having these issues 1) the results are not being written in the csv file 2) when showing the frames that the model is extracting are oddly tiny it would be helpful if someone can explain what is going on as I am confused regarding this

Me volví fan tuyo, qué capo, tus explicaciones son maravillosas. Gracias por todo tu trabajo, me inspiraste más a llevar mi carrera a otro nivel. Te saluda y agradece un Ingeniero Físico :D

How can I contact you? i'm ready to pay for your help

give me a idea,my project is face attendance sytem using face-api first thing the webcam starts face capture and then splited into frames ,frames can be converted into images, images converted into embeddings that can be stored in mongodb and then compare the embedding with the newly given image that also converted into embeddings that embeddings can compare with previous stored embeddings in mongodb give a correct image

i think guys to solve this problem we had to tell the collect data script to save just frames where he could detect our hands else we will store bad models that will ends with this getting errors like "inhomogeneous shapes" , i actually try to solved this problem by not moving my hand when collecting data and making my model else you can try this code to check your images that are stored This script will only print the paths of the images that are deleted due to no hands being detected. It won't display any image windows. ##########################################" import os import cv2 import mediapipe as mp def process_and_show(image_path, mp_drawing): mp_hands = mp.solutions.hands hands = mp_hands.Hands() # Read the image image = cv2.imread(image_path) image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) # Detect hands and landmarks results = hands.process(image_rgb) if not results.multi_hand_landmarks: print(f"Deleted image: {image_path}") # Delete the image with no hands detected os.remove(image_path) # Path to your data folder containing subfolders data_folder = "data" mp_drawing = mp.solutions.drawing_utils mp_drawing_styles = mp.solutions.drawing_styles # Iterate through subfolders for folder_name in os.listdir(data_folder): folder_path = os.path.join(data_folder, folder_name) if os.path.isdir(folder_path): print(f"Checking images in folder: {folder_name}") # Iterate through images in the folder for filename in os.listdir(folder_path): if filename.endswith(".jpg") or filename.endswith(".png"): image_path = os.path.join(folder_path, filename) process_and_show(image_path, mp_drawing)

HI, I have a project wherein, I have to segment multiple classes, how do i go about it? What changes do I need to make in the code?

Very helpful insights

Thank you a lot, I would like to know how to exploit the results of a trained model on unseen data.

Would this also apply to keypoint detection using YoloV8 please?

Where can I find the video of the parking lot you have used?

Hello, thank you so much for this video ! I trained my model, but the labels can't be found and I do not know why. The labels have the same names as the images, they are in .txt , yolo format and in the folder "labels". And I have used the ultimate path. Do you have any idea why ?

can i ask how can you moved this into mobile / android studio

Hi! Thanks for the video! I'm curious, is it possible to combine yolo for the detection of an object and a multimodal like LLaVA to have a description of the object?

hello sir!, Is it possible to train an easyOCR model to detect images based on my own dataset?

Hey very nice Video, i am very new to this topic. Where do you get the .txt files in the labels folder?

Thanks for the tutorial! In X-Ray tutorial if we increase an image size from 224x224 to 448x448 for example, will it increase the accuracy of the model?

how can i make it in real time, i mean no pre recorded video, real time video like stream ?

Will this work on a person?

Thank you for this video, I am currently working on my thesis and content like yours helps me understand topics more quickly. God bless you.

🦾🦾🦾🦾

Wonderful! I was wondering why prediction didn't work with your alpaca tutorial video. No I completely understood. I tested my scripts with only 56 images and did not get any prediction. I will increase the number of images! Bravo! I appreciate your work!!

Your videos are very helpful! Thank you so much! However I have a question, If i want to do a multiclass object detection, do i need separate training folders or do i just put every image with different classes in one folder?

@ComputerVisionEngineer thank you for this detailed video, much appreciated!

Anyone else encountering this error "Unable to locate package Nvidia-driver-450

Hey, thank you very much. this was helpful. But when it’s done training, in the detects folder, the images have no bounding boxes. Please advice

Wow. you are amazing bro. Thank you so much for teaching me this!!!