Text Detection using Neural Networks

Text Detection using Neural Networks | OPENCV Python

Рет қаралды 143,096

Murtaza's Workshop - Robotics and AI

4 жыл бұрын

In this video, we are going to learn how to detect text by creating a Convolution Neural Network to Classify digits from 0 to 9. We will write the Training code from scratch and go step by step to train about 10000 images of 10 different classes. Later we will create a testing script to use along with a webcam. I will be sharing all the details including the version of the packages and the parameters for the training
🚀🚀 My Urdu/Hindi AI KZfaq Channel 🚀🚀
/ @murtazahassan01
Code & Files:
coming soon
Premium Courses:
✔️ Computer Vision Game Development Course:
bit.ly/3ttLZ2s
✔️ Computer Vision with Arduino Course:
bit.ly/3wzLB4m
✔️ Advanced Drone Programming Course:
bit.ly/3qs3v5g
✔️ Learn to Build Computer Vision Mobile Apps:
bit.ly/3uioY1J
✔️ Jetson Nano Premium Course:
bit.ly/3L8uIlF
⚙️⚙️⚙️--My Gear - ⚙️⚙️⚙️
👉 Complete Gear 💈: www.computervision.zone/tech-...
👉 My PC Specs 🖥️: www.computervision.zone/tech-...
👉 My Video Shooting Gear📽️ : www.computervision.zone/tech-...
👉 My Laptops 💻: www.computervision.zone/tech-...
👉 Educational Products🧑‍🎓: www.computervision.zone/tech-...
👉 KZfaq Starter Kit 🔴: www.computervision.zone/tech-...
Follow Me:
TikTok: bit.ly/3Vo76OQ
Facebook Group: bit.ly/3irDcb7
Discord: bit.ly/3JvyxAM
Facebook Page: bit.ly/3IvpU7W
Instagram : bit.ly/3NdGME3
Website: bit.ly/3ICFTS0
Github: bit.ly/3woU6PS
#ComputerVision
#OpenCV
#CVZone

Пікірлер: 484

@gabrielprocopenco 4 жыл бұрын

Great tuorial and a big thank you for the versions for each library!

@moviescontroversy1927 3 жыл бұрын

kzfaq.info/get/bejne/l8CgY5iDy9C1oJc.html

@prantikbose2158 2 жыл бұрын

such a high quality content for free.... man u r doing a great job

@abdulwahabmalik852 4 жыл бұрын

Mashallah! and thank you for high quality content in the field of AI.

@murtazasworkshop 4 жыл бұрын

Glad you enjoy it!

@rakeshdhakshinamurthy7745 3 жыл бұрын

Great stufff...Keep doing your great work. You earned a sub today

@edSabio572 3 жыл бұрын

Dr. Murtaza, Thanks for a great tutorial!!!

@milindtandon3261 3 жыл бұрын

Thank You Sir, your way of teaching is superb 🤗🤗🤗

@vasylpavlus 3 жыл бұрын

Great chanel! Thank you! Question: what minimal hardware would you recommend for running all this OpenCV/TensorFlow tasks?

@engineeringprojectsece7305 4 жыл бұрын

Finally a full detailed vedio😍😍😍😍😍 ,,,thank you so much ,,, please brother upload vedio on open cv 🤩🤩🤩

@murtazasworkshop 4 жыл бұрын

You'r Welcome. I am working on the OpenCV course will share soon .

@murtazasworkshop 4 жыл бұрын

here is the complete opencv course kzfaq.info/get/bejne/jbeVorJosq-Ucqc.html

@hfe1833 3 жыл бұрын

One of the reason I like this channel is explanation in clear ,consider manner ,not so fast perfect for beginners like me

@murtazasworkshop 3 жыл бұрын

Glad to hear that!

@huzailmunir3097 3 жыл бұрын

@@murtazasworkshop can you share a download link to the number set here, i cant download it from your website

@sargamhemnani Жыл бұрын

@@huzailmunir3097 if you have the dataset link,could you please share

@syukrikoko5975 3 жыл бұрын

I really appreciate your works..

@TheOldNo07 3 жыл бұрын

Hello Murtaza, thank you for your great videos. Can you provide a source (video, website, paper,...) to understand your CNN-model in detail? I'm trying to understand your traffic sign recognition project in depth. Best regards :)

@shreyagoel8297 3 жыл бұрын

Thank you so much. It was very helpful.

@lamotesparadise4466 3 жыл бұрын

How do I get those images that you used? Great Videos!!!

@Maertaugh 3 жыл бұрын

You do a lot of great jobs ! One question : is it possible To run all that great job on a Android device like Phone ? How To do this ?

@sayatorazkulov 4 жыл бұрын

Tnx very much! Really appreciated your job!

@murtazasworkshop 4 жыл бұрын

Glad it helped!

@s.m.jabiralamshouccho6822 2 жыл бұрын

Thanks for the qualitiful content

@challenger5879 4 жыл бұрын

thanks for this tutorial you are the best :)

@murtazasworkshop 4 жыл бұрын

Thank you for you kind words

@programmingdigest7582 4 жыл бұрын

U r great sir thank you so much for detail tutorial❤️❤️

@murtazasworkshop 4 жыл бұрын

Most welcome 😊

@amansoni7373 3 жыл бұрын

@@murtazasworkshop i get an error at this ( img=img.reshape(1,32,32,1) ) before be send img to predection . Helf me sir

@CodingCircle 3 жыл бұрын

@@amansoni7373 use img = img[np.newaxis, :32, :32, np.newaxis] instead

@tyt3772 4 жыл бұрын

Thank you Murtaza. You are my superman.

@moviescontroversy1927 3 жыл бұрын

kzfaq.info/get/bejne/l8CgY5iDy9C1oJc.html

@deltaelectrocode4417 3 жыл бұрын

First I thank you for your great explanation. One thing I'm not clear that, why I should split the data into training, testing and validation? I see some people Split only in train and test and then evaluate the model with testing data. Hope you'll explain this sir.

@CodeDefender2 Жыл бұрын

Hi Murtaza! Thank you so much for the video. Is it possible for you to also provide any paper based on which you have done in this video? Much appreciated.

@leochang3915 4 жыл бұрын

so helpful!!! thx you guys

@murtazasworkshop 4 жыл бұрын

Happy to help!

@MrNadeem1984 2 жыл бұрын

Thank you very much for such high quality tutorial. How could I get the co-ordinates of detected text region and mark bounding box around that?

@ShovitBhari 2 жыл бұрын

Great Tutorial! Please add the link for the data.

@fusssgy8190 4 жыл бұрын

I am wondering where could I find those digit images? Thank you for a great tutorial.

@moviescontroversy1927 3 жыл бұрын

kzfaq.info/get/bejne/l8CgY5iDy9C1oJc.html

@jaumegasiamerce9285 4 жыл бұрын

Great video!

@murtazasworkshop 4 жыл бұрын

Thanks!

@RedBlood526 4 жыл бұрын

Hello Murtaza, thank you for these amazing courses. I have a question. I watched your Traffic Signs video also but there is one thing missed. Beside your dataset, how can i find dataset as (32,32)? Thus, i can create my own dataset. Just because i don't want all datasets i just want to parking signs, stop signs, right-left signs and go ahead only or if i want to create a new dataset (e.g. recognition birds) how can i create folder with 5000 images. Should i find them seperately on internet?

@abhinavmathur6072 3 жыл бұрын

Resize it as givin

@SivaShankarsss 3 жыл бұрын

Inputsize resize it

@radugabriel7131 4 жыл бұрын

Hello! This was a lovely tutorial and thanks for it. I have a question. I don’t understand why you have two of the exact convolution layers without an activation function between them. I mean you use “model.add((Conv2D(noOfFilters//2,sizeOFFilter2.....” two times. What is the functional scope of this, or do you have any link where i cand read some more about this? Thank you!

@murtazasworkshop 4 жыл бұрын

This is based on lenet architecture you can look that up.

@shehanjayaweera741 4 жыл бұрын

Very nice, useful video.. thank you..🎁🎁🎁 I like to implement this same project on raspberry pi, what are the special thing to do it.. And also can you please do a another video, on explain more about CNN..

@asifanowar423 4 жыл бұрын

hi there,thank you very msuch for such an amazing tutorial in details. I have a question. What should be the minimum system requirement for doing this project and how much time does it take to train the model?

@murtazasworkshop 4 жыл бұрын

Since its just using CPU a decent cpu with average ram should be enough. On my PC it took about 6 mins for each epoch

@deepakgowda89 4 жыл бұрын

@@murtazasworkshop set 'steps_per_epoch=200', it will be much faster. steps_per_epoch = (Total items) / Batch size = (10160) / 50 = 203

@donaldjump4527 2 жыл бұрын

wow thank you so much, it helps me so much for final year project. may I know that about this code can be use to recognize a word ?

@patrickpuentelml4958 4 жыл бұрын

Hi Murtza's Workshop congratulations for your job I'm a relly fan of your channel. I am working in my degree project, I am working in a bottle collector so The question is that: HOW CAN I DRAW A SQUARE AROUND THE RECOGNIZEZ OBJECT USING THE CNN PREDICTIONS ? IN OTHER WORDS I WANT TO HAVE A RESULT SIMILAR TO YOLO. PS: I understand all the job of the preproccessing of images and the use of Keras I have problems in the CV. Please I need your help

@manufg6366 3 жыл бұрын

If we had installed packages initially using pip command, then should we install them separately for each new project?

@dhivyasubburaman8828 3 жыл бұрын

Thank you so much for ur knowledge share ,.......really grateful to you ...is there any possibility to learn some projects on Natural language processing

@murtazasworkshop 3 жыл бұрын

Will upload soon

@catalinacatalina1474 2 жыл бұрын

Hello, you don't have this course on the website mentioned, is it there under other name . Thank you Dr Murtanza

@hanaealkaddouri3192 3 жыл бұрын

Thank you for the content, i'm just wondering about those digit images that you used, where i can find them ? cause i already check the link in the description but i didn't find anything, can you please help me ?

@abhishekchaudhari970 Жыл бұрын

Here drive.google.com/file/d/1cZr91zzHl93H1cbmIwx_7upfQPPMPi33/view

@TheOmoyoruba 3 жыл бұрын

Hi Murtaza, thanks for the tutorial. Is it possible to extend this to include handwritten texts? Do we need additional package?

@PodcastShortsReal 2 жыл бұрын

You would just need to add loads of images

@indrajeetsinghyadav876 2 жыл бұрын

Hi great tutorial. A small suggestion you could save the tensorflow nn model by model.save(). I got a question though. Is there a reason that you used one hot encoder? I prefer to use label encoder. Does it effect the accuracy in any way? Basically i already have a program where i have used mnsit dataset. so i was thinking to just append your data as well. So would the encoder effect in any way. Cause as far as I understood both do the same thing. Please do elaborate your answer.

@kyriosabbes3737 4 жыл бұрын

Hi friend, it's the best video ,it's contain all details ... , If u can add a video about YOLOv3 with details ❤️❤️❤️

@murtazasworkshop 4 жыл бұрын

Thanx, i will look into it.

@kyriosabbes3737 4 жыл бұрын

We are waiting 😉

@ozanerbasanful 3 жыл бұрын

Really glad for such perfect content and thank you. For including all characters (numbers+letters) how we can edit this code can you give us an advice? Thanks in advance.

@kzchannel9075 3 жыл бұрын

could you find answer?

@yasinact007 2 жыл бұрын

@@kzchannel9075 could you find answer? :)

@TheBanker93 3 жыл бұрын

Thanks a lot.

@abdulansari7673 4 жыл бұрын

Amazing Tutorial!!! I am not being able to install tensorflow, could you help me with that?

@murtazasworkshop 4 жыл бұрын

Check the version of the python and opencv . Make sure they are same as the video

@lizzzsmiling630 2 жыл бұрын

For those who has resize() problem, here is my solution:)) Probally it is because the .DS store file. Hope can help you. 1. insert 'print(y)' around line35 to print out the y value in your image folder. Check whether there is a .DS store file. 2. If have, delete the .DS store file using the terminal command: find . -name ".DS_Store" -delete

@augpie4249 3 жыл бұрын

Someone else got this warning too? My steps for epoch stop at ~136/2000 *WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches (in this case, 2000 batches). You may need to use the repeat() function when building your dataset*

@jirkafryjauf156 3 жыл бұрын

same problem here

@suriyakrishnan5177 3 жыл бұрын

I too got this error

@sterben04 3 жыл бұрын

me too. mine stops at 131/2000, and goes on for only 2 epochs.

@397sidhu 3 жыл бұрын

Maybe you are using a different version of the package that was shown at the beginning of the video. It is most likely caused by the latest version of tensorflow and keras. Try using the same version as mentioned in the video. Keras - 2.3.1 and Tensorflow - 2.0.0. This worked for me.

@kzchannel9075 3 жыл бұрын

try this pip uninstall tensorflow pip uninstall keras pip install tensorflow==2.2.0 pip install keras==2.3.1

@akashhprabhu3763 2 жыл бұрын

great tutorial sir .....how to detect series of digits and print it??

@grlg6910 4 жыл бұрын

thank you so much. I have a question. How can I get data from a video in order to collect data? I want to divide an image to sub-region by vanishing line and to classify each sub-region including any object and so on. Pls help me.

@NileNetworks 3 жыл бұрын

Thanks Murtaza for this great video. I'm a big fan and I've followed a lot of your projects on your website. My question is how can we extend this to double digits numbers like 10, 11 .... . Do you have an available dataset for that?

@murtazasworkshop 3 жыл бұрын

This is classification . To do that you will need a detection method. I would suggest to look into pytesseract.

@NileNetworks 3 жыл бұрын

@@murtazasworkshop Thank you so much. You helped me a lot with this cuz I will need it in my new project. I started learning some OCR and text detection and it seems like it's the right way to go.

@bolzanoitaly8360 Жыл бұрын

@@murtazasworkshop , Why if we can extract and classify one digit, how we can classify two or three digits, I am looking also for this question. I am also one of the great fans, of yours MURTAZA. thanks, please, guide us. thanks best regards

@pinakidas4695 4 жыл бұрын

Hello Mr. Murtaza..... Can i use this code to train disaster images to identify between flood, earthquake etc?

@juliocesarproducoes 4 жыл бұрын

I would like to make a project License Plate Recognition, I will try with your code is it possible? , thank you so much! Please, share your OpenCV course. We're waiting...

@murtazasworkshop 4 жыл бұрын

i am working on it . will update soon .

@grlg6910 4 жыл бұрын

Thank you so much 😍😍😍. I want to make vanishing point/line detection using AI. Could you give me some guidance, please?

@murtazasworkshop 4 жыл бұрын

i am planning to do a tutorial on that . for now you can have a look at the lane detection using shape and color. kzfaq.info/get/bejne/Y7ilireoqdLTpGw.html

@sanjidampaul819 4 жыл бұрын

How do you calculate the "step_per_epoch" =2000, How can I calculate this number for my dataset?

@fmanzano1 Жыл бұрын

Hello, kindly show to us where can we get the folders from 1 to 10?

@teluguforyou3992 4 жыл бұрын

Sir how can I automate attendence management system using webcam(CNN)

@sohailali5741 4 жыл бұрын

Great tutorial. Thanks. Can you please let me know how we can put name of the class? Like if we want to put "Five" and probability 0.90 how we can do this.

@murtazasworkshop 4 жыл бұрын

you can look at the example implementation here www.murtazahassan.com/classify-traffic-signs-using-cnn/ look at the def getCalssName() function

@mohamedhabiboullahelhoubab6079 2 жыл бұрын

first of all thank you for this wonderful video, then how did you build the database?

@stevenmanangu4052 2 жыл бұрын

To my side I used the chars74k dataset, then picked only the handwritten and font styles images of the digits. I ignored the alphabets and created a smaller dataset with only digits from 0-9. It worked.

@yafaabentili2770 3 жыл бұрын

Hello Murtaza, thank you for these amazing courses. The link ro tge Model Trained.p dont work

@murtazasworkshop 3 жыл бұрын

Thanks for pointing out. The link in fixed.

@ahmedyamany5065 2 жыл бұрын

Great bro, I need to work on detecting handwritten Alphabets or words for English and other langages such as Arabic, could you guide me? what about tesseract , how to train model ?

@technology4875 4 жыл бұрын

Thank you, you are greate!! I cant stitch images(10 image), would you make little lesson about panorama maker?

@murtazasworkshop 4 жыл бұрын

yes will be sharing soon

@viswatejvarma7792 3 жыл бұрын

i am searching for the dataset from past 2 days..help me buddy

@dani889295 4 жыл бұрын

This is a very good tutorial, can you please help me also to draw a rectangle around detected digit? Thank you!

@murtazasworkshop 4 жыл бұрын

That is detection . This is classification . I will share some detection tutorials soon.

@ahmedmiladi2821 2 жыл бұрын

Question : if i make a new folder called "cats" full of pictures of cats, would the program train and learn with the same code or you need new implementation ?? I'm a beginner in this field

@adityanambidi5129 3 жыл бұрын

thanks a lot, amazing tutorial. it worked for me. but how to make it detect more than 1 number at the same time and print all the detected numbers?

@murtazasworkshop 3 жыл бұрын

This is a classification method you might want to look into detection . I have a separate text detection video try that.

@adityanambidi5129 3 жыл бұрын

@@murtazasworkshop thanks

@oktayahmadli785 2 жыл бұрын

is it gonna work with normal objects or is this code specific for digits?

@w7bani156 2 жыл бұрын

Greet video Thank you.♥️ Can you help me please if i want detect from hand what can i do ???

@pietrofusco7903 2 жыл бұрын

Great video, but at th time 1:53 you show an image with accuracy metric. It is weird because the validation accuracy is higher than training accuracy. Thanks

@mjkh9440 2 жыл бұрын

what is your application text editor do you use for install opencv on 2minute , 22 second

@user-je6it7ct8h 3 ай бұрын

Hi , thank you . This video became very helpful for me . I have a question that i tried to do this project but why can i find "model_trained.p " file

@trungdang5549 4 жыл бұрын

Great tutorial! I would like to remake this project, so could you share the dataset? Thank you very much!

@murtazasworkshop 4 жыл бұрын

the data set is here drive.google.com/open?id=1cZr91zzHl93H1cbmIwx_7upfQPPMPi33

@trungdang5549 4 жыл бұрын

@@murtazasworkshop thank you very much!

@technology4875 4 жыл бұрын

Thank you for dataset you are the best, keep making CV courses, especially stitching images, panorama maker please!!!

@thep-rajshow73 3 жыл бұрын

Can this be done in macbook?

@CodingCircle 3 жыл бұрын

@@murtazasworkshop Thank u Very much

@winwiths.g6155 9 ай бұрын

Hey murtaza wanted to know how can we increase the accuracy of our model?

@asifanowar423 4 жыл бұрын

Do we need to use exactly the same version that you used or we can use the latest version of the each library? Will there be any problem if we use the latest versions for all of them?

@murtazasworkshop 4 жыл бұрын

you might encounter issues if you use all latest version. specially for tensorflow. Its betterto use the same as in the video

@asifanowar423 4 жыл бұрын

Thank you very much for your reply.. But, unfortunately I can't download the exact version for tensor flow,that you mentioned here.. It's telling no compatible version found.. I tried a lot of time.. Except it other things, I could download..

@murtazasworkshop 4 жыл бұрын

@@asifanowar423 make sure your python version is 3.7.6

@asifanowar423 4 жыл бұрын

Thanks for the reply bro.. That's so nice of you..

@asifanowar423 4 жыл бұрын

@@murtazasworkshop finally I could install and run everything as per your instructions and everything went well.. 😊 ( the accuracy seemed a little less in my case though) It was an amazing tutorial. Hope to get a similar tutorial on neural network soon

@nayyershahzad8051 3 жыл бұрын

Excellent effort! I am getting following error at 48:11 of video: NameError: name 'sequential' is not defined. Is it something to do with Tensorflow?

@maheshvicky6078 3 жыл бұрын

@Nayyer Shahzad have a look at 1:04:55 , u need to import all of those before using them

@nayyershahzad8051 3 жыл бұрын

@@maheshvicky6078 Thanks! It solved my issue.

@asdasdasasdasdas9073 3 жыл бұрын

If I were to train it with every letter and sign would it be possible to solve captchas?

@shobhit7572 Жыл бұрын

Sir which dataset are you using?

@mariomichalik9015 2 жыл бұрын

Hello, is there any chance, that you can give your datasets available?? Thanks :)

@taneryilmaz6171 3 жыл бұрын

hi, Murtaza. I have a problem to extract data from plot images those old paper with grid lines and scanned . I know all manually programs.but i have many image. may ı extract data automatically??? Thanks in advance ..

@talhachaudhary5141 3 жыл бұрын

moreover if i put value of videocapture(1) then it gives error but when i put 0 it works?????/

@merveozdas1193 3 жыл бұрын

tank you, great tutorial:) Please ,Can you answer my questions?

@labahlabahoren 3 жыл бұрын

42:30 keras image data generator added 45:48 keras categorical added

@ganeshnaik8827 2 жыл бұрын

where did he added Adam and Flattern, Conv2D methods

@inextremis1928 4 жыл бұрын

Great video, but could u tell me where i can download the dataset that you are using in the tutorial?

@murtazasworkshop 4 жыл бұрын

you can download it here drive.google.com/file/d/1cZr91zzHl93H1cbmIwx_7upfQPPMPi33/view

@inextremis1928 4 жыл бұрын

@@murtazasworkshop thx mate

@devgohel5080 3 жыл бұрын

where can i get the dataset as the link isnt provided in description

@ShubhamPatil-xb9we 2 жыл бұрын

Which editor you used here

@mukhdarmustafa3727 2 жыл бұрын

what is tehe problem with this error Traceback (most recent call last): File "D:/Project/OCR/venv/OCR_CNN_Training", line 8, in myList = os.listdir(path) FileNotFoundError: [WinError 3] The system cannot find the path specified: 'myData'

@miladrostamian4316 3 жыл бұрын

Is there any way for loading model in c++ opencv? Thanks.

@vjukulkarni6057 4 жыл бұрын

can we try this by taking snap of written images snap,

@patrickpuentelml4958 4 жыл бұрын

Hello How can I make a bounding box around the number using the predictions and How can i know de center point of the BBOX i need this because i want to create a object detector of pencils and i want to follow the pencil with a car so i need the cooordinates od the bounding box

@creativetalks3229 2 жыл бұрын

Can you do same king of video for identifying seven segment LED readings

@bolzanoitaly8360 Жыл бұрын

AssalamuAlaikum, Murtaza brother, Can you help, if there is two digits as 48, how that can be detected with this code, please? Thanks, and requested to respond as soon as possible. thanks again best regards Gul Rukh

@pragatitanwar2169 3 жыл бұрын

M getting Assertion error, everytym m using cv2. resize() method, I hve to submit my project on cnn, instead of 9 image folders , I hve 45 folders, but my pgm is stuck in image preprocessing n augmentation coz it is throwing error, can you resolve it?

@talhachaudhary5141 3 жыл бұрын

sir i want to ask how you calculated the prediction in 80% 90% in the end after 10 epoch??????????????

@merveozdas1193 3 жыл бұрын

Why did you convert array to ( numpy array ) ?

@akhilsai660 3 жыл бұрын

Can you provide a link for those images please

@brainloading5543 3 жыл бұрын

Can we use this for captchas ?

@CComputervision 3 жыл бұрын

hi guy, i can't setup lib tensorflow . you can tell me how to fix .tks you

@pestisid 3 жыл бұрын

can't we use model.save() to save our model in this program?

@gawaderajesh 3 жыл бұрын

Thank you... However could not locate image folder... I tried git also. I am missing something please help..... Thanks in advance.

@jackjacki8191 4 жыл бұрын

hello sir you can give me what areas of application of this recognition I mean how important is this applciation in our usual life

@murtazasworkshop 4 жыл бұрын

these classification methods are useful for controlled environments

@duongTran-he6mk 3 жыл бұрын

Can you show me the source of all your pictures of number? Or you take them by your camera? Thank you so much

@user-rf9rj4nv9u 2 жыл бұрын

Hello, Sir. I am a college student from China. Fortunately, I saw this video and followed it to complete this project, but I often made mistakes.However, I have a question that I hope to get your reply: it seems that all the data sets are printed numbers, can the trained model realize the recognition of hand-written numbers? I am doing research on hand-written numbers recognition based on convolutional neural network, so it is very important to me.I am looking forward to your reply.

@sietjiunwenjoseph8884 Жыл бұрын

Hi, you can go and search for "mnist dataset", and how to import it in KERAS library

@nimeshkumar3663 2 жыл бұрын

hi,can you help me with text detection using tensorflow js or opencv js

@zainabmouddae12 3 жыл бұрын

hello i need some help plzzzz in my code , I tried to use the same code in the video on my own dataset(OK, NOK) to classify by cam but I get this error : line 69, in to_categorical y = np.array(y, dtype='int') ValueError: invalid literal for int() with base 10: 'NOK' "line 69---> y_train = to_categorical(y_train,noOfClasses)"

@leancabiluna6852 3 жыл бұрын

please help Traceback (most recent call last): File "C:/JustDoIt/Python/mydata/number recognition.py", line 9, in myList = os.listdir(path) FileNotFoundError: [WinError 3] The system cannot find the path specified: 'JustDoIt'