Sign language detection with Python and Scikit Learn | Landmark detection | Computer vision tutorial
In this tutorial we are detecting hand signs with Python, Mediapipe, Opencv and Scikit Learn!
0:00 Intro
1:35 Data collection
4:55 This is the most important thing
11:31 Data processing
27:52 Train model
41:02 Test model
Code: github.com/computervisioneng/...
#computervision #signlanguagedetection #objectdetection #scikitlearn #python #opencv #mediapipe #landmarkdetection
Пікірлер: 366
Did you enjoy this video? Try my premium courses! 😃🙌😊 ● End-To-End Computer Vision: Build and Deploy a Video Summarization API bit.ly/3tyQX0M ● Hands-On Computer Vision in the Cloud: Building an AWS-based Real Time Number Plate Recognition System bit.ly/3RXrE1Y ● Machine Learning Entrepreneur: How to start your entrepreneurial journey as a freelancer and content creator bit.ly/4bFLeaC All my premium courses are available to the Computer Vision Experts in my Patreon. 😉 www.patreon.com/ComputerVisionEngineer
Thanks a lot! I really appreciate keeping this under an hour as well :))
Having trouble with my ML project now, but so happy to find your video. Thanks for all the work!!
Hello from Mexico! I love your job, I did each step in the same way as you, and I had no difficulties, I really feel very grateful for the time you spent teaching us. Congratulations teacher! 👨🏫
@ComputerVisionEngineer
10 ай бұрын
Thank you! So glad you enjoy the content! 😃🙌
@ITRAiswaryaS
2 ай бұрын
Could you tell me the installation process
great tutorial on how to organize the project into separate steps!
@ComputerVisionEngineer
Жыл бұрын
Good organization is the key to a successful project I am happy you enjoyed the video! 😄🙌
srsly like the best video, now i can train my custom hand gestures etc. even, thank youu❤❤
Thank you so much, sir for this wonderful project. I've completed my term project easily with the help of your video. Loved how we can create our own data instead of getting it from somewhere else.
@malesaketh8952
19 күн бұрын
Can u pls help me out? Please
Sir!! You have my respect I have really learned lots of things in your whole video . Just keep making this ML/DL Project videos , that you have done like implementing from scratch any exciting ML/DL project. Just Keep Going Sir!!! Thankyou So much!!✨✨✨✨✨✨❤❤❤❤❤❤
@ComputerVisionEngineer
2 ай бұрын
Thank you for your support! 😃🙌💪
very awesome tutorial with brilliant idea and conceptualization. Thanks a lost Felipe!
@ComputerVisionEngineer
2 ай бұрын
Thank you for your support! Glad you enjoyed it! 😃🙌
Really Thank you sir. Great Project you helped me a lot to learn many things. After multiple errors solving finally i succeeded in making full project.
@ComputerVisionEngineer
2 ай бұрын
Glad the content is helpful! 😃🙌
i love all that, you are very clearly and simply 😍😍
@ComputerVisionEngineer
9 ай бұрын
Thank you! Glad you enjoyed it! 😃💪
Thank you sir for this video
Hi! Great tutorial thank you. I have a question: does this program have data augmentation? and did u calculate the sensibility and accuracy of the program?
hehe subscribed, tysm for this it was very helpful
Great content, thank you so much.
@ComputerVisionEngineer
9 ай бұрын
You are welcome!! 😃
Thanks a lot bro, I watched many videos and i wasted a lot of time and finally found your video and done my project.
@ComputerVisionEngineer
5 ай бұрын
You are welcome! Glad it was helpful! 😃
@RohanVector
5 ай бұрын
Please send your github link please
@RohanVector
5 ай бұрын
I got lot of error bro please please please please
For all who are getting errors like "inhomogeneous shapes" while training on big datasets take into account that the MP Hands processing not always return 42 features (sometimes it just doesn't predict the coordinates well enough). To avoid this situations always check the length of every array. You must have the same amount of images and labels, and the labels (landmark coordinates) should have the same shapes. Just remove the samples that doesn't return all the landmarks or doesn't work well with the Mediapipe hands solution, to ensure all the data has the same shape and to avoid these numpy errors (and bad models).
@RAHUL-dt5xm
2 ай бұрын
can you help me. when I trained only one gesture nothing else, but the system detects untrained gestures as the trained gesture why? any idea
@user-qm4oc8nb8e
2 ай бұрын
can you please share the changed code
@mohamedlhachimi2933
Ай бұрын
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)
hello from Nigeria i must say thanks for this video it was short, precise and educative yes, i had some errors which i was able to handle due to my past knowledge on Deep Learning. And for those that had issues with the disparity in the length of the data, you can always pad to its maximum length currently, i have a model that can identify 26 classes correctly and i will definitely increase the classes. i made each classes to have 700 images under different lighting condition thanks for all you do.
@ijaspr5486
5 ай бұрын
bro can you send me the file for your project
@e2mnaturals442
5 ай бұрын
@@ijaspr5486 like the whole file?
@rarir0012
2 ай бұрын
Could you share your GitHub link of your project?
@user-qm4oc8nb8e
Ай бұрын
@@e2mnaturals442 yes like github code or i give you my social media id
@TheDreamsandTears
20 күн бұрын
can you share your code? I'm having somre errors, while I try do identify the letters. Also, in your code, could you do with signs with both hands and with movements? @e2mnaturals442
another great project
@ComputerVisionEngineer
Жыл бұрын
Thank you, Arif! I am happy you enjoyed it. 😃🙌
Great Video
Thank you, very clear what was taught. I want to ask what if the dataset from a public video had the initial and final movements? whether the start and end frames go into training . and using deep learning?
thank you my teacher, great a video , i tried it myself, I did it :)
@ComputerVisionEngineer
8 ай бұрын
You are welcome! 😃 Glad you enjoyed it!! 🙂🙌
life saver.
For those who faces the error where it can't convert the 'data' values from dictionary data_dict, just make sure that in photo samples you are giving the full hand because if not, there will be inconsistent data and the lists will not have the same lenght inside the data_dict['data']. Do again the photos retrieve part and all should be fine
@artiste9357
5 ай бұрын
Thanks a lot!! How did you notice that this was the issue?
@saivaraprasadmandala8558
4 ай бұрын
thanks a lot bro!!!
Hello, I have watched your video and found it very informative. However, I was wondering if you could make a video for recognizing different characters for a sequence of movements, for example, the letter "J" or "Z." Thank you for your video.
@ComputerVisionEngineer
Жыл бұрын
I will try to. 🙌
sir , the projects get closed if more hands are placed in the real-time video , i know that randomforest classifier uses only certain features , is there a way so that the program doesnt close if more hands are in the video
Thanks a lot! I really appreciate keeping this under an hour as well :)) We are trying to implement this model in Flutter to develop a mobile app. How can we create Flutter integration ?
I have trained my model using only numbers' data. It is working but the problem is it is only showing the numbers 9 or 1 in the frame. Do you think it's because of unclear data or problem in the training model. BTW great tutorial 👍
Thanks man
Thank you so much it's helpful for me 😊
@ComputerVisionEngineer
7 ай бұрын
Glad to hear it is helpful! 😃🙌
@RohanVector
5 ай бұрын
size.width>0 && size.height>0 in function 'cv::imshow' error sir
thanks
great tutorial so helpful for my pfe project i actually have to do hand recognition identification biometric only but the hand contour you explained so well the part "this is the most important thing" and I really need help when it comes to the approach of how i can solve this if it? is possible for you to help me by doing a video of it ?cause its the first time for me working with python i usually work with Matlab. thank you again for this video
@ComputerVisionEngineer
Жыл бұрын
Hey Hayat, I am glad you found it helpful! 😄 Do you mean making a video about how to be strategic when starting a project and choose the most promising approach? Sure, I can do a video about problem solving strategies! 😃🙌
@luongtranle2979
Жыл бұрын
Do you have file word report ?
Thanks for your good tutorial How to act for the rest of the letters?
I have just subscribed, Currently working on a similar project, fingers crossed I'm at a right place..😂
@ComputerVisionEngineer
Жыл бұрын
🤞😀 Good luck with your project, Martin! 🙌
@martinsilungwe2725
Жыл бұрын
@@ComputerVisionEngineer Sir i have an error "ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2. ", what can be the problem, im trying to classfy all the alphabet letters, your help will be highly appreciated.
Really great video tutorial! Why did you choose scikt learn and not Yolo? How many changes would you have to make to use Yolo?
@ComputerVisionEngineer
8 ай бұрын
Do you mean using Yolo for object detection instead of mediapipe + Scikit learn? It can be done. You just need to train it. I did it with mediapipe + Scikit learn only for simplicity, and I think it also results in a more robust classifier. 🙌
Thank you for the video, can you also make a video on sign language recognition on a video dataset (Word level american sign language dataset).
@ComputerVisionEngineer
Жыл бұрын
You are welcome! I will try to make a video about it. 🙌
Hii!! I loved your video. I learned a lot. I just have one question, if at the end I want to form a sentence and print it, how can I save each character on the screen to have a full sentence at the end?
@TheDreamsandTears
20 күн бұрын
Hi, did you get it?
Hlo Sir, very nice video.... I also want to make a similar project ... But there will a bit difference.. I want to generate the entire subtitle for people who can't speak using their hand gestures during video conferencing in real time. Can you please guide me with the same ... Bcoz I completely a beginner. Your help will be appreciated. Thanks in advance. 😀
@ComputerVisionEngineer
Жыл бұрын
Hey Sourabh, it sounds like a complex and very cool project! I would start by saving all the symbols you detect, its confidence score, and the duration of time you detect them so you can analyze this info later on. This is going to help you to understand the problem a little better and also it is going to help you to define rules in order to achieve your goal. 😃💪
@Abhaykumar-bu7ei
8 ай бұрын
Hi Sourabh were you able to make it if yes could you please share some update or code for the same
I checked the github repo and there are some changes compared to the video. Why are you substracting the min of x_ from x (data_aux.append(x - min(x_))), also for y ? Why is it necessary to do that instead of just append x the way it is to the array. I saw u did that in the data processing and also in the model testing. Thanks a lot!
@ComputerVisionEngineer
Жыл бұрын
Hey George! Yeah, I sent that change in a new commit. It makes the solution more robust, you could think about it as a way of 'normalization'. This makes the classifier learn better than the (x, y) position of each landmark is not that important, the distance of each landmark to each other landmark is what matters most! 😃💪
@georgevalentin9483
Жыл бұрын
@@ComputerVisionEngineer Thanks a lot for the answer! I thought it has something to do with the mediapipe library and is a must, but it actually makes sense to be some kind of normalization. Thanks for you time!
I am getting plots for every data set size which i have taken is it fine bcs i have plt.savefig function, annotated it so that the plt for every dataset size is saved in main data directory
Hello , great tutorial 😀can this same approach be applied for british sign language because that uses both hands to make gestures , also can this be deployed in the real world and used at production level ?
@ComputerVisionEngineer
8 ай бұрын
You would need to make some edits in order to use it with both hands but I guess it would work, yes. Regarding the performance, yeah you could train it and improve it so it can be used at a production level. 🙌
@MrFurious0007
8 ай бұрын
thanks @@ComputerVisionEngineer 😁i'll try and see if it works out
@MrFurious0007
8 ай бұрын
Hey @@ComputerVisionEngineer , its not working efficiently for the british sign lang , maybe because it uses both hands , do you have any suggestions on how i can build up my project , it'll be a huge help , thanks
hello Sir, I follow your video for learning about computer vision . So I have a trouble with "DATA_DIR = './data'" , Is this file need to import from somewhere or should we need to prepare them? Can you help me to solve this?
@peterbarasa9190
8 ай бұрын
am also thinking the same. The images seem no to be there
I am new to AI. I just want to know are we using Natural Language, Machine Learning and computer vision.
why do you use and random forest classifier algorithm? maybe it is better for it? could i try with a pretrained model to get better results?
@ComputerVisionEngineer
Жыл бұрын
No particular reason why I used a Random Forest, I think pretty much any other classifier would have a similar performance in this case.
@CanalIFES
Жыл бұрын
@@ComputerVisionEngineer Thanks felipe!!
hi I am a 15 year old and i want to do this for my school tech convention. What program are you using to code this
Just wanted to tell you that your project is very famous in SMIT 😊
@ComputerVisionEngineer
Жыл бұрын
😃 That is soooo cool! I am happy to help you guys. 😊🙌
@martinsilungwe2725
Жыл бұрын
Have you manage to Train the model with all alphabet letters
can we make this project with pose detection models like openpose or deeppose? and what is the difference
Hello, I have watched your video and found it very informative. However, I was wondering what is the limitation of this project?
@ComputerVisionEngineer
11 ай бұрын
Hey, limitation in terms of possible symbols? I would say any static symbol made with only one hand.
great project! may i ask what algorithm is used in your sign language?
@ComputerVisionEngineer
Жыл бұрын
Hey, thank you! I am using mediapipe as a hand detector and landmark detector and a Random Forest classifier as sign classifier. 🙌
Hello while executing your codes when i was keeping the number of objects grater than 4 thn trainclassifier was unable to generate model.p file in my device can you help me out to solve this issue
The camera crashes when I show more than one hand. Can you tell me how it can be fixed?
I have tried it with arabic Sign language,and it did not working correctly, I get one letter almost every time and it's wrong letter, any ideas that can help me train the model. I got the dataset from kaggle.
Some hand sign have two hand ,than what we can do that situation ?
Hi, while going through this code i'm getting model_dict = pickle.load(open('./model.p', 'rb')) FileNotFoundError: [Errno 2] No such file or directory: './model.p' and I didn't find any model.p file in your repository
@ComputerVisionEngineer
Жыл бұрын
Hey, you can create the model yourself following the steps I describe in the video. 😃🙌
Sir only 9 character can be trained plz help me to train 26 character
How can I get accuracy for the letters predicted? Basically I want live accuracy for the letters that are predicted , since if you show any random hand gesture it will always predict some random letter, so it will be much better if you could also show live accuracy .Is it possible can u guide me a little bit through this?
@ComputerVisionEngineer
Жыл бұрын
Try using the method 'predict_proba' instead of 'predict'. You wil get a probability vector for all the classes. Taking the largest number will give you the confidence value you are looking for. 💪💪
@prathamupadhyay1265
Жыл бұрын
@@ComputerVisionEngineer Thanks a lot you are amazing !!! 😃
@yashanchule9641
Жыл бұрын
@@prathamupadhyay1265 bhai if u dont mind kya app apke code ki zip file mujhe share kar skte hai, coz im getting many errors and i have tried many steps but kuch ho nahi raha hai. PLZ!!!!!!
@yashanchule9641
Жыл бұрын
plz bhai
@054_vishwadhimar4
11 ай бұрын
@@yashanchule9641 GitHub link is there..or have you tried that too?!
Hi... Since many signs involve some type of movement, I wonder if videos could be used in place of pictures. I hope you can reply to me because your video is very helpful for us. Thanks in advance.
@ComputerVisionEngineer
7 ай бұрын
Yes, you could try with video classification. 🙌
@VnZR_
7 күн бұрын
@@ComputerVisionEngineer how to insert video type in pycharm?
@VnZR_
7 күн бұрын
I hope you can help us..thank you
@VnZR_
7 күн бұрын
Is there a front - end that can connect in pycharm?
why does it close when you put another hand?
Great tutorial! Can you tell me how can I do this for Indian Sign Language which uses 2 hands?
@ComputerVisionEngineer
Жыл бұрын
I am looking at the Indian sign language alphabet and I see some characters are done with 2 hands and others with 1 hand. In order to do something based on landmarks as we did on this video you would have to train 2 classifiers, one of them taking as input the landmarks of one hand only (as we did on the video) and the other classifier taking as input the landmarks of both hands. Then some logic to apply one classifier or the other one depending on how many hands appear on the frame. Or, you can just follow a different approach and train an image classifier taking the crop of the hand/s. 💪🙌
@v5j7bxb
2 ай бұрын
Hi ! Have you completed working on this project? Did it worked ?
The app crashes when using both hands. How can I fix this?
Hello sir, I got a one problem. I made the same with you and my code is worked but it only showed at least 5 mins for capturing then the camera will shutdown automatically and got some errors. :((((
First of all i want to thank you for this tutorial. I want actually to make a program for sign language but i am confused about the Dataset and how to process the Data which i will maybe get as Videos or Images. can you maybe give me some advice.
@ComputerVisionEngineer
Жыл бұрын
Sure. Do you think you can take an approach as I do in the video?
Hello, i was adding new alphabets to the dataset and got this error , unable to solve : " File "D:\Major project\.Major Project\code\train_classifier.py", line 11, in data = np.asarray(data_dict['data']) ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (400,) + inhomogeneous part."
@tvrtkokaurinovic7370
5 ай бұрын
did you fix this error?
did you use any particular research paper for this project. i have to make a report for my project and cite a reference and it would help if you can tell me which one you used or which one will be the most similar to this project.
@ComputerVisionEngineer
11 ай бұрын
Hey, I didn't use any research paper for this project. 🙌
@054_vishwadhimar4
11 ай бұрын
@@ComputerVisionEngineer alright then...but do you have any idea which one would be similar or near to this?
@aakritityagi7203
10 ай бұрын
@@054_vishwadhimar4 hi, did you get the research paper?
@054_vishwadhimar4
10 ай бұрын
@@aakritityagi7203 no I did not actually... thankfully my mentor did not force me to find one and accepted multiple youtube.videos as references
Can the project created by exported to an .exe? Im worried because of the pickle file.
Am from Ghana
does it only recognise A B and L? or all the other letter?
Hi sir, Thanks for your tutorial. Yet, I a problem in locating the file(./data), and received an error message of [Errno 20] Not a directory: './data/.DS_Store'. while using "create_dataset.py". Currently all file are put in desktop, do you know why? (I m using MacBook)
@gXLg
8 ай бұрын
The thing about Apple is that MacOS often puts a file called ".DS_Store" in the directory which stores some information. In your code where you iterate over folders, compare the name with ".DS_Store" and simply skip it
hey its does not work for more than 5 sign can show value error about the shape can you please fix it
Who can I add more sign because it's getting error when I try to add more signs
If you train it in a specific place ex: your bedroom would this work like with the background of your kitchen or different place?
@ComputerVisionEngineer
6 ай бұрын
Yes, by the way we are doing it in this tutorial, it should work if you change the background. 🙌
@mohamedlhachimi2933
Ай бұрын
@@ComputerVisionEngineer 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)
can i ask how can you moved this into mobile / android studio
Is there a way that we can contact you apart, from the comments section, because I really need your help on the splitting of the datasets, I have followed every step in the tutorial but to no avail, it it not working for me.... The part were you are splitting the data to training set and test set, to be specific
@ComputerVisionEngineer
Жыл бұрын
You may try to contact me in our discord.
Cant we get any tflite file from this model ?
amazing project, i want to do it but with raspberry pi, some suggestion?
@ComputerVisionEngineer
10 ай бұрын
Thank you! I haven't tried to do it an edge device, I don't have any suggestions. 🙌
which version of python is to be used?
how to make this project on web based like on react or flask
May I ask you the report about this project ?
EVERYTHING IS WORKING FINE, EXCEPT FOR THE FACT THAT THE MY FINAL PROGRAM IS UNABLE TO RECOGNIZE ANY SIGN. IT JUST GIVE EVERY SIGN THE SAME LABEL WHATEVER THERE IS IN THE INDEX 0 OF THE LABEL LIST. I don't understand why its not working???
@tvrtkokaurinovic7370
5 ай бұрын
same here, did you fix it?
@ComputerVisionEngineer ValueError: X has 84 features, but RandomForestClassifier is expecting 42 features as input..I am getting this error when i run the inference_clasifier.py model...What change should i make in the code.....
@shwetaevangeline
2 ай бұрын
If you're getting this, that means you're showing something else that isn't in the data. Only show what you've captured. Or else simply increase number of classes and take different pictures from different angles.
@mohamedlhachimi2933
Ай бұрын
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)
@luciferani8279
16 күн бұрын
Do not give 2 hands at the same on your camera
when you crop the image to just show the sign does that mean anyone can sign the alphabet and it will show what sign they are doing?
@ComputerVisionEngineer
9 ай бұрын
Once the model is trained, anyone can sign the alphabet and it will show what sign they are doing.
How will this accept video feed from a phone ?
Very cool, i have a question. How can i test de accuracy of the detection?
@ComputerVisionEngineer
Жыл бұрын
Do you mean the accuracy of the hand detection?
@ocelottes
Жыл бұрын
@@ComputerVisionEngineer yes
@ComputerVisionEngineer
Жыл бұрын
@@ocelottes it is mediapipe hand detection, if you want to test it's accuracy you would need to take another hand detector to compare mediapipe detections against
Hi, I am getting an error that ./data/.DS_Store is not a directory and is not found.
@ComputerVisionEngineer
Жыл бұрын
Hey, what file / line triggers this error?
hello sir i am getting this error ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2. x_train, x_test, y_train, y_test = train_test_split(data, labels, test_size=0.2, shuffle=True, stratify=labels) i observe that if i remove stratify i donot get error but after that i get 0.0% of samples were classified correctly !
@ComputerVisionEngineer
Жыл бұрын
Hey, how many different symbols are you trying to classify? How did you collect the data for each symbol?
@texsesyt2902
Жыл бұрын
@@ComputerVisionEngineer I change number_of_classes to 5 and i collect data through opencv by capturing images(by using the method describe in this video) Note: python version 3.11.2
@texsesyt2902
Жыл бұрын
total 5 symbols each got 0 to 99 images
@ComputerVisionEngineer
Жыл бұрын
There is a probably a bug with the data. Take a look at 'labels', how many elements are there for the different classes? Is it an array of integers or is it other data type?
@texsesyt2902
Жыл бұрын
@@ComputerVisionEngineer Now i am getting this error when i make 25 classes(for each alphabet). data = np.asarray(data_dict['data']) ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2471,) + inhomogeneous part.
Hi, I wondered how this would work if you had text files for each image, which held the class information and the bounding box coordinates (top left and bottom right), kinda like the YOLO format txt files?
@ComputerVisionEngineer
Жыл бұрын
Hey, yeah I think that would work for a video for example, where you have already computed the object detection and classification for that video beforehand. If you are detecting objects live, in a webcam, you would need an object detector and an image classifier. I don't think you could load the annotations from a txt file in yolo fomat because you are capturing the data live. 💪💪
@daisybristow7036
Жыл бұрын
@@ComputerVisionEngineer Thank you for your response! I may have made my last comment a bit confusing. Basically, I am trying to adapt this code to eliminate the media pipe elements. I already have a dataset of still images and corresponding text files holding the bounding box coordinates. I am using scikit to train still. But I keep getting errors when i run the training script. Your help would be much appreciated
@ComputerVisionEngineer
Жыл бұрын
@daisybristow7036 oh I see, yes sure you could use something like yolov8 and replace both mediapipe and Scikit learn. Once you collected the data, you can just train yolov8 following the steps in my video on how to train yolov8 on a custom dataset. Then, for inference, take a look at my video on object detection + tracking. 🙌
@daisybristow7036
Жыл бұрын
@@ComputerVisionEngineer This would be an optimal solution, however I am required to use scikit to train not yolo. Would it be ok if I could explain it further beyond the comment section of this video? 😵💫
@ComputerVisionEngineer
Жыл бұрын
@@daisybristow7036 you could use both Scikit learn and yolov8, so you use Scikit learn to validate the class you got with yolov8, that would be a super robust solution! 😃 I may create a discord or something similar later on, for now it is only the comments section of my videos.
Hello, thank u for tutorial, that was amazing but i have an error when y run the classifier: ValueError: X has 42 features, but RandomForestClassifier is expecting 84 features as input. how can i fix that error?
@uzairkabeer
11 ай бұрын
@michaenrangelgiraldo5428 Okay so, I'm assuming that you are getting this error when predicting for that I just put an if condition like: if (len(data_aux) != 84) And with in that if condition I predict the values. I myself don't know whats causing this error but my assumption is it has something to do with the both left and right hand landmarks (42+42=84). Nevertheless, this solves this issue hope it will help you too.
@alexday4949
11 ай бұрын
Can you try this code: desired_length = 4200 # Pad data_aux with zeros to achieve the desired length while len(data_aux) data_aux.extend([0.0, 0.0]) # Truncate data_aux if it exceeds the desired length data_aux = data_aux[:desired_length]
@mohamedlhachimi2933
Ай бұрын
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)
doesnt this work when you use labeled dataset
Sir kindly help me with this error . . ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2.
@tihbohsyednap8644
Жыл бұрын
Sir kindly help me with this error. I am working on this project as my final year project and I have to extend it as my major project work.
@mohamedlhachimi2933
Ай бұрын
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)
The mediapipe library is giving error in installation what should I do?
@fruitpnchsmuraiG
2 ай бұрын
did you figure it out?
model p file is missed on the folder
chilean spanish?? good tutorial
@ComputerVisionEngineer
2 ай бұрын
Hi, thank you! My home country is Uruguay. 🙌
Hello sir, Kindly solve this error for me ----> ValueError: With n_samples=1, test_size=0.2 and train_size=0.8, the resulting train set will be empty. Adjust any of the aforementioned parameters.
@ComputerVisionEngineer
Жыл бұрын
Hey, would you please copy paste the full description of the error you get?
it's showing the error: ValueError: setting an array element with a sequence. after loading the dictionary in the model.
@mohamedlhachimi2933
Ай бұрын
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)
Hello! I tried to do exactly what you did but using the 26 alphabets. I don't know where I went wrong but the data list when converted to an nparray is giving me this error: ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2581,) + inhomogeneous part. I have so many things but I am utterly stuck. Please do you have any idea on how I can fix this error.
@ComputerVisionEngineer
9 ай бұрын
Hey, not sure what could be going on, although it is always a good practice to take projects one step at the time. Try to do it with only 2 or 3 symbols and work your way up. It will make things easier to debug. 😃🙌
@user-mh6ek3hv3k
9 ай бұрын
@@ComputerVisionEngineer Thank you. I took your advice and was able to fix the problem by breaking it down. Turns out the data for 3 letters were not properly captured but I re captured them and the 26 letters are working perfectly!! Thank you.
@ComputerVisionEngineer
9 ай бұрын
@@user-mh6ek3hv3k Amazing! Happy to hear you solved the problem! 😃
@foru1854
8 ай бұрын
@@user-mh6ek3hv3k i am actually also facing the same error how can i identify which letter data is not captured correctly? pls can you tell me
@user-mh6ek3hv3k
8 ай бұрын
@@foru1854 What I did was start with the first letter (A) , did carried out all the steps and trained the model. When I saw it worked, I added the second letter and did the two; then the third and that gave me the error so I knew the third had a problem and recaptured. I followed on like that and when I add a new one and I get the error I will know that alphabet needs to be recaptured. Hope that helps
Sir please help............during training it shows value error..data = np.asarray(data_dict['data']) ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (199,) + inhomogeneous part......for 3 class
@SohamKaranjkar
6 ай бұрын
i got the same error, were you able to solve it?
@krzysztofgalek5276
5 ай бұрын
Did u solve it?
@e2mnaturals442
5 ай бұрын
i was able to sort it using padding if you want me to explain more, i will be glad to
@Elenas1178
4 ай бұрын
@@e2mnaturals442 please explain
Hello, first and formost . Thank you for helping me with this fun project! Second , ive stumbled in an error while typing "import matplotlib.pyplot as plt" as in Problems it says that "No module named 'pyplot' " Please help
@ComputerVisionEngineer
Жыл бұрын
Hey, have you installed the project requirements?
@tam1k.
Жыл бұрын
@@ComputerVisionEngineer yes, even the specific versions
i wnat to crete senetence ?what to do
What python version have you used in this project?
@ComputerVisionEngineer
8 ай бұрын
Python 3.7 if not mistaken
can we make an android app for this???