YOLOv8: How to Train for Object Detection on a Custom Dataset

[@AndroidDjRealEDM]

Finally is really simple to use for industrial projects!

[@SkalskiP]

Exactly!

[@goodtechdoor]

Epic, waiting on the next parts. Cheering for Roboflow & Ultralytics teams !

[@giridharidash9528]

00:05 Yellow V8 is the latest object detection model that fine tunes much faster than its predecessors 02:29 Yellow V3 and Yellow V5 repositories have almost 45,000 stars on GitHub and will solve previous issues in the Yellow V8 project. 04:58 Importing Yolo from ultralytics and running inference 07:36 Creating a dataset for training the YOLO model using Roboflow 10:16 Use Cinema to label images and create a dataset for training 13:00 The training has been completed and the results are satisfactory. 15:41 Training the models could take longer and yield better results. 18:04 Yellow V8 model can be trained and deployed for inference using a single line of code. 20:16 Comparing yellow V8 to previous object detection models Crafted by Merlin AI.

[@matheusmartins1000]

Good diction, i'm currently learning English, and I find your pronunciation much easier to understand compared to most people, not sure why. Great video!

[@AndrewTSq]

Lol I have noticed this too!, Its often easier for me to understand non-native english people

[@ayanpaul2210]

Thank you Roboflow!! Always keeps us updated🤝🤝

[@Roboflow]

Thank you for wanting to be updated!

[@kevinwoodrobotics]

Great video! Definitely useful to train your own dataset since yolov8 was originally trained on COCO so it may not work for special applications!

[@anujjain4406]

Thank you Brother , The Roboflow is just Amazing and super easy to use.

[@ozgurkan]

You are the best. Roboflow 💙

[@shivamgoel0897]

Great video! very helpful to get started with Yolov8

[@dineshe90]

good job Roboflow and Ultralytics team... I want similar videos in docker... Thank you

[@anren7445]

at 13:45 you can utilize gpu by typing "device=0" so it can train faster

[@Roboflow]

Doesn’t it train by default on GPU if it is accessible?

[@muhammadrizwanmunawar]

Nicely explained!

[@SkalskiP]

Thank you!

[@serverxeon]

Is there something wrong with your code, or did recent ultralytics version change break the code?

[@Roboflow]

Do you experience some problems now?

[@afrahthahir7179]

Is this working good in real time rtsp stream fetched from CCTV cameras??

[@SkalskiP]

Hi it is Peter from video! 👋Honestly I haven't checked that out, but it sounds like a very good topic for next tutorial video.

[@afrahthahir7179]

@@SkalskiP yes please do that for the next video.

[@CantPickTheNameIwant]

​@@afrahthahir7179just keep in mind that it works good mostly on big size objects

[@MarceloSEO]

on 18:08 you mentioned that you downloaded the result and played the video. Do you mind sharing how to do that?

[@Amy_desu]

did you find out?

[@hggaming911]

Very simple and useful… Thank you so much

[@Roboflow]

Stay tuned, we will soon post YOLOv8 instance segmentation too ;)

[@tryingtobeproductive]

easy tutorial to follow, thanks!

[@Roboflow]

Awesome!

[@ML.ArtificialIntelligence]

I am getting this error again and again during training Dataset not found ⚠, missing paths ['/content/datasets/football-players-detection-4/valid/images'] Error executing job with overrides: ['task=detect', 'mode=train', 'model=yolov8s.pt', 'data=/content/football-players-detection-4/data.yaml', 'epochs=25', 'imgsz=800'] Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/cli.py", line 56, in cli func(cfg) File "/usr/local/lib/python3.8/dist-packages/hydra/main.py", line 79, in decorated_main return task_function(cfg_passthrough) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/v8/detect/train.py", line 207, in train model.train(**cfg) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/engine/model.py", line 189, in train self.trainer = self.TrainerClass(overrides=overrides) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/engine/trainer.py", line 126, in __init__ self.data = check_dataset_yaml(self.data) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/data/utils.py", line 232, in check_dataset_yaml raise FileNotFoundError('Dataset not found ❌') FileNotFoundError: Dataset not found ❌ Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

[@SkalskiP]

Hi it is Peter from the video! 👋Are you getting that error with our notebook?

[@mohammadhaadiakhter2869]

@@SkalskiP Yes me to, I got the same error while custom training

[@treudden]

same

[@ML.ArtificialIntelligence]

Yes I am getting this error while using the notebook you provided in this video

[@golasa7646]

I got same problem

[@kuaranir2440]

Thank you RoboFlow! Please how to show in this case number of detected objects on the test image?

[@Roboflow]

We have this exact example in the supervision readme. Take a look: github.com/roboflow/supervision?tab=readme-ov-file#-quickstart

[@aleksandramelnik4862]

It was soooo helpful! Thank you!

[@Roboflow]

I love to hear that!

[@kelemawiguzo9611]

@@Roboflow could you do the same for OneFormer pls.

[@FatemehZaremehrjardi]

Thanks! I tested the model on some images I can see the results in text but the bounding boxes on the pictures won't save.

[@SkalskiP]

Hi it is Peter from the video. I just updated our notebook for object detection. Could you check one more time? The issue should be fixed now :)

[@Mc.Gucket]

what is the best.pt file? ı just downloaded it and closed everything else. did ı save my model? can ı use it?

[@sujinyang4373]

This video has made my DL work so much easier! Thx for the great tutorial on YoloV8 and connecting it to Roboflow workflow😊😊

[@SkalskiP]

Hi! It's peter from the video. Thats what I wanted to hear! 💜

[@poushalinag7942]

Hey, for my dataset its taking so much time to train the model and i am running out of GPU limits, earlier i was getting error in training but i added batch size 8 ,now its training the model but taking too much time and GPU. Can u suggest what should i do?

[@lynguyenminhOfficial]

That is a great tutorial! Thanks sir.

[@Roboflow]

Thanks a lot!

[@MehulGupta-b5k]

Hey so when I'm running the video, the model is detecting the objects and the count frame by frame. But I'm not able to see the video to see which objects it detect. Can you please help me out?

[@Roboflow]

Do you pass show=True ?

[@benephr]

Hello I have encountered this issue for command at 13:47 Dataset '/content/datasets/Football-1/data.yaml' images not found ⚠, missing path '/content/datasets/Football-1/Football-1/valid/images' Note dataset download directory is '/content/datasets'. You can update this in '/root/.config/Ultralytics/settings.json'

[@benephr]

I changed the path in data.yaml and it seems worked

[@ManuelHernandez-zq5em]

I ran the roboflow Yolov8 snippet and generated me this folder structure: datasets > objcts-to-detect > train > images ... When I ran the !yolo task=detect mode=train... step, it crashed with this error: Dataset not found ⚠, missing paths ['/content/datasets/pkslsp-and-tksrs-1/valid/images'] The roboflow snippet did not generate folder "valid" before "images". How can I fix this?

[@Roboflow]

Could paste here a link to your dataset at Roboflow?

[@ManuelHernandez-zq5em]

@@Roboflow Everytime I paste the link right here, it gets deleted. I am going to paste only what is after the roboflow domain, which is: /pc-solutions/pkslsp-and-tksrs/1. Let me know if this helps. 😕

[@Roboflow]

@@ManuelHernandez-zq5em great, thanks! We didn't created that directory, because you don't have any valid and test images in your dataset. 4 images in train and 0 in valid and test. YOLOv8 requires you to have some validation set.

[@yiksengtee8402]

@@Roboflow Hi I'm having the same problem and tucked at Custom Training section, where it shows: Dataset not found ⚠, missing paths ['/content/datasets/PV-Temperature-detection--2/valid/images'] Traceback (most recent call last): File "/usr/local/bin/yolo", line 8, in sys.exit(entrypoint()) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/cli.py", line 148, in entrypoint cli(cfg) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/cli.py", line 84, in cli func(cfg) File "/usr/local/lib/python3.8/dist-packages/hydra/main.py", line 79, in decorated_main return task_function(cfg_passthrough) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/v8/detect/train.py", line 207, in train model.train(**cfg) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/engine/model.py", line 199, in train self.trainer = self.TrainerClass(overrides=overrides) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/engine/trainer.py", line 126, in __init__ self.data = check_dataset_yaml(self.data) File "/usr/local/lib/python3.8/dist-packages/ultralytics/yolo/data/utils.py", line 232, in check_dataset_yaml raise FileNotFoundError('Dataset not found ❌') FileNotFoundError: Dataset not found ❌ I have adjusted and having valid and test images in my Roboflow dataset. The link is "app(dot)roboflow(dot)com/apu-vbwqe/pv-temperature-detection/2" Appreciate if you could help me check

[@gomathinalla3575]

You gotta change the paths for respective folders say test,train and val in data.yaml file. And try running it again, it should work. Hope this helps!

[@pruthvidarshanss1586]

Hey, in the video at 11:26, u said that u have posted the links in the description but i couldn't find that link. Can u please check for that link? It will be very helpful for me.

[@sevenscapes]

Just a quick question, upon completing training, can I download the newly created Yolo model?

[@Roboflow]

yup! all weights are saved in google colab after training; you can download them to your hard drive.

[@meryem8634]

thank you for great video :)

[@Roboflow]

Thanks a lot for watching :)

[@entertainmentvideos1281]

hello sir after detection there is no predict directory where my video and test images are stored... detection on video perform and completed successfully but predict directory is not

[@SkalskiP]

Hi it is Peter from video. I just pushed slightly updated version of our notebook. I think you should not experience that problem now. Could you take a look?

[@jojis4950]

Hi, thank you for the lovely video. Although I am getting this error when I initiate training: FileNotFoundError: Dataset '/content/project_name/data.yaml' not found ⚠, missing paths ['/content/datasets/project_name/valid/images']

[@Roboflow]

Hi 👋🏻 could you create a bug report here: github.com/roboflow/notebooks? Please provide us with as many details as possible.

[@themuppetman3671]

This happens to a lot of the files for some reason, it also did it for 'predict3' and required a change to ''predict2'. I'm not sure whether this is intentional or not : |

[@themuppetman3671]

@@Roboflow For me this occurred because the 'train' file (/runs/detect/train/weights/best.pt) was displaced for some reason. All the weights had saved to 'train3'rather than the preestablished location within the given code. Try and find where the files are saving and change the file destinations (i.e., from /runs/detect/train/weights/best.pt to /runs/detect/train3/weights/best.pt).

[@MrCantyousea]

I can't see the Submit Images For review section. Why?

[@Roboflow]

Hi! 👋Do you have only images or images and annotations? If you have annotations in what format?

[@MrCantyousea]

​@@Roboflow Hi, thanks for your help. This is my first project actually. I do almost everything same with you. Just I don't use same dataset with you.(I couldn't find your dataset). I use different football match images dateset from roboflow. Total 114 images and I annotated 5 of them.(I don't know which format are they.) Then I want to annotate others automatically like you but I can't see the Submit Images for review button.

[@MrCantyousea]

@@Roboflow I also couldn't see Approved or Rejected options in Overview. Probably something may wrong about my dataset. But they are only images with unannotated

[@MrCantyousea]

@@Roboflow I think I misunderstood. I guess we should manually annotate all the pictures that will be used for the model we will build first. Then we can easily label and annotate much more data with the model formed after that. I guess you meant it

[@liao-g9v]

Hello! I really enjoy your series of tutorials; they are particularly detailed and clear! However, when applying them in practice, I encountered a problem. The target I want to detect is partly included in the YOLO pre-trained model, and the other part is not. For the targets not included, I have trained a custom dataset. How can I combine the custom model with the pre-trained model to recognize all the targets I want in a single image?Thank you!!!

[@helloansuman]

Please create a video on how to utilize multi GPU in a single node.

[@rohanpokale4651]

Hello.. I trained a model on YOLOv8 and it worked very well. I had a question. Like I wanted to make some changes in the Predict file when I was running yolov8 in my system locally on CLI. I wanted to integrate a alarm system when any thing is detected. So I wanted the location of the Predict file. I have download the ultralytics repo in my pc.

[@SkalskiP]

Hi 👋It is Peter from video! If you want to do changes, I encourage you not to install via pip but clone repo and install it the old way.

[@narsilberkay]

Output of the predict method doesn't give the location of the predicted images, how can i fix it ?

[@Roboflow]

Add save=True to your command

[@mohammadhaadiakhter2869]

Did you use pre-train model on COCO dataset and just updated the weights or did you actually created a new instance YOLOv8?

[@Roboflow]

Hi! If I understand your question correctly, you ask if we used transfer learning or not?

[@mohammadhaadiakhter2869]

@@Roboflow No no, it was something else, but now I am encountering the same error as Rachaer CR ERROR-Error executing job with overrides I also used my own dataset. Please help

[@Roboflow]

@@mohammadhaadiakhter2869 could you create a issue here: github.com/roboflow/notebooks/issues? It would be great if you could include link to your version of notebook.

[@mohammadhaadiakhter2869]

@@Roboflow Just one more thing from ultralytics import YOLO model = YOLO("yolov8n.pt") import cv2 import numpy as np cap=cv2.VideoCapture(0) while cap.isOpened(): ret,frame=cap.read() results=model(frame) cv2.imshow('frame',np.squeeze(results.render)) if cv2.waitKey(10)& 0xFF==ord('q'): break cap.release() cv2.destroyAllWindows() I am encountering an OS error, any idea how to solve it?

[@Roboflow]

@@mohammadhaadiakhter2869 is that your help request here: github.com/roboflow/notebooks/discussions/44

[@sholehuye2737]

Sorry sir, permission to ask if the code that runs on google collab can be run on pycham

[@tonyzedlav]

would higher epochs on training mean higher accuracy?

[@Roboflow]

It may be more tricky. If you train for too long, you might overfit your model. Especially if your dataset is small.

[@tonyzedlav]

@@Roboflow thank you, what would be your suggested number of epochs?

[@wptgroup]

Thanks for the fantastic video. My prediction picture data won't store in /runs/detect/predict at the moment I run with mode=predict. What should I do? I repeatedly ran my code, but it failed to save. Your advice is essential. thank you in advance.

[@Roboflow]

Try to use save=True parameter

[@aswath_tamilan]

i cant access the ultralytics command line to further process

[@Roboflow]

Could you give me a bit more detail?

[@aswath_tamilan]

@@Roboflow i can't access that ultralytics page and set of commands on colab .

[@Roboflow]

@@aswath_tamilan could you create bug report here: github.com/roboflow/notebooks/issues and describe your issues?

[@aswath_tamilan]

@@Roboflow ok

[@iMJKhan]

Thanks for your efforts. How to generate a confusion matrix if the training is stopped due to no improvements in loss?

[@omerkaya5669]

I trained our network with custom dataset. The training period lasted a long time. I want to test the performance of my test set with the network I trained at another time. Is there any other solution than retraining the network?

[@fatrat1184]

Hi, how if i don't want to use yolov8n, and i want to change yolov8m, where should i change it? Someone pls help me thx

[@kevinwoodrobotics]

When you call the YOLO function, you can change your model input there as a string to your model name. Have to first import from ultralytics

[@razorphone77]

When you train a model, the weights are saved in the runs folder correct? We do not have to upload to roboflow? Also using v5 you used to be able to put custom data sets in a certain place in the directory structure which you reference with a data.yaml file. Is this not the case anymore? Where are the datasets stored now? Is it no longer on the local machine in the directory? Do we have to use roboflow and upload there? Thanks

[@AjayReddy1]

How to get the google colab file for training

[@SkalskiP]

Hi it is Peter from the video! If you mean link to the Notebook, it is in description bellow ;)

[@robparatore1940]

Are there any footage requirements for inputting into YOLOV8? I am trying to use it for sports analysis and wondered whether you need the whole pitch/tactical wide lens?!how zoomed in does it need to be? Will it capture a ball being hit at really high speeds?

[@edumaba]

Hi all, please where can I get the football data used in this tutorial?

[@Roboflow]

here’s the dataset: universe.roboflow.com/roboflow-jvuqo/football-players-detection-3zvbc :)

[@Agronomistapolo]

Could you explain how to edit the bounding box to visualize them with a better appearance?

[@Roboflow]

Did you try our supervision pip package? We offer custom annotators for bounding boxes there.

[@RAZZKIRAN]

thank you, useful, great content

[@Roboflow]

Thanks a lot!

[@RAZZKIRAN]

@@Roboflow welcome sir, getting errors at code, please solve sir

[@Roboflow]

@@RAZZKIRAN I'm happy to help. Could you please create a thread on ours discussions page: github.com/roboflow/notebooks/discussions/categories/q-a ?

[@roobeshbalaji9282]

Hello! Quick question, when trying to deploy the model, I'm getting the message "an error occured when getting the model upload URL: This version has a trained model. Please generate and train a new version in order to upload model to Roboflow." How can I fix this?

[@Roboflow]

Hi, it is Peter from the video. 👋For now, we only allow one model version to be tied with one version of the dataset. Looks like you already have some models tied with that version of dataset.

[@roobeshbalaji9282]

@@Roboflow I'm not sure exactly. I ran the colab file pretty along with you following the video, except I made my own dataset how you showed it in the video and used the api information from that. Pretty much ran the rest of the colab file as is.

[@Roboflow]

@@roobeshbalaji9282 can you send me link to your dataset?

[@muhdirshat9858]

hello, i have some problems on confusion matrix part where the font size that shows number in that confusion matrix is too small and quite hard to read. is there any way that i can make the font size on that confusion matrix bigger? is there any modification on the code?

[@Roboflow]

No. But you can use supervision confusion matrix: github.com/roboflow/supervision

[@venkatasubramaniat7163]

is there any detailed blog or tutorial for yolov8 classification. with custom dataset. am having problem with data parameter in model.train

[@esooghazy]

Me too! It raises FileNotFound: None error

[@ranggayogiswara5148]

The option to export in yoloV8 format is now available. Do I still have to export the annotated dataset to yoloV5?

[@Roboflow]

Good question. It is better if you'll export in YOLOv8 format.

[@navyabaireddy5920]

All at once in the sense, rather than annotating all the images manually is there any way we could do it faster?

[@luizgarcia3878]

How did you added the labels at the video? When I try using a test video it does the process and shows the classification but the video remain the same

[@watanabeyou3446]

How to download the dataset with python?

[@bryceayoung]

Thanks for the video! Does yolo segment things in geometries that aren’t rectangles? For instance, if you wanted to segment different planar surfaces on a roof from aerial imagery.

[@muza886]

Hii i have error in project deployment " AttributeError: 'UltralyticsCFG' object has no attribute 'items'"

[@Roboflow]

Could you please create issue here: github.com/roboflow/notebooks/issues ? That could help us track that issue. And please provide as much details as you can.

[@TerukiVAL]

How can I exclude certain classes when generating weights? During my annotation process, I included all the classes I needed, but I only want the model to generate weights based on specific classes. How can I achieve this?

[@moahaimen]

how to make the predication on KZbin video, i was doing this on Yolov5

[@Roboflow]

It is not working with YOLOv8 CLI?

[@robinchriqui2407]

Thank you very much it worked very well with my own custom dataset, I have a question how do you download the result on the video?

[@Roboflow]

You mean from Colab?

[@robinchriqui2407]

I just had save and it worked, yes from collab

[@omerkaya5669]

Could you send the video? predict part is not coming.

[@Roboflow]

@@omerkaya5669 could you be a bit more specific?

[@omerkaya5669]

@@Roboflow %cd {HOME} !yolo task=detect mode=predict model={HOME}/runs/detect/train2/weights/last.pt conf=0.1 source=/content/25km.mp4 I run this code, but I can't see where the video is saved.

[@tzadokavraham]

hi,how can i download the results from the colab?

[@Roboflow]

Result of both training and detection is saved in runs directory. Take a look here stackoverflow.com/questions/49394737/exporting-data-from-google-colab-to-local-machine to learn how to download stuff from colab.

[@JustShorts-7]

amazing but how can i give Live camera real time video instead of video to detect object that is trained

[@Roboflow]

We actually done webcam live-stream processing with YOLOv8 tutorial: kzbin.info/www/bejne/h4ebZpiPhMdqnc0 Take a look :)

[@jpatrx]

keep getting a failed upload of my model. what could be the problem?

[@Roboflow]

For now, you can only have one model per dataset version. Do you already have some model tied to your dataset version?

[@blackwhalestudio]

if you want to seperate the teams would you do that in the labelling (annotation) when preparing the dataset or later in the algorithm based on for example the jersey color? Thanks for the great video!

[@red-bluelife]

Yes, you would need to do the annotation, but the model will predict poorly on new teams.

[@muhammadhilman1045]

THANK YOUU SO MUCHH BROO 👍👍👍👍👍👍

[@AmmarAbbasi-l2n]

can we run live inferencing on yolov8 models without using ultralytics library like we used to in previous version of yolov5? I want to setup the codebase for just running inferencing without using the ultralytics library.

[@Fctxxx]

Hello, I am trying to make the same application with a different dataset. In the "Training" section, I get the error "boolean index did not match indexed array along dimension 0; dimension is 1 but corresponding boolean dimension is 9" and train section stops. how can i solve this?

[@Roboflow]

Hi! Are you using our notebook for training with no changes other than your dataset? Do you use dataset loaded from Roboflow?

[@Fctxxx]

Yes im using dataset from roboflow. Everything same except dataset. But i have a error.

[@Roboflow]

@@Fctxxx could you please create issue here: github.com/roboflow/notebooks/issues? It would help us to track this issue. Please make sure to give us as much detail as you can.

[@BinodKhatri-i4x]

Hello, thanks for the amazing tutorial. the older version of roboflow is working fine but I could not figure out why is the the roboflow 1.0.1 or later throwing following error just by importing it. TypeError: unsupported operand type(s) for +: 'NoneType' and 'str'

[@Roboflow]

Could you please create new issue here: github.com/roboflow/notebooks/issues and give me a bit more detail?

[@HashirAKhan]

My question is, once we train on custom classes will Yolo only predict those classes or the pre-existing classes in Yolo will also be there in our predictions?

[@Roboflow]

It will only detect the new classes.

[@HashirAKhan]

@@Roboflow so how can we add custom classes to yolov8?

[@Roboflow]

@@HashirAKhan so you want to keep the old and add new?

[@HashirAKhan]

@@Roboflow yes exactly! Like keep the old classes and add the new ones.

[@HashirAKhan]

@@Roboflow So basically reinforcement learning, using the old weights and new weights, do you have any tutorial on that?

[@judesequeira1643]

do we need to specify device=none parameter while training to access GPU even after changing GPU settings under Runtime bar in Colab? When i execute training even after changing to GPU settings under runtime tab, i get device=none mentioned in the output of training

[@728239]

What is the best way to resize images to 640x640? Is it stretching or resizing keepeing proporions?

[@seroshmannan]

how can we change the hyperparameters according to our custom dataset

[@Roboflow]

Do you mean hyperparameters of the model?

[@seroshmannan]

@@Roboflow yes

[@Roboflow]

@@seroshmannan you can pass your training hyperparamiters as arguments to yolo CLI

[@moazamadrees5409]

hey how can we use our own weights file it's generated in PT extension?

[@SkalskiP]

Hi it is Peter from video :) What would you like to do with them? Deploy in Roboflow? ;)

[@moazamadrees5409]

@@SkalskiP I am using the yolo default weights in my own code for detection, but when I train a model on custom data set, it generates weights in pt extension which aren't useable unless in weights extension so is there a way?

[@SkalskiP]

@@moazamadrees5409 I try to follow what you are saying but I don't quite understand. .pt file is the standard PyTorch file extension. Is file in that extension not working for you?

[@moazamadrees5409]

@@SkalskiP well when I deploy the model in my code I used yolov7.weights file, but the one generated from custom model is Pt file, can it be changed into weights is my question

[@kaka0199]

Im looking for that answer to Have you found a solution?

[@thearpitkatiyar637]

What algo you are using with yolo for image detection

[@rachealcr6752]

is that possible for the yolov8 train model to implement in MATLAB?

[@Roboflow]

I’m afraid not.

[@roni1422]

how can we dowload the final models from the notebook for using in pycharm?

[@Roboflow]

Of course you can! Mode is saved in runs directory. And you can download it from colab. Take a look at this stackoverflow.com/questions/49394737/exporting-data-from-google-colab-to-local-machine to learn how to download stuff from colab to local.

[@roni1422]

@@Roboflow can you explain how to set the runs directory please? for exaple ,my google drive. what is the relevant command?

[@AkankshyaParida-z1m]

i am getting error again and again if i use any other dataset , my epochs are not running only.. suggest what to do

[@AmaBaidoo]

Please how can I edit the code to count the number of objects detected instead of just drawing boxes?

[@Roboflow]

We will do exactly that tutorial on Monday or Tuesday

[@hchattaway]

Iam new to YOLO and object detection.... What is the relationship between YOLO and PyTorch? This video didn't mention PyTorch but in other tutorials on YOLO, PyTorch was brought up but it was not clear how they integrate or if that is even needed...Any help is greatly appreciated!

[@SkalskiP]

Hi it is Peter from video! PyTorch is a general framework used to build neural networks. YOLO is one of neural networks that is written in PyTorch.

[@hchattaway]

@@SkalskiP oh! YOLO is written in pytorch! Didn't know that... So no other separate processing by pytorch is needed, thanks!

[@aryachowkekar2769]

TypeError: unhashable type: 'numpy.ndarray' (Having this error in custom training process)

[@Roboflow]

Could you give me a bit more detail? When is that problem occuring?

[@akifakbulut765]

What can I do to make the model I have trained to continue training again leter?

[@Roboflow]

resume=True I believe :)

[@janaud14]

Doesn't work for me, i have an issue for the custom training step : "(...)/data.yaml' is not a valid YOLO argument."

[@arunesh_7]

Same problem

[@Roboflow]

Is that happening in our notebook?

[@pcsolutionsezcloudsystems5929]

After extracting the downloaded dataset zip file (from my roboflow account), to which folder (following this video) should I upload the valid, train and test folders and, the data.yaml and README text files?

[@Roboflow]

Dou you use manual download or pip package?

[@pcsolutionsezcloudsystems5929]

@@Roboflow I used manual download from the roboflow online app. I click the "Export Dataset" button. Then select "YOLO8" format. Then select "download zip to computer" option and finally click the "Continue" button. Trouble is, the snippet I copied/pasted into my Colab crashed when ran because it does not include a workspace name. :(

[@AbdulAziz-cj4hg]

Im a complete beginner, studied in art and design school, is there any recomendation that will guide me step by step learning about terms and all?

[@צדוקאברהם]

I am trying to download the final files to my pycharm and i can not do it.please, can you write over here the command i have to use for dowloading the final files to my google drive? in other words, how can i set my google drive as dircetory files and where i have to place it in the code in the notebook.thank you very much

[@Roboflow]

I see that we are getting a lot of similar comments over the last 2 days. I’m actually quite curious why is that. Haha can you create a new thread here: github.com/roboflow/notebooks/discussions/categories/q-a Asking about that. I’ll try to create a small tutorial on how to do it.

[@omerkaya5669]

I have uploaded video for object detection. However it takes a very long time to download the analyzed video. How can i shorten this time? Or how can i watch without downloading?

[@HoAnLocK18DN]

Hi Roboflow, i applied histogram equalization preprocessing image in my dataset to train yolov8 model then i will use this pretrain model to predict each frame in my web cam, so i want to ask you that how can i preprocessing my frame like roboflow's histogram equalization preprossing did.

[@abd-alrhmanabdallah8388]

How can I prepare dataset_params if I have a dataset structured as follows: Vid1/images and labels, Vid2/images and labels, and so on up to Vid100? The dataset consists of multiple videos, with each video stored in its own folder.

[@John-wx3zn]

do you have a tutorial on how to use roboflow?

[@ecaleks17]

So I’m new to all of this, I’m assuming this is all in python, is there any way to turn this from .pt files to .pb files

[@muhdnajhan886]

can you show with the coordinate please at the bounding box . I am very need that

[@JohnJevyAlimpolos]

is there custom train for pose estimation?

[@debeshbiswas1672]

while running inference on a custom dataset i get this error: TF-TRT Warning: Could not find TensorRT. After then it detects properly. I just don't get the visual of its detection!

[@aaronmalupet8329]

why the validation dataset images are trained?

[@Roboflow]

Those images are used to test model during the training.

[@notyetnotnowyouknow]

Hey what about pose detection training??

[@wordpreneur6059]

Hi, thanks for the great knowledge and information you have provided. Please could you help use the custom model created to create an app/UI using Streamlit or Flask with Webcamp?