Train YOLO to detect a custom object (online with free GPU)

Files and Instructions: pysource.com/2...
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/o...
➤ Follow me on:
Instagram: / pysource7
LinkedIn: / pysource
➤ For business inquiries:
pysource.com/c...

[@pysource-com]

►► You can Build a Computer Vision software to DETECT and TRACK any Object. → 4-Step FREE Workshop pysource.com/blueprint-workshop-signup/

[@Creek1575]

This is the most beginner/pro friendly tutorial i've ever seen.

[@kishore3785]

608 x 608 create 6 permanent cpu-threads help this

[@JNK369]

True

[@Anushka-dy5in]

@@kishore3785 did you get the solution to it?

[@vbprogrammingchannel]

@@kishore3785 same here. How do you fix it?

[@hritikgupta8765]

Please make a video tutorial for multiple class object detection, would be very helpful. Thanks

[@lucasharim]

Wombat in the 4th picture: "Am I a joke to you ?"

[@unclesam7853]

This is so so helpful Thank you so much Literally no other video on KZbin has a tutorial like this which shows how to save the custom trained yolo model and use it in your own project

[@StudentTasksChannel]

Thanks for your tutorial about YOLO.. Helping student finished their Tasks 🙏👍👍

[@dokenedgar8778]

If your execution stops with "608 x 608 create 6 permanent cpu-threads"... Check: - all image files are .jpg, no .png - all image files have corresponding .txt labels - the class of your label is what's in the colab notebook, not 'Koala' (i.e if you're using something else)

[@syedwaliuddin3656]

My code stops at 608x608 And my images are png , And the weight files are not uploading on my gdrive yolov3 folder :(

[@muhammadridwansyahputralub4205]

hello Doken, can you explain the detail about third point?

[@nickkosir9895]

Also, if your zipped folder "images" contains another folder that contains the actual image files (jpg,txt), then I get the same 608X608 message. So, I had to make sure my zipped images.zip folder didn't contain any nested folders and only contained the data (images and text files)

[@imagenigraphics]

this tutorial is super easy! thank you for this, I'm training my own yolo weights at the moment

[@gaurangpatel9968]

I have one question here. How can we use preprinted model and add our newly trained model with that. For example i have 80 classes in coco names but now i trained model with 2 new classes and i want that 80 and also 2 new classes. So in result my model is able to detect total 82 object. Please Help me for this...

[@khushboopriya9895]

hi, did you find any way ? Can you share

[@prashantmishra2179]

you can freeze the model till the last convolution layer, add 82 units in the next layer with softmax activation, and then retrain this last layer with the input of the frozen layer on the new dataset with 82 classes.

[@marx427]

khushboo priya transfer learning

[@hexiangpan7789]

You saved my weekend holiday, thank you!

[@murattoprak644]

You earned my subscription, too (someone said this below). Great work. Keep it up!

[@adarshds3]

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?

[@adem880]

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!

[@IngFDGang]

Thank you soo much bro, very good and clear lectures , no biting about the bushes.

[@achintyatripathi1199]

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.

[@jitusaini]

Thank you, It's working very well. Please teach how to train multiple animals.

[@lauradonelian]

Great Video!! When it is possible, could you make a video considering 2 classes? Like cats and dogs... or Koalas and Bears? Tks!!!

[@matssoto6061]

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?

[@roshansuvaris6942]

Thank you... Awesome... It worked properly for my dataset...

[@brentsimpson3791]

Thanks! I think my brain just exploded....

[@mykolatokariev8260]

Hey, nice tutorial. Thanks a lot. I did the same thing, but suddenly got an error like this one: output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()] IndexError: invalid index to scalar variable. Do you have an idea what is wrong with this? I see taht opencv.dnn.readNet( ) doesnt have any response. But I can't understand why. Can you give me a tip?!

[@hienongxuan3588]

Change i[0] to i

[@iremdemirci2357]

@@hienongxuan3588 Thank you.

[@yashbhole8917]

@@hienongxuan3588 Hello, for me changing i[0] to i only gives the image as it is. It's not identifying the image. What could be the problem?

[@neetesshhr]

Traceback (most recent call last): File "yolo_object_detection.py", line 8, in net = cv2.dnn.readNet("yolov3_training_last(1).weights", "yolov3_testing.cfg") cv2.error: OpenCV(4.2.0) /io/opencv/modules/dnn/src/darknet/darknet_importer.cpp:214: error: (-212:Parsing error) Failed to parse NetParameter file: yolov3_training_last(1).weights in function 'readNetFromDarknet'

[@feliperamirez9048]

You’re a master Sir, I had no idea about this and I could do it! Thank u very much!!

[@ritikajha2700]

where u get dataset?

[@alekssgolovcenko2523]

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?

[@dicharjachkson8003]

Hey! i have same problem, do you solved the problem?

[@alekssgolovcenko2523]

@@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...

[@hendriyawanachmad2017]

simply and easy understanding tutorial, thanks

[@ragaventhrananandhan9119]

How can i train for more than 1 classes

[@asadullashaikh4977]

can I use this same code for multiple object detection?

[@shalerr5513]

let me know if you find the answer please

[@zaidsiddique5777]

Yeah please let me know too

[@khanshehzadali8392]

yes plz let me know too becoz i m also working on same kind of project.

[@rohitjg]

This is exactly what i expected since i had amd ryzen laptop i cant use cuda but this helped me!! Thank you!!

[@artishah9000]

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

[@kesinirajesh7986]

this is the very good video for beginners, I have ever seen...thnk you so much

[@adityendrapratapsingh7999]

I can't find the labellmg software through the link.

[@yvantinguha9424]

I can't also find the labelImg software huhuhu

[@Melonpancito]

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?

[@programmerjowo]

did you know what is the best image resolution?

[@simplesyntax2341]

super, waiting for next video

[@michaelaaronsy6214]

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

[@TirthajitBaruah]

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.

[@johannamonin5884]

Hello, I don't see the image when I execute the programm. Can you help me ?

[@srivatsan804]

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.

[@m7mmd244]

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 ://

[@alexandrpetrov1110]

Amazing tutorial, everything works

[@charissayu8025]

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!

[@azamatzhubandykov5642]

Why getting ( process finished with exit code 0) on pycharm without any output?!

[@ehsanziaee1183]

I am having the same problem. I tried the code on Pycharm a month ago and it's working fine but right now I don't get any images at the output when I run the Train_yolo_to_detect_custom_object. I don't know what I'm doing different or what could go wrong. I also don't get any error.

[@nurulnajwa8963]

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

[@avinashsoni9533]

you are awesome and ,something to the point and exactness!

[@nabajitdey]

thank you so much!! can you please tell the changes we need for multiple classes

[@mohsin4397]

any changes required? i am trying for 3 classes

[@MB-tv8im]

How to Re-train custom yolo weights?

[@queenelozabeth]

I am looking for that! Any solution??

[@rog0079]

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!

[@Anushka-dy5in]

Hey, I am not getting the file in my drive after training. What should I do?

[@x-raymusic5221]

that is because you did not save the file in yolo format while using labelImg, you probably saved it with pascal formal.

[@idaitesamatarp]

i try to badminton racket but didnt work, i have 200 images. Can you help my problem?

[@VolleCe]

first of all I wanted to thank you for the successful video, you explain really simple, I have followed your instructions but the files are not created after the training, maybe you can tell me what I'm doing wrong Greetings Volle

[@samhitajoshi]

Got to learn some new things. Informative video, not like boring style Videos.

[@phillipspodcast]

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

[@phillipspodcast]

By the way, great channel!

[@mjaworsky2010]

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.

[@dyaakhaled9219]

Why getting ( process finished with exit code 0) on pycharm without any output?! I am using python 3.7

[@azamatzhubandykov5642]

How did you solved this problem?

[@k.o.v_3639]

How did you solved that problem??? Please

[@dyaakhaled9219]

Unfortunately no solution i found, giving "exit code 0" is good thing giving indication that the code working fine but no output

[@dionstefenmarsahalasinaga5223]

hi,, Error: l.outputs == params.inputs filter= in [convolutional]-layer does not match class= or mask= in [yolo]-layer magsut from error mentrain data, why?

[@jouiniahmed8834]

does anyone knows why i don"t find the model and weights on the yolov3 after training ?

[@hamez1300]

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!

[@AfnanKhakwani]

Stunned by your work. Love from Pakistan

[@hanishahzada230]

From where you have find colab notebook?

[@peteroregan7786]

Very informative tutorial - thanks!

[@satyabratsharma486]

great video , please tell ..can we use the same method for multiple classes??

[@gritsanapongpunti7121]

I try to train in linux on GPU but idk how to enable GPU. But now i can fix it. thanks this VDO

[@mmnn9982]

I followed all steps in the video but I had this error in the end (error you set incorrect value batch=1 for training you should set batch=64 subdivision=64) can anyone help me

[@yoniazhar3896]

Thanks. It's a great tutorial and super easy. How to show loss training loss and accuracy anyway?

[@siddharthct4799]

Precise and very informative

[@shawntai]

Wait, correct me if I'm wrong, but are you using the same dataset of images for both training and testing? Because I don't see you splitting them into the training set and testing set anywhere in your video. Thanks!

[@rahulkelkar1246]

I have the same doubt

[@lawrencechen0215]

There are some stupid mistakes I have made. Sorry for my poor English. 1. Do the exact same way to zip all the files and images. (It means that we should ctrl+A to select all the files and right-click to zip them so that the files will right be inside the zip file.) 2. Be sure that your class.txt should only have one class, and all of the text files should start with 0, which means that it belongs to class 0. (I labeled my data "car", but I selected the one provided by labelImg , so it turned out to be multiple classes.)

[@lawrencechen0215]

I have the problems 2) Why does your output stop here: "608 x 608 create 6 permanent cpu-threads"? at first.

[@lawrencechen0215]

You can also check out the Extract Images part, print(images_list) shouldn't just print [] , it means that it doesn't detect our images.

[@kaizen8492]

@@lawrencechen0215 I am getting this problem where it prints [], how can I resolve this?

[@nunobartolo2908]

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??

[@queenelozabeth]

Did Anyone solve the transfer learning with previous weights??

[@m.pavankalyan2650]

@@queenelozabeth can you plaese send the source code

[@ironrockygamer3840]

I can't find the ipynb file at all

[@edu_6161]

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?

[@lucreziatosato360]

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...

[@yevhenlebedenko2049]

Thank you very much, it's the best tutorial today

[@rlb5261]

Thank you. Excellent video!!!!

[@FredyGonzales]

El mejor curso, un excelente maestro, gracias por compartir.

[@mostafaibrahim5154]

When I try to test the predictions this error appears IndexError: invalid index to scalar variable. output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()] can someone help ?

[@mustafasabrialtun9010]

thank youuuuuu !!! so glad that I have you

[@muhammadharis6176]

here you using your label images to test can it work without labeled one for example we give image without labelling and check weather it works or not ?

[@luqmansen]

Great tutorial, many thanks!!

[@clotildamariamathias7416]

After training no files in drive are created

[@aditikhandewale8755]

i have installed opencv still getting these error Traceback (most recent call last): File "C:/Users/Aditi Khandewale/yolo_object_detection.py", line 1, in import cv2 ModuleNotFoundError: No module named 'cv2'

[@akshatpande1649]

just change "import cv2 "to "from cv2 import cv2"

[@srivatsan804]

Make sure you execute it in the command line as python3 and then the name of the file rather than python

[@prs16265]

You earned my subscription. Thanks.

[@JackJGX]

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.

[@manojrajsr6001]

you told that time limit for that online gpu is 12 hours? is it 12 hours for that account or 12 hours for that project? (ie,) can i reupload the files after 12 hours with the same gmail account?

[@tyty21315]

you can reupload after 12 hours im sure

[@rbr1344]

Nice video loved ..and excellent explanation

[@hanishahzada230]

unable to find colab notebook on your blog

[@softwarebox9639]

same here

[@harshinivenkataraman5185]

This is amazing. Thanks a ton !!

[@vipingautam9501]

Hi Sergio, Thanks for the tutorial. I have a question is the process same for yolov4 ?

[@alpenapple]

you are the best!!! thank you again!!!

[@sysadmin9396]

Hello, Is it possible to train my own dataset, and use a web cam to run detections as well as extract class information form the detected objects? For example, I want to create a data set of cards.. train yolo to recognize the cards and once a card is recognized be able to pass that recognized object to another function?

[@pysource-com]

Hi Luis, yes it's possible to do that. Once you detect the object, you can apply any function you want using python.

[@sysadmin9396]

Pysource Awesome. Do you have a course that I can buy/watch that will point me in the right direction to help me achieve my goal mentioned above?

[@pysource-com]

@@sysadmin9396 Hi Luis, yes, I have an object detection course (Opencv & Deep learning) which will help you to achieve that: pysource.com/object-detection-opencv-deep-learning-video-course/

[@dwiadityah3065]

Thank u sir, i hope you make tutorial more than 1 object detection.

[@m.pavankalyan2650]

I am gonna try this , I hope at least this tutorial helps me

[@differentperspective1000]

scores = detection[5:] why we did this and why we multiply the width center_x = int(detection[0] * width) ?

[@vamsikrishna-qc2xg]

Great video! Can we take input as a video rather than an image and work the same way?

[@godwingeorgethekkanath]

This is great💯. I really appreciate your work👏.Can we use coco dataset and custom trained models simultaneously?

[@aouamchaimae6248]

Same question !

[@captainezzy3870]

with my experience. the coco works with xml files and the yolo with txt

[@wishalarshad5117]

Same question. Please let me know if you have found a way to do that

[@MagicNutza]

hi can you help me fix this problem on pycharm when I ran the code it has an error that show ModuleNotFoundError: No module named 'cv2' I am already done pip install opencv-python but it still has this error

[@tahashahid5429]

you might be using python3. try "pip3 install opencv-python" or "pip3 install opencv-contrib-python"

[@coccosapiens]

@Abdul Wajid already tried still not working :(

[@immalegit0]

Hello sir, may I ask does using raspberry pi 4 model B 8gb is enough to make the same mechanism but using it for detecting cats only.

[@Viral-4PM]

Which image size should be downloaded from Google if we train yolov5. Or we can download random image sizes . Plz suggest me

[@madeandika6410]

is there any way on how to put the training result on a graph?

[@fraterdem2738]

I did all the instructions but the steps progress very slowly throughout the training. I also adjusted the GPU settings in Colab. What should I do to fix this problem?

[@sukasukadika8811]

i cannt find the model weight at my drive yolov3 after training session, how to solve it?

[@pratyoshsahoo1608]

same error....how to solve ?????

[@godlysunny1896]

Thankyou for this! Can you post a code snippet for linking this to a live video feed such as a webcam or drone feed?

[@sohailawan77]

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.

[@ahmednacerbabahammou7814]

hi, did you find solution ?

[@sureshkumar0707]

I do not find the 2 weight files in my yolov3 folder in my drive ? The Training is not also performed in my program. I followed the same, I changed the Class name from Koala to Apple, Remaining all the things are same. [yolo] params: iou loss: mse (2), iou_norm: 0.75, cls_norm: 1.00, scale_x_y: 1.00 Total BFLOPS 65.304 avg_outputs = 516723 Allocate additional workspace_size = 12.46 MB Loading weights from darknet53.conv.74... seen 64, trained: 0 K-images (0 Kilo-batches_64) Done! Loaded 75 layers from weights-file Learning Rate: 0.001, Momentum: 0.9, Decay: 0.0005 Resizing, random_coef = 1.40 608 x 608 Create 6 permanent cpu-threads

[@arjunpj2623]

same issue here , i tried to change the directory , still the same issue

[@pysource-com]

Hi Suresh, "Create 6 permanent cpu-threads" the last line of the output is saying "Create 6 cpu-threads", this most likely means that you didn't activate the GPU on your nootebook. That might be the problem, check carefully the video tutorial, I explain how to activate the GPU

[@MrFreechelsea]

@@pysource-com I followed the tutorial and already activate the GPU on my notebook, but still faced the same error. Any advice?