ฝัง
- เผยแพร่เมื่อ 21 พ.ค. 2024
- Files and Instructions: pysource.com/2020/04/02/train...
In this tutorial I’m going to explain you one of the easiest way to train YOLO to detect a custom object even if you’re a beginner and have no experience with coding.
You will need just a simple laptop (windows, linux or mac), as the training is going to be done online, taking advantage of the free gpu offered by google colab.
We can train YOLO to detect a custom object, I choosed for example to detect a Koala, you can choose any animal/object you prefer.
➤ Full Videocourses:
Object Detection: pysource.com/object-detection...
➤ Follow me on:
Instagram: / pysource7
LinkedIn: / pysource
➤ For business inquiries:
pysource.com/contact
►► You can Build a Computer Vision software to DETECT and TRACK any Object.
→ 4-Step FREE Workshop pysource.com/blueprint-workshop-signup/
This is so so helpful
Thank you so much
Literally no other video on TH-cam has a tutorial like this which shows how to save the custom trained yolo model and use it in your own project
this tutorial is super easy! thank you for this, I'm training my own yolo weights at the moment
Please make a video tutorial for multiple class object detection, would be very helpful. Thanks
Thanks for your tutorial about YOLO..
Helping student finished their Tasks 🙏👍👍
Great tutorial! Useful content for sure. Thank you very much.
Could you let me know the changes which need to be performed for multiple object detection?
Thank you soo much bro, very good and clear lectures , no biting about the bushes.
You saved my weekend holiday, thank you!
You earned my subscription, too (someone said this below). Great work. Keep it up!
This is the most beginner/pro friendly tutorial i've ever seen.
608 x 608 create 6 permanent cpu-threads help this
True
@@kishore3785 did you get the solution to it?
@@kishore3785 same here. How do you fix it?
Hi Sergio, great tutorial! I have one quick question though which I'm sure a lot of people are wondering about. I keep getting disconnected from colab which prevents me from finishing the training. Instead of training the model from scratch again, is it possible to load latest weights instead of pretrained ones and continue training from there in new session? Many thanks!
Sir. It was great to see your video and the way each part was explained was great Thank You and keep up the great work.
*F.A.Q. : below you'll find my reply to your most requested questions*
*1) Train YOLO for multiple classes?*
This specific tutorial I've created is for just one class. I wanted to make it as simple as possible for beginners to just get the hands on object detection.
If you want to train YOLO for multiple classes do consider buying my Object Detection Course: pysource.com/object-detection-opencv-deep-learning-video-course/
You fill find also a dedicated lesson and python notebook to train your detector for multiple classes.
*2) Why does your output stop here: "608 x 608 create 6 permanent cpu-threads"?*
This error is difficult to debug, because it might be for a series of errors. Just make sure that you followed the tutorial correctly, that there are no typos on the folder names you've created and most importante, make sure that all the images are ".jpg" format.
*3) Weights file are not added to google drive?*
First of all make sure that that the training reached at least 100 iterations, after that weights file will be saved each 1000 iterations.
*4) Cuda out of memory error?*
Probably you have a big dataset of images and the GPU can't fid them all, so your dataset should be smaller, at least to work with these specific settings.
Salve Sergio, sono nell'ultima fase nel mio progetto, non ho più tanto tempo e ho avuto un po di problemi nel mio training, voglio che mi daresti una mano o un piccolo aiuto per favore , il tuo tutorial è il migliore di tutti quelli che ho visto grazie.
Hello sergio if you can make a tutorial about SSD custom object detection please
yes, very interested.
thanks, I'm really looking forward for more course from you
thank you for the tutorial, it was very helpful ... what I asked was how I got the testing.cfg file for my custom object detection??
simply and easy understanding tutorial, thanks
Amazing tutorial, everything works
This is exactly what i expected since i had amd ryzen laptop i cant use cuda but this helped me!! Thank you!!
Thank you... Awesome... It worked properly for my dataset...
You’re a master Sir, I had no idea about this and I could do it! Thank u very much!!
where u get dataset?
this is the very good video for beginners, I have ever seen...thnk you so much
Very informative tutorial - thanks!
super, waiting for next video
Thank you very much Sergio this is a great tutorial. I would be interested in knowing how to extend the code for detecting more classes. Would you give an update?
Do we need to change the image sizes before uploading and do we need to resize the x, y labels in the .txt file according to the input 416 size that the yolo takes? Please help pysource.
Thank you, It's working very well. Please teach how to train multiple animals.
Great tutorial, many thanks!!
Wombat in the 4th picture: "Am I a joke to you ?"
thank youuuuuu !!!
so glad that I have you
You earned my subscription. Thanks.
Thank you. Excellent video!!!!
Thank you very much, it's the best tutorial today
Hi! Excellent video! I've also watched the workshop... Awesome... One question... If I have a "moving" background, not fixed, the only way to track one exclusively item is by Yolo? I was trying but it's very heavy for mobile, isn't it?
you are awesome and ,something to the point and exactness!
Hello, thanks for this tutorial. Will this generate a coco.name classes file according to your customized dateset, or should i create it self after manualy?
Great Video!! When it is possible, could you make a video considering 2 classes? Like cats and dogs... or Koalas and Bears? Tks!!!
This is amazing. Thanks a ton !!
Hi! Thanks for the tutorial, can you explain a bit what happens after the image extractions? It is not very clear to me!
I'm trying to make a "heads" detector, so I trained the network in images where there are many different heads (in the .txt file I have many rows with the various bounding boxes present in an image).
As the camera is on top, it is a very difficult task, indeed, some heads look more like black circles...
So I tried to do Data Augmentation, but this time the iteration stops around 1000 instead of 2000, I have no idea why...
Precise and very informative
El mejor curso, un excelente maestro, gracias por compartir.
Hi Sergio, Thanks for the tutorial. I have a question is the process same for yolov4 ?
Hey! great video
i just want to know if we were training for multi classes so what changes to be made in this line:
!echo "Apple Orange Banana Bread Carrot Grape Juice Lemon Pizza Tomato" > data/obj.names
like this ? or this is wrong can u pls help!
nice work. I'm confused does the training you did on the koala dataset happen on a yolo model with all weights initialized randomly or are the weights of the inner model locked during training? or do you need to import pre trained weights if you want transfer leaning some custom datasets are very small how is it able to fit such a huge model??
Did Anyone solve the transfer learning with previous weights??
@@queenelozabeth can you plaese send the source code
What a great tutorial, I really learned a new thing.
I have one question, how can I train this yolov3 and save the model in h5 and cfg files, I am really struggled here ://
Thanks for this, the hardest part appears to be setting the parameters in the yolo config file. Yolo's default of 20 - 80 objects is not helpful. 1 class is much easier to start with.
Hey man great video! I'm working on a project which also requires detecting koalas. Is there any chance I could borrow your dataset? Thanks!
Great video brother, simple and crisp. Also, it would be great if u cud tell me how to implement this for real-time object detection.
Hello, I don't see the image when I execute the programm. Can you help me ?
Great tutorial! Thank you very much for this.
Can you please make a detailed video on how to detect a custom object in live stream?
Thank You
Nice video loved ..and excellent explanation
Hey Pysource! Love your videos man. Would it be possible for you to edit and upload an edited version of the Train_Yolov3.ipynb script to allow for multiple classes rather than just one? I was looking at the script trying to figure it out myself but I couldn't work it out.
It would be much appreciated.
Thank u sir, i hope you make tutorial more than 1 object detection.
Thanks. It's a great tutorial and super easy. How to show loss training loss and accuracy anyway?
Great thank you for sharing,
I have a question, why you didn't put anything in test.txt ?
Thank you so much for the turorial but i a have a question What changes i have to make for more than one class. like koala and snake etc?
Very nice tutorial thank you. Can you please let me know how can we evaluate our testing set in terms of mAP?
Great video! Can we take input as a video rather than an image and work the same way?
awesome tutorial!!
Hi Sergio,O have a huge dataset so when i training it the Google colabs time is out and it suggest me to use colab pro which I have to pay for it.My question is can I train a dataset which i already trained? Please answer,thank you for your videos.
you are the best!!! thank you again!!!
Hi Thank you for this fantastic video! May I know how to change the code if we train in local computer GPU instead of Google colab? Thanks!
great video , please tell ..can we use the same method for multiple classes??
Stunned by your work.
Love from Pakistan
From where you have find colab notebook?
Great tutorial. But where can I find your colab notebooks?
Hey Sergio , did u use the same data for testing and training?
Great video , thank you
Thankyou for this! Can you post a code snippet for linking this to a live video feed such as a webcam or drone feed?
Hi Bro !
I have a question how can i visualize the middle point (coordinate) of the image prediction or the bounding box with OPENCV ?
In other words i want to knoe the center point of the Koala's predictions .... Can you explain that in one video please.
Hi sir, I have tried using my own images which I am detecting melon fruit. However, it is not giving me the exact position when i tested it on Python. Perhaps you could explain what may cause it to be inaccurate? Thank you so much sir
Hey,i just wanted to let you know that i followed your tutorial exactly as you mentioned but i was not able to train the model.Whenever i tried the training process the output i get is seen 64 trained : 0 k-images(o kilo-batches_64)
please if you don't mind,can you help me know why i am having this error
Hello ! Great tutorial so far I have seen ! just bit curious what if I have two animal in a single image. do we need to make two rectangle using labelimg software ??
Yes you do.
Hi I would like to ask why does it prompt "'sed' is not recognized as an internal or external command,
operable program or batch file." when I try to run the program
I try to train in linux on GPU but idk how to enable GPU. But now i can fix it. thanks this VDO
Hi Sergio, what if I shoot images of Koalas with the same camera and I would like to know the XYZ position of the Koala with respect to the camera?
Based on the fact that I know the parameters of the camera, may I do it using this code as basis? Thank you
Do images in the dataset have to be of some specific size in pixels? also, do all of them have to be of the same type e.g. all of them landscape or square, or it doesn't matter?
did you know what is the best image resolution?
Hello Sergio,
Thank you for the great work and your time. I am curious about whether I can run the model after the training on a video. I am working on my research that I need to detect how many times a specific object (logo) appeared in a 2-hour video. Is it possible?
Thank you for your response.
Hi, yes it's possible.
Just consider that what for us it's a video, for the computer it's a series of images called frames. So you need to treat it in the same way as if it was an image but in a loop.
hey, great video! I was going to create a video about building a koala bear detector and found you already did it! lol, I will just choose a diferent marsupial : P
By the way, great channel!
thank you so much!! can you please tell the changes we need for multiple classes
any changes required? i am trying for 3 classes
Got to learn some new things. Informative video, not like boring style Videos.
Explained Well!!!
great video, very helpfull
Is it possible to train in Jetson NX let's say 12,000 images (6 types x2,000) and infere/export the model in a RPI? What would be the approx. size for a VGA resolution? Another this is the model size is approx. double of Zip size so I guess you need at least that free ram to run the model?
Can u explain pls what is Yolo and what is the diff between it and OpenCV ? and which python code editor do u use ?
hi sir!
i want to do with two classes,
when i denote with that program,
which is better , the images with two classes or images with only one class ??
for example tiger,cat
the images with a tiger and a cat ,
or the images with a tiger plus the images with a cat
Hi,thanks alot for such awesome tutorial,I want to ask one thing that if I want to train Yolov3-tiny what changes I have to made to train my custom model.waiting for your reply.
hi, did you find solution ?
Hi, thank you for this tutorial. I have a question though. Will the yolov3_testing.cfg file you provided on your site work with other single class projects? If not how do I find one for my project? Thank you
Hi, the yolov3_testing.cfg file provided can be used on any single class project, not only the koala project..
the only thing that need to be different is the weights file
Thank u professor
u just saved me! thanks A BUNCH
Hello! I followed this tutorial to make a model that can detect License Plates of motorcycles, and it worked on the two test images that I gave it. Thanks for the awesome tutorial! I have a question though, can I use this model in a different program to detect license plate from Video instead of images?
Yes you can.
Check this other tutorial of mine, and just use your own weights and cfg:
th-cam.com/video/xKK2mkJ-pHU/w-d-xo.html
@@pysource-com What if I want to apply it to camera shots or real-time?
Dear Sergio, Thank you for this tutorial. I have a question. Instead of labeling the koalas in the input images, if I crop them and give the crop image as an input ( without any .txt info file ) will it work ?
Hi, it won't work that way. The txt file must be there for each image
@@pysource-com Thank you for your response. It would be really kind if you please suggest me, whether there is any way ( rewriting the code ) so that I can do so, because the dataset I have, only contains the object ( cropped from the main image. And my use case is only for one class, therefore only localization is enough ..
I have a dataset with image and yml folder but for the training ı have to made the yml folder to txt folder. İn my yml folders there is xmin, xmax, ymin, ymax , depth, width,height
which numbers did ı have to write in the txt folder?
fantastic. thanks for sharing..
This is great💯. I really appreciate your work👏.Can we use coco dataset and custom trained models simultaneously?
Same question !
with my experience. the coco works with xml files and the yolo with txt
Same question. Please let me know if you have found a way to do that
hi sir great video thanks a lot. How can i run the dnn function on the google colab ?
Hi Segio, what modification i need to make in order to train 2 classes? i
know what changes to make on the notebook code number of classes and
filters and ect my question is about the images&txt files that we
upload to the drive, i put all the images&txt from the two classes
combined to one folder or i upload to folders ?
any changes required? i am trying for 3 classes
In the testing stage, I copy the yolo_object_detection.py file to Jupiter notebook and run it. There is no error, but no testing image come out. I wonder if it is the problem of getting image from the file path in the line:
images_path = glob.glob(r"localhost:8888/tree/yolo_images/*.jpg")
as I upload the images to the anaconda folder named yolo_images.
or I have tried to save the images on local folder and paste the link inside images_path = glob.glob(r"/Users/qianyu/Desktop/*.jpg")
It doesn't work neither. May I know what the problem is?
hi thanks for your greate toturial,I have a problem: training part last only about 5 minutes and not 3 hours,it stops automatically.ehat should I do?
Hi Segio, thanks for the tutorial. I have a question, Can this run in real time for the nvidia jetson nano using the pi camera?
Hi Diego, Jetson Nano is too weak to handle the full version of Yolo at decent FPS. You can expect it will run at around 2 frames per second.
I suggest you to train it using tiny Yolo, so you can get a decent speed on the jetson nano (around 16 fps)
Thank you for your response.
Thank you for your video. I have a question: how could I delete label of the bounding box in test images?? I want to have just bounding box without label.
alter the opencv code
Great video, sir. Could you make a video to train yolo in real time? Thanks you
Hi Thanks for this great tutorial. i tried the labeling app for the linux Linux_v1.4.3, it generated the xml instead of txt file, how to change the file format to txt? Thanks
When downloading in google colabotory from Train_YoloV3.ipynb file, Yolov3_trianing_1000.weights file and Yolov3_trianing_last.weights file. Does not appear, what to do?
Hey man! Nice video I really enjoy it, easy to follow and everything but when I get to the last step on the image processing instead of learning it takes only a few seconds and then a message pops up saying "Create 6 permanent CPU-threads ". Any Idea what could be the problem?
Hey! i have same problem, do you solved the problem?
@@dicharjachkson8003 Ye I did, it is important that you have the right file format... I had .JPG files but it only accepts .jpg files... Ye, it doesn't accept .JPG with capital letters...