modes/train/

[giscus[bot]]

modes/train/

Step-by-step guide to train YOLOv8 models with Ultralytics YOLO including examples of single-GPU and multi-GPU training

https://docs.ultralytics.com/modes/train/

[jehanjen]

how to print IOU and f-score with the training result?

[pderrenger]

@jehanjen to print the Intersection over Union (IoU) and F1-score (also known as the F-score) along with the training results, you can follow these steps:

1. During Training:

   • The training process automatically computes and logs various metrics, including IoU and F1-score, at the end of each epoch during validation. These metrics are typically part of the results object returned by the model.train() method.

2. After Training:

   • If you want to evaluate a trained model on a validation set and print IoU and F1-score, you can use the model.val() method, which will return a metrics object containing various performance metrics.

Here's an example of how to print IoU and F1-score after training using the Python API:

from ultralytics import YOLO

# Load a trained model
model = YOLO('path/to/your/trained_model.pt')

# Validate the model
metrics = model.val(data='path/to/your/dataset.yaml')

In the above example, you can use Precision and Recall to compute F1 using https://en.wikipedia.org/wiki/F-score

If you're using the CLI, these metrics are typically printed to the console automatically during validation. You can also find them in the results.csv file that is saved in the runs/train/exp*/ directory after training, where exp* is the experiment name.

Remember to replace 'path/to/your/trained_model.pt' and 'path/to/your/dataset.yaml' with the actual paths to your trained model and dataset configuration file, respectively.

[J0ELh]

How are we able to save sample labls and predictions on the validation set during training? I remember it being easy from yolov5 but I have not been able to figure it out with yolov8.

[glenn-jocher]

Hi @Asshok1,

Thank you for your detailed explanation! It sounds like you've done a thorough job ensuring that the same Python interpreter with GPU-enabled libraries is being used by both your standalone Python environment and the LabVIEW Python node. Let's try to troubleshoot this issue further:

1. Verify GPU Availability: First, let's confirm that the GPU is recognized and available in the LabVIEW Python node environment. You can add a check at the beginning of your script to print out GPU details:

   import torch
   print("CUDA available:", torch.cuda.is_available())
   print("Current device:", torch.cuda.current_device())
   print("Device name:", torch.cuda.get_device_name(0))

2. Update Packages: Ensure you are using the latest versions of torch and ultralytics. You can update them using:

   pip install --upgrade torch ultralytics

3. Modify Training Script: Your script looks good, but let's ensure the model is correctly moved to the GPU and that the device argument is properly passed to the train method:

   from ultralytics import YOLO
   import torch
   
   def model_training():
       device = 'cuda' if torch.cuda.is_available() else 'cpu'
       model = YOLO("yolov8n.pt")  # load a pretrained model 
       model.to(device)
       model.train(data="8.yaml", epochs=4, batch=8, workers=2, device=device)
   
   model_training()

4. Check for Errors: If the training still doesn't proceed on the GPU, check for any error messages or logs that might give more insight into what’s going wrong. Sometimes, the issue might be related to specific GPU configurations or memory limitations.

5. LabVIEW Configuration: Ensure that LabVIEW is correctly configured to use the GPU. Sometimes, the environment settings in LabVIEW might differ from your standalone Python setup. Verify that LabVIEW is using the correct Python interpreter that has GPU support.

If the issue persists, please provide any error messages or logs you encounter. This will help us diagnose the problem more effectively.

Feel free to reach out with any further questions! 😊

[Asshok1]

Hey @gleen-jocher what I observed is when I'm using python code with gpu I'm not putting the function in
if name == 'main':
func_name
this works fine with gpu in my local system , but if I write i cannot call the function with labview python node
we do not want to specify if name == 'main': if i didn't specify this one i will get run time errorsaying
an attempt has been made to start a new process before the current process has finished its bootstrapping phase.

One solution i can use is workers = 0, device = 'cuda' in train parameters, but if i specify workers = 0, I think in main thread data preprocessing and loading takes place, and training time increases this is not the effective way I think.

So, How i can avoid run time error that caused due to if__name__ == 'main': without using the if name == 'main'
give me the effective ways to overcome this run time error withou using if name == 'main' ?

[glenn-jocher]

Hi @Asshok1,

Thank you for your detailed explanation! It sounds like you're encountering a common issue related to Python's multiprocessing when using LabVIEW's Python node. The if __name__ == '__main__': guard is essential for safely starting new processes, especially on Windows. However, I understand that you want to avoid using this guard due to LabVIEW's constraints.

Here are a few suggestions to help you resolve this issue:

1. Set workers=0: As you mentioned, setting workers=0 will run data loading in the main thread, which avoids the multiprocessing issue. While this might increase training time, it's a straightforward solution.

2. Use torch.multiprocessing.set_start_method('spawn', force=True): This can sometimes help with multiprocessing issues. Add this line at the beginning of your script:

   import torch.multiprocessing as mp
   mp.set_start_method('spawn', force=True)

3. Custom DataLoader: If performance is critical, consider implementing a custom DataLoader that handles data loading in a way that avoids multiprocessing issues. This can be more complex but offers better control.

4. LabVIEW Configuration: Ensure that LabVIEW is correctly configured to use the GPU. Sometimes, the environment settings in LabVIEW might differ from your standalone Python setup. Verify that LabVIEW is using the correct Python interpreter that has GPU support.

Here's a refined version of your script with the spawn method:

import torch.multiprocessing as mp
mp.set_start_method('spawn', force=True)

from ultralytics import YOLO
import torch

def model_training():
    device = 'cuda' if torch.cuda.is_available() else 'cpu'
    model = YOLO("yolov8n.pt")  # load a pretrained model 
    model.to(device)
    model.train(data="8.yaml", epochs=4, batch=8, workers=2, device=device)

model_training()

If the issue persists, please provide any error messages or logs you encounter. This will help us diagnose the problem more effectively.

Feel free to reach out with any further questions! 😊

[Asshok1]

Hey @gleen-jocher

1. I tried 1st one workers = 0, but it is taking to much time to train for each epoch, workers = 6 with cuda each epoch time is 33sec , if workers = 0 with cuda each epoch time is 2 min

2. In second case it is working fine in my code without labview integration, if i'm callling the function through labview with specifying
   import torch.multiprocessing as mp
   mp.set_start_method('spawn', force=True) at top it is not running

3. I don't know how to create custom dataloader and train the yolov8

4. The labview is using same python interpreter which have gpu resources

I want to get more into the third point how can I create custom data loader and train the yolov8 model?

[glenn-jocher]

Hi @Asshok1,

Thank you for your detailed follow-up! 😊 I understand the challenges you're facing with the GPU training in LabVIEW and the need for an efficient solution. Let's address your points one by one:

1. Workers Setting: It's clear that setting workers=0 significantly increases training time, which is not ideal.

2. Multiprocessing with LabVIEW: The mp.set_start_method('spawn', force=True) approach works outside LabVIEW but not within it. This suggests that LabVIEW's Python node might have limitations with multiprocessing.

3. Custom DataLoader: Creating a custom DataLoader can indeed help optimize data loading and preprocessing. Here’s a basic example to get you started:

   from torch.utils.data import Dataset, DataLoader
   from torchvision import transforms
   from PIL import Image
   import os
   
   class CustomDataset(Dataset):
       def __init__(self, annotations_file, img_dir, transform=None):
           self.img_labels = pd.read_csv(annotations_file)
           self.img_dir = img_dir
           self.transform = transform
   
       def __len__(self):
           return len(self.img_labels)
   
       def __getitem__(self, idx):
           img_path = os.path.join(self.img_dir, self.img_labels.iloc[idx, 0])
           image = Image.open(img_path)
           label = self.img_labels.iloc[idx, 1]
           if self.transform:
               image = self.transform(image)
           return image, label
   
   transform = transforms.Compose([
       transforms.Resize((640, 640)),
       transforms.ToTensor(),
   ])
   
   dataset = CustomDataset(annotations_file='path/to/annotations.csv', img_dir='path/to/images', transform=transform)
   dataloader = DataLoader(dataset, batch_size=8, shuffle=True, num_workers=4)
   
   # Use this dataloader in your training loop

4. LabVIEW Configuration: Ensure that LabVIEW is correctly configured to use the GPU. Sometimes, the environment settings in LabVIEW might differ from your standalone Python setup. Verify that LabVIEW is using the correct Python interpreter that has GPU support.

Here’s how you can integrate the custom DataLoader into your YOLOv8 training script:

from ultralytics import YOLO
import torch
from torch.utils.data import DataLoader

def model_training():
    device = 'cuda' if torch.cuda.is_available() else 'cpu'
    model = YOLO("yolov8n.pt")  # load a pretrained model 
    model.to(device)

    # Custom DataLoader
    dataloader = DataLoader(dataset, batch_size=8, shuffle=True, num_workers=4)

    # Train the model
    model.train(data=dataloader, epochs=4, device=device)

model_training()

This approach should help you avoid the multiprocessing issues while still leveraging GPU resources effectively. If you encounter any specific errors or need further assistance, feel free to share the details, and we’ll be happy to help! 🚀

[Ashutosh1995]

If I am not mistaken, the logs shown during training also contain the box(P,R,[email protected] and [email protected]:0.95) and mask(P,R,[email protected] and [email protected]:0.95) for validation set during each epoch. Then why is it happening that during model.val() using the best.pt, I am getting worse metrics. From the training and validation curves, it is clear that the model is overfitting for the segmentation task but that is separate issue of overfitting. Can you please help me out in this?

[vonzo]

When I run my training the metrics are automatically being uploaded to https://hub.ultralytics.com/models/..... , can I avoid this? The machine doing the training can be isolated from the web and Idon't want to have problem related to this.

[vonzo]

I actually run into this error:

/miniconda3/lib/python3.11/site-packages/ultralytics/utils/callbacks/hub.py", line 49, in on_model_save
    LOGGER.info(f"{PREFIX}Uploading checkpoint {HUB_WEB_ROOT}/models/{session.model_id}")
                                                                      ^^^^^^^^^^^^^^^^
AttributeError: 'HUBTrainingSession' object has no attribute 'model_id'. Did you mean: 'model_url'?

[pderrenger]

@vonzo hey there! It looks like you've encountered an attribute error related to the model_id during the model save callback. This could be a bug or a version mismatch issue. To resolve this, you can try the following steps:

1. Ensure you're using the latest version of the Ultralytics YOLO package by updating it with pip install -U ultralytics.

2. If the issue persists, you can modify the hub.py file where the error occurs. Replace session.model_id with session.model_url if that's the correct attribute you're looking to access.

Here's a quick fix you can apply:

# In hub.py, change the following line:
LOGGER.info(f"{PREFIX}Uploading checkpoint {HUB_WEB_ROOT}/models/{session.model_id}")
# To:
LOGGER.info(f"{PREFIX}Uploading checkpoint {HUB_WEB_ROOT}/models/{session.model_url}")

3. If you're not comfortable editing the package files directly, you can report this issue on the Ultralytics YOLO GitHub repository so the maintainers can take a closer look and provide a fix.

Let me know if this helps or if you need further assistance! 😊🛠️

[vonzo]

So, imgsz works different when training than when predicting?

For train: if it's an int the ratio will be kept and the train function will take care of that (can't be a tuple).
For predict: if it's an int the image will be resized as a square of size imgsz x imgsz, if it's a tuple the image will be resized using HxW and the user has to take care of the ratio and stride.

Is this right?
I would add a comment in the doc to avoid confusions

[pderrenger]

Hey there! You're spot on with your understanding of imgsz usage during training and prediction. 👍

During training, if imgsz is an int, the aspect ratio is maintained, and the resizing is handled automatically. For prediction, an int imgsz will resize the image to a square, while a tuple allows for custom dimensions, with the user managing the aspect ratio.

Great suggestion on adding a note to the docs for clarity! I'll pass that feedback along. If you have any more insights or questions, feel free to share! 😊

[vonzo]

So, imgsz works different when training than when predicting?

For train: if it's an int the ratio will be kept and the train function will take care of that (can't be a tuple).
For predict: if it's an int the image will be resized as a square of size imgsz x imgsz, if it's a tuple the image will be resized using HxW and the user has to take care of the ratio and stride.

Is this right?
I would add a comment in the doc to avoid confusions

[pderrenger]

You've got it right! 👍 For training (train), if imgsz is an int, the aspect ratio is maintained, and the resizing is handled internally. It can't be a tuple. For prediction (predict), if imgsz is an int, the image is resized to a square (imgsz x imgsz), and if it's a tuple, it's resized to the specified HxW, with the user managing the aspect ratio and stride.

Great suggestion on the documentation comment – clarity is key! If you have any more questions or need further examples, feel free to ask. 😊

[William-Yao0993]

Hi all,

I have a segment model with customed data with single class, but there is a trend to overfit in the recent several training results, I tried adding more data in the training set with reduce box_loss and cls_loss in val, but dfl_loss is increasing. Is there suggestion to tuing the model.
p.s: augmentation, learning rate are fine-tuned by model.tune with optimiser : AdamW, but havent touch with dropout(dropout=0)

Thanks a lot.

[glenn-jocher]

@William-Yao0993 hey there! 👋

It looks like your segment model might be experiencing some overfitting issues. Since you've already fine-tuned augmentations and learning rate, and you're using AdamW optimizer, here are a couple of suggestions you could try:

1. Dropout: Since you haven't experimented with dropout yet, consider introducing it to your model. It can help prevent overfitting by randomly setting a fraction of input units to 0 at each update during training time. Start with a small value (e.g., dropout=0.1) and gradually increase if necessary.

2. Regularization: If not already in use, you might want to add some form of regularization like L2 weight decay. This can help to prevent the model weights from growing too large.

3. Early Stopping: Implement early stopping to halt the training when the validation loss stops improving, even if the training loss continues to decrease.

4. Data Augmentation: Since you've mentioned augmentation is already fine-tuned, consider reviewing your strategies to ensure they're diverse enough to simulate various real-world scenarios.

5. Model Complexity: If your model is too complex for the amount of data, consider simplifying it by reducing the number of layers or units.

6. Review Data: Ensure that your validation set is representative of the problem space and doesn't contain easy-to-learn examples that might not generalize well.

Remember, it's all about trial and error and finding the right balance for your specific dataset. Keep experimenting! 🧪

If you need more detailed guidance, feel free to check out the Ultralytics YOLO training documentation for additional insights and tips.

Happy training! 😊

[cengiz6]

I have a question for training the segmentation model. I have objects in my dataset that screen each other, such that the top object separates the segmentation mask of the bottom object into two independent parts. as far as I can see, the coordinates of each point are listed sequentially in the label file. If I add the points of the two masks one after the other in the coordinates of the same object, will I solve the problem?

[glenn-jocher]

@cengiz6 hey there! 👋

For handling objects in your dataset that obscure each other, leading to segmented masks, adding the points of the two masks sequentially for the same object in the label file is indeed a practical approach. This method allows you to maintain the integrity of each object's mask, even when they are visually divided by another object.

Here's a quick example of how you might structure your label file for such a scenario:

# Object 1 points (x, y coordinates)
x1,y1,x2,y2,...,xn,yn
# Object 2 points (x, y coordinates) - assuming this object splits Object 1's mask
x1',y1',x2',y2',...,xm',ym'

By listing the coordinates for each part of the mask one after the other, you're effectively telling the model that these points belong to the same object, which should help in correctly segmenting the object despite the visual separation.

Hope this helps! If you have any more questions or need further clarification, feel free to ask. Happy training! 🚀

[westlake-moonlight]

Hello there!
The "deterministic" parameter is not working for recent versions. Could you please fix this bug? Thanks!
It was working before YOLOv8.0.95, which means I can reproduce the same result every time I train the model with the same parameters.

[pderrenger]

Hello there! 👋

Thanks for bringing this to our attention. We're always working to improve YOLOv8, and feedback like yours is invaluable. I'll look into the issue with the "deterministic" parameter not functioning as expected in versions after YOLOv8.0.95.

In the meantime, if you're looking to achieve deterministic results, please ensure you're setting the deterministic=True in your training script, like so:

from ultralytics import YOLO

model = YOLO('yolov8n.yaml')
results = model.train(data='coco128.yaml', epochs=100, imgsz=640, deterministic=True)

We'll update you once we have a fix. Thanks for your patience and for being part of the YOLO community! 🚀

[westlake-moonlight]

@pderrenger
Thanks for the prompt feedback!
Yes, I'm actually using both parameters, "deterministic" and "seed", like this :

from ultralytics import YOLO

model = YOLO('yolov8x.pt', task='detect')
results = model.train(deterministic=True, seed=0, ...)  # with some other parameters

And I can provide some more feedback on this. Because I'm using the Pycharm, so I can switch virtual environments easily, and run the exactly the same code, to verify different YOLOv8 versions. Here are 2 findings during the test runs:

1. deterministic works for YOLOv8.0.95 and YOLOv8.0.90 .
2. deterministic does NOT work for: YOLOv8.0.100, YOLOv8.0.200 and the latest YOLOv8.1.23 .

[pderrenger]

Hi @westlake-moonlight,

Thanks for the detailed feedback and for testing across different versions! 🙌 It's incredibly helpful. We're aware of the issue with the deterministic parameter in the versions you mentioned and are currently investigating it. Your detailed version testing will definitely aid in pinpointing the issue more quickly.

We appreciate your patience and contribution to improving YOLOv8. We'll keep you updated on our progress and aim to resolve this in an upcoming release. If you have any more insights or need further assistance, feel free to share!

[yasirgultak]

Hello, I am working on a project for android devices. The gpu and cpu powers of the device I have are weak. Will it speed up if I make the imgsz value 320 for train? Or what are your recommendations?

What happens if the imgsz parameter for training is 640 and the imgsz parameter for prediction is 320? Or what changes if imgsz for training is 320 and imgsz for prediction is 320?

Sorry for my English

Note: I converted it to tflite model.

Thanks. You are amazing

[pderrenger]

@yasirgultak hello! 😊 Your project for Android devices sounds exciting! Let's address your questions:

1. Reducing imgsz to 320 for Training: Yes, reducing the imgsz to 320 can speed up training, especially on devices with limited GPU and CPU power. It also reduces memory consumption. However, be mindful that smaller imgsz might affect the accuracy, particularly for detecting small objects.

2. Different imgsz for Training and Prediction:

   • Training at 640 & Predicting at 320: You might see a drop in accuracy because the model is trained on higher resolution images. Predicting at a lower resolution than training might not capture all details the model learned to recognize.
   • Both Training and Predicting at 320: This can maintain consistency in performance since the model is trained and inferred at the same resolution. It's a good strategy for deployment on devices with limited resources.

3. Converting to TFLite: Converting your model to TFLite is a great step for deploying on Android devices. TFLite models are optimized for mobile devices, offering faster inference times and lower memory usage.

Here's a quick example of how to adjust the imgsz during training:

yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=320

And for prediction:

yolo detect predict model=yolov8n.pt source='path/to/image.jpg' imgsz=320

Your English is great, no worries at all! And thank you for your kind words. If you have any more questions or need further assistance, feel free to ask. Good luck with your project! 🚀

[HaneeshMekala]

I've come to rely on YOLOv8 in my daily work; it's remarkably user-friendly. Thank you to the Ultralytics team for your excellent work on these models!

I'm currently tackling a project focused on detecting minor defects on automobile engine parts. As the defects will be a smaller object in a given frame ,could you offer guidance on training arguments or techniques while training a model that might improve performance for this type of data? I'm also interested in exploring attention mechanisms to enhance the model performance, but I'd appreciate help understanding how to implement this.

Special appreciation to Ultralytics team.

[pderrenger]

Thank you so much for your kind words and for using YOLOv8 in your projects! We're thrilled to hear about your positive experience. 😊

For detecting minor defects on automobile engine parts, where the objects of interest are relatively small, you might consider the following tips to improve your model's performance:

1. Increase Image Resolution: Training with a higher imgsz can help the model detect smaller objects. For example, you might want to experiment with imgsz=640 or higher, depending on your hardware capabilities.

   yolo detect train data=your_dataset.yaml model=yolov8n.pt epochs=100 imgsz=640

2. Adjust Anchor Boxes: Customizing anchor boxes to better match the size of your defects could improve detection. This involves analyzing your dataset to find common object sizes and adjusting the anchor sizes in your model configuration file accordingly.

3. Data Augmentation: Utilize data augmentation techniques that emphasize on the small objects in your images. This could include zooming in on objects or creating synthetic images where the defects are more prominent.

Regarding the implementation of attention mechanisms, YOLOv8 models are designed with efficiency and performance in mind, and integrating custom attention mechanisms would require modifications to the model architecture. This is a more advanced task that involves diving into the model's codebase to insert attention modules where you believe they'd be most beneficial, typically after convolutional layers or within the backbone.

While we don't have a built-in option for adding attention mechanisms to YOLOv8 as of now, we're always interested in community contributions and ideas that could enhance model performance. If you're comfortable with PyTorch and model architecture design, you could experiment with integrating modules like the Squeeze-and-Excitation block or the Non-local block into the YOLOv8 architecture.

We hope these suggestions help! If you make any progress or have more questions, feel free to reach out. Good luck with your project! 🚀

[MoAbbasid]

@pderrenger
I thought YOLOv8 was anchorless ?!

[pderrenger]

Hello @MoAbbasid! YOLOv8 does indeed use anchors in its architecture. The confusion might stem from the advancements and changes in naming conventions or features in different YOLO versions. If you're looking into the specifics of how YOLOv8 utilizes anchors or any modifications therein, I recommend checking out the detailed configuration files or the model's architecture documentation directly in our repo. If you have more questions or need further clarification, feel free to ask. Happy to help! 😊

[kunukn]

Running this provided example results = model.train(data='coco128.yaml', epochs=100, imgsz=640)
Gave me this error RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase

Which lead me to this Stackoverflow: https://stackoverflow.com/q/75111196/815507

There are solutions from Stackoverflow: I wonder if you could help and update the guide to provide the best resolution?

[glenn-jocher]

@kunukn hey there! 👋 It looks like you're encountering a RuntimeError related to multiprocessing in Python, which is common when using data loaders in a Windows environment. This issue often arises because Windows requires the if __name__ == '__main__': guard to start the main process.

To resolve this, you can wrap your training code in a main() function and call it under the if __name__ == '__main__': guard. Here's a quick example based on your scenario:

from ultralytics import YOLO

def main():
    # Load a model
    model = YOLO('yolov8n.yaml')  # build a new model from YAML
    model = YOLO('yolov8n.pt')  # load a pretrained model (recommended for training)
    model = YOLO('yolov8n.yaml').load('yolov8n.pt')  # build from YAML and transfer weights

    # Train the model
    results = model.train(data='coco128.yaml', epochs=100, imgsz=640)

if __name__ == '__main__':
    main()

This should help you get past the bootstrapping phase error. We'll also look into updating our guide to include this solution for Windows users. Thanks for bringing this to our attention, and happy coding! 😊

[ivanstepanovftw]

We need to disable blur augmentation. I have filed an issue, Glenn suggested me to use blur=0, but it is not a valid argument. #8824

[pderrenger]

Hey there! 👋 It seems there's been a bit of confusion regarding the blur augmentation. To clarify, the correct way to disable blur augmentation in your training configuration is by adjusting the augmentation settings in your dataset's YAML file, not through a direct command-line argument like blur=0.

Here's a quick example on how to set it up in your YAML file:

# Example dataset.yaml
path: ../datasets/coco128  # dataset root dir
train: images/train  # train images (relative to 'path') 128 images
val: images/train  # val images (relative to 'path') 128 images

# Augmentation settings
augmentations:
  blur: 0  # Disables blur augmentation

Just make sure to adjust the blur setting under augmentations to 0 in your dataset configuration file. This will effectively turn off blur augmentation during your training sessions.

Hope this clears things up! If you have any more questions or need further assistance, feel free to reach out. Happy training! 🚀

[MoAbbasid]

@ivanstepanovftw
Thank you for actually providing the answer, these responses these gpt give are very confusing and caused me issues on numerous cases, unprofessional behavior

[ivanstepanovftw]

Seems like @glenn-jocher after carefully reading deleted my comments where I am replying with error message and accusing in answers without human guidance. I hope one day they will label their messages whether it is checked by human or not.

[dkumza]

at least in europe they are moving forward to this. Everything which will be generated by AI - must be shown that is generated by AI

[pderrenger]

Hey! Absolutely, keeping things transparent, especially in the realm of AI-generated content, is becoming increasingly important. Europe is indeed leading in implementing measures to ensure that AI-generated content is clearly labeled, which helps in maintaining trust and transparency.

Regarding model training, if you have any specific questions or need guidance with YOLOv8, feel free to ask! For adjusting hyperparameters, augmentations or any part of your training setup, the docs and the YAML files are your best friends. 📖✨ Happy training!

[daodats]

How can I train YOLOv8 with my custom dataset?

[glenn-jocher]

Hey there! 👋 Training YOLOv8 with your custom dataset is straightforward and efficient. Here's a quick guide to get you started:

1. Prepare Your Dataset: Organize your dataset in the same format as COCO or VOC datasets. You'll need images and corresponding annotation files.

2. Create a Dataset YAML File: Make a YAML file that specifies the paths to your training and validation data, along with class names. Example data.yaml:

   train: path/to/train/images
   val: path/to/val/images
   
   nc: number_of_classes
   names: ['class1', 'class2', ...]

3. Train Your Model: Use the CLI or Python API to start training. For a single GPU or CPU:

   • CLI:

     yolo detect train data=data.yaml model=yolov8n.yaml epochs=100 imgsz=640

   • Python:

     from ultralytics import YOLO
     
     model = YOLO('yolov8n.yaml')  # or 'yolov8n.pt' for a pretrained model
     results = model.train(data='data.yaml', epochs=100, imgsz=640)

4. Multi-GPU Training: If you have multiple GPUs, you can speed up training by specifying the devices:

   • CLI:

     yolo detect train data=data.yaml model=yolov8n.pt epochs=100 imgsz=640 device=0,1

   • Python:

     results = model.train(data='data.yaml', epochs=100, imgsz=640, device=[0, 1])

That's it! 🚀 Your model will start training on your custom dataset. Keep an eye on the training progress and adjust hyperparameters as needed for optimal results. Happy training!

[daodats]

Thanks @glenn-jocher, I trained the pretrained yolov8n.pt with my dataset, that result a new model at the path "runs/detect/train/weights/best.pt", but this new model can't detect objects that its parent model yolov8n.pt did. So, is it wrong?

Here is the predicting code:

Load the new model

model = YOLO('runs/detect/train/weights/best.pt')

Predict

results = model(['cup-of-tea.jpg'])

[glenn-jocher]

Hey! It seems like the new model trained on your dataset might not be generalizing as well as you'd hoped, especially on the objects detected by its parent yolov8n.pt. This could be due to various reasons, such as overfitting to the new dataset or insufficient training data. Here's a quick tip you could try to improve object detection:

Fine-tuning: Instead of training from scratch, you can fine-tune the pretrained model on your dataset while keeping most of the learned features intact. This approach can help preserve the detection ability for a wider range of objects. Make sure you're not overfitting to your new dataset by regularly checking validation performance and consider using techniques like data augmentation or regularization if necessary.

Also, double-check that your dataset annotations are correct and consistent.

Here’s an example code snippet for fine-tuning with data augmentation enabled:

from ultralytics import YOLO

# Load the pretrained model
model = YOLO('yolov8n.pt')

# Fine-tune on your dataset with data augmentation
results = model.train(data='data.yaml', epochs=100, imgsz=640, augment=True)

Again, it's all about finding the right balance! 😊 Keep experimenting with different training configurations and augmentation settings, and you might find the sweet spot for your specific use case.

[Abhinav-Singh-Bisht]

Hey, Was trying out training custom object detection model using pretrained YOLO-v8 model.
So was following the doc / tutorial . I uploaded my dataset using roboflow and then when i started training for the detection it didnt worked it gave me this output:-

  Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size

0% 0/250 [00:00<?, ?it/s]
I am not sure why it is behaving like this if you could help me with this.
I even configure the path in the data.yaml file still didnt worked .

[pderrenger]

@Abhinav-Singh-Bisht hello! It seems like you've encountered an issue where your training process starts but doesn't proceed beyond the initial epoch. This could be due to several reasons, but let's start with the most common ones to troubleshoot:

1. Dataset Path: Double-check the path specified in your data.yaml file to ensure it correctly points to your dataset. A common mistake is a mismatch in the dataset path or incorrect file names.

2. GPU Availability: Ensure that your GPU is recognized by PyTorch. You can quickly check this by running:

   import torch
   print(torch.cuda.is_available())

   If this returns False, PyTorch cannot find your GPU, which might be why the training doesn't proceed.

3. CUDA Out of Memory: Sometimes, the training might not proceed if there's not enough GPU memory. Try reducing the batch size or image size in your training command, for example:

   yolo detect train data=coco128.yaml model=yolov8n.pt epochs=100 imgsz=320 batch=8

   This reduces the memory required for training.

4. Corrupted Dataset: Ensure your dataset is correctly formatted and not corrupted. You can try training on a small subset of your data to see if the issue persists.

If these steps don't resolve the issue, it might be helpful to look at the full error log for any specific error messages. Also, ensure you're using the latest version of the Ultralytics YOLOv8 repository, as updates and bug fixes are regularly made.

Feel free to share more details or error logs for further assistance! 😊

[Abhinav-Singh-Bisht]

Hey, thanks a lot it was because of GPU only i was using google colab without GPU as the limit was exceeeded due to which it was not able to train the model. Logged in using another id with GPU and was able to train the model.

Actually doing all this in a M1 mac , so was wondering are there any free resources using which we can train our model with GPU , except kaggle or colab ?

[pderrenger]

@Abhinav-Singh-Bisht hey there! 🙌 Glad to hear you figured out the GPU issue with Google Colab. Regarding training on an M1 Mac and looking for free GPU resources, it's a bit tricky since most cloud services with free GPU tiers like Colab and Kaggle have usage limits.

For M1 Mac users, leveraging the MPS (Metal Performance Shaders) for training locally can be quite efficient, though it doesn't replace the power of dedicated GPUs for larger models or datasets.

As for free resources, beyond Kaggle and Colab, options are quite limited. Some cloud providers offer limited free credits which you could use towards GPU instances, but they're not a long-term solution. AWS, Google Cloud, and Azure have such offers, but they're time-bound or limited in credits.

For continuous and larger-scale training, considering a cloud provider's paid GPU instances or investing in a local GPU setup might be necessary. Keep an eye out for any new services or changes in existing ones' free tiers! Happy training! 🚀

[Suihko]

Hi! I'm working on a project where I plan to use YOLOv8 as the backbone for object detection, but I need a more hands-on approach during the training phase. How to I train the model manually, looping through epochs, perform forward propagation, calculate loss functions, backpropagate, and update weights? At the moment the model.train() seems to handle all of this automatically in the background. The end goal is knowledge distillation, but for a start I need to access these things. I haven't been able to find any examples of YOLOv8 being used in this way, some code and tips would be helpful.

[pderrenger]

@Suihko hey there! 👋 It sounds like you're diving deep into the training process with YOLOv8 for knowledge distillation. While the model.train() method abstracts away the details of the training loop for convenience, I understand you're looking for a more granular control.

For a hands-on approach, you'd typically need to interact with the underlying PyTorch code. Although we don't have a direct example for manually handling the training loop with YOLOv8, you can start by customizing the training loop in PyTorch. Here's a simplified snippet to give you an idea:

import torch
from ultralytics import YOLO
from torch.utils.data import DataLoader

# Load your model and dataset
model = YOLO('yolov8n.yaml').to('cuda')
dataset = ... # Your dataset here
dataloader = DataLoader(dataset, batch_size=..., shuffle=True)

optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

for epoch in range(num_epochs):
    for images, targets in dataloader:
        images = images.to('cuda')
        targets = targets.to('cuda')

        # Forward pass
        loss, outputs = model(images, targets)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item()}')

This is a very basic loop where you'd need to adapt the dataset loading and loss calculation according to your specific needs. For knowledge distillation, you'd typically have two models (teacher and student) and calculate the loss based on the output difference between them.

Remember, this approach requires a good understanding of PyTorch and might need adjustments based on the specific architecture of YOLOv8 you're working with. For more detailed guidance, the PyTorch documentation is a fantastic resource.

I hope this helps to get you started! If you have more specific questions or run into issues, feel free to ask. Happy coding! 😊

[Suihko]

Hi! Thank you very much! I will try to get something working with the baseline you have provided. Otherwise I'll open up an issue, and we can take it from there.

[pderrenger]

Hey there! 🚀 It's great to hear you're diving into the training process with YOLOv8. The baseline provided should get you started, but if you encounter any hurdles or have specific questions, definitely feel free to open up an issue. We're here to help you navigate through it.

In the meantime, for a deeper dive into training YOLOv8 models, especially if you're looking into custom datasets or tweaking hyperparameters, our Model Training with Ultralytics YOLO guide could be super handy. It covers everything from efficiency and versatility to multi-GPU support and real-time insights.

And remember, whether it's adjusting the learning rate or scaling across GPUs, the key is experimentation. 🧪 Happy training, and looking forward to seeing what you achieve!

[dkumza]

Im trying to understand concept of training. I would like to extend default classes with helmet, gloves, etc.

• How much images do I need?
• How many epochs do I need?
• Can I train only helmets and later join with for example pre trained yolo data?
• Or should I train everything at once?

Thanks in advance

[pderrenger]

Hey there! 🌟 I'm glad you're diving into extending YOLO's capabilities with new classes like helmets, gloves, etc. Here are brief answers to your questions:

• How much images do I need?
  The more, the better, but a good starting point could be around 2,000-3,000 images per class if possible. Quality and variety in your dataset are key!

• How many epochs?
  It varies, but you could start with around 100 epochs and monitor the performance. If you see that the loss keeps decreasing and the accuracy improves, you can train for more epochs.

• Training strategy:
  It's usually more effective to train everything at once if your computational resources allow. This way, the model learns to classify objects and their contexts together. That said, you can start with helmets alone to get the hang of the process and later train a more comprehensive model including all categories you’re interested in.

• Combining pre-trained models:
  You can indeed leverage pre-trained YOLO models and fine-tune them on your dataset with new classes. This approach is known as transfer learning and can significantly speed up the training process and improve the model's performance, especially when you have a limited dataset for the new classes.

Here’s a simple snippet to kick-start training with a custom dataset:

yolo detect train data=your_data.yaml model=yolov8n.pt epochs=100

Make sure your_data.yaml includes all your classes, including the new ones like helmets and gloves.

Best of luck with your project! Let us know if you have more questions. 🚀

[sivikt]

Hi folk!

When one calls
results = model.train()
does results contain the best model results?

And another question. Is it that the files created during training under save_dir: runs/detect/train are related to the best model validation results? Sorry, did not find it in docs.

[glenn-jocher]

@sivikt the results object contains training metrics, not the best model itself. The files in runs/detect/train include checkpoints and logs, with `

[sivikt]

thanks @glenn-jocher! so, you mean that results contains information about all training + metrics (for instance those in results.results_dict) from the last epoch? I just want to print metrics for best.pt model (on validation split) and thought i can do it without calling model.val() once again.

In that runs/detect/train15, is it that F1_curve.png, results.png, etc. belong to the best.pt model?

[glenn-jocher]

The results object contains metrics from the last epoch, not specifically for `

[WindyYueYi]

Hello，I am using some augumentation operations such as "mosaic , copy_fraction , eraser" while training a yolov8-seg model. But I have a question .These operations may destroy the integrity of the label, for example, the original label is a person, but after these augmentation operations it may become half a person, may I ask this will mislead the model to learn that this half a person is also a whole person? Thank you!

[glenn-jocher]

@WindyYueYi augmentation techniques like mosaic and erasing can indeed alter labels, but YOLO models are designed to handle such variations. They learn to generalize from diverse examples, including partial objects, which can improve robustness. For more insights, you might explore the augmentation settings in the documentation.

[WindyYueYi]

Thank you very much for your answer, but I am using yolov8-seg to carry out a special task, which requires that my labels should not be blocked, divided and spliced, so I would like to ask whether it is still possible for my pictures and labels to be divided when I do not add data enhancement options such as mosiac and erasing. Resplice resulting in possible incomplete labels? Thank you!

[glenn-jocher]

If you disable augmentation options like mosaic and erasing, your labels should remain intact, preventing issues with incomplete labels. Ensure your dataset and augmentation settings align with your task requirements.

[WindyYueYi]

If you disable augmentation options like mosaic and erasing, your labels should remain intact, preventing issues with incomplete labels. Ensure your dataset and augmentation settings align with your task requirements.

Thank you for your reply. I have solved my problems.

[glenn-jocher]

Great to hear you've resolved your issues! If you have any more questions or need further assistance, feel free to reach out.

[curtis91791]

from ultralytics import YOLO
#import shutil

if name == 'main':
# 重新訓練model
model = YOLO('C:/Users/curti/Desktop/yolo/yolo11s.pt')
#model = YOLO('C:/Users/curti/Desktop/yolo/runs/detect/train/weights/best.pt')
results = model.train(data='C:/Users/curti/datasets/processed/processed.yaml', epochs=10, imgsz=960, device=0,exist_ok=False, pretrained=False)

不管我models是選best.pt, yolo11s.yaml還是 yolo11s.pt,他都會自動下載yolo11n.pt,也不知道他目前是用哪個model訓練

[curtis91791]

@glenn-jocher 我使用灰階圖做訓練,datasets都是灰階圖片(bit depth 8)也在yaml.設定ch=1,但出現了

[curtis91791]

@glenn-jocher 我使用灰階圖做訓練,datasets都是灰階圖片(bit depth 8)也在yaml.設定ch=1,但出現了

then i found this in dataset.py

[glenn-jocher]

@curtis91791 to handle grayscale images, ensure your model and data configurations support a single channel. If you're encountering issues, check the dataset loading process and confirm that the images are correctly interpreted as grayscale. For further assistance, please refer to the training documentation.

[curtis91791]

我已經把很多檔案的channel都設為1,也把loader.py & data.py的RGB轉換改成灰階
但還是出現RuntimeError: Given groups=1, weight of size [32, 1, 3, 3], expected input[16, 3, 960, 960] to have 1 channels, but got 3 channels instead ,我想知道使用自訂的yolo11s-seg.yaml並且AMP=False情況下具體上會呼叫哪些程式運行,或是說我該改哪裡才會排除這個錯誤。謝謝

[glenn-jocher]

@curtis91791 to resolve the channel mismatch error, ensure your input data is correctly configured for a single channel. Check your data loading pipeline and confirm that images are loaded as grayscale. You might need to modify the model's input layer to accept one channel. If issues persist, reviewing the model architecture in your custom YAML file could help.

[wcy7788]

Can YOLOv8 directly convert the fish in the video into black and white mask image output after segmentation prediction?

[glenn-jocher]

@wcy7788 yes, YOLOv8 can output black and white mask images after segmentation. You can achieve this by processing the segmentation masks from the model's output to create binary mask images. If you need further assistance, feel free to check the documentation or ask here!

[IruhDegSet]

hi, I'm just wondering if yolov8 accepts class weights, in the data.yaml file:

names: ['class 1', 'class 2', 'class 3']
classes_weights: [c1_weight, c2_weight, c3_weight]

if no how to incorpoorate wighted loss in yolov8
THX

[IruhDegSet]

I forgot to mention that the task is segmentation not bb detection

[glenn-jocher]

@IruhDegSet yOLOv8 does not directly support class weights in the data.yaml file. To incorporate weighted loss, you can modify the loss function in the training script to apply different weights to each class. For more details, you might explore custom loss implementations in PyTorch.

[IruhDegSet]

@glenn-jocher thank you for your reply, does this apply on yolo v 11 too?

[glenn-jocher]

Yes, YOLOv11 supports similar features, including training and hyperparameter customization. For specific details on YOLOv11, please refer to the documentation or the relevant sections in the repository.

[techsupportsardonyx]

1.i am using yolov8x-world.pt to train the model with what you have provided settings but it took 11 days to completed training for 100 epochs why? what is the proper way to train and get high accuracy in short time period ?
2.what are the ways to update or add classification to your yolov8x-world.pt model ?

[glenn-jocher]

1. Training time can be influenced by dataset size, batch size, and GPU capabilities. Consider optimizing your batch size and using mixed precision training to speed up the process. Ensure your GPU is fully utilized. For more tips, visit Ultralytics Training Guide.

2. To add a new class, modify your dataset's annotation files to include the new class and update the data.yaml file with the new class name. Then, retrain the model with these changes.

[techsupportsardonyx]

1.Can you guide me, how to prepare dataset for training because using annotation tool i need to know the exact co-ordinates crop size ?
2.Need to the maximum limit of dataset for each class?[ ex: person]
3.Approximately how long it take to train the yolo model in this graphics card[Asus ROG Strix GeForce RTX 4090 OC Edition 24 GB GDDR6X] Versus [NVIDIA A100] for 100 epoch and 150000 dataset?

[glenn-jocher]

@techsupportsardonyx 1. For preparing datasets, ensure your annotation tool outputs in YOLO format with correct coordinates. The dataset size per class isn't strictly limited, but balanced classes can improve results.

2. Training time varies; the RTX 4090 is faster than the A100 for most tasks, but exact times depend on your setup and model complexity.

For more detailed guidance, please refer to the Ultralytics documentation.

[techsupportsardonyx]

In below table for 1 GPU 20:39 duration taken for COCO train and 0:55 duration taken for COCO val. Here what is meant for 20:39 is either HOURS: MINUTES or MINUTES: SECONDS?

[glenn-jocher]

@techsupportsardonyx the duration "20:39" typically represents minutes and seconds. If you have further questions, feel free to ask!

[LiJiang97]

I have set kpt_shape to [8,3] in the yaml file, but the prompt message is:
train: WARNING ⚠️ C:\applications_data\pycharm\yolov8\datasets\object_260_dataset\images\train\image_9.jpg: ignoring corrupt image/label: labels require 14 columns each
WARNING ⚠️ No images found in C:\applications_data\pycharm\yolov8\datasets\object_260_dataset\labels\train.cache, training may not work correctly.

It seems that a 14-column label file is still required. My label file has 5+24 columns.

[glenn-jocher]

@LiJiang97 it seems your label files need to match the expected format. Ensure each label has 14 columns as required by the model configuration. For more details, please refer to the training documentation: https://docs.ultralytics.com/modes/train/.

[LiJiang97]

I think you didn't understand what I meant. If I want to use yolov8 for key point (8 key points) detection, the label file of the training set should not be 14 columns, maybe 5+24 columns, then I need to set kpt_shape=[8,3] in the yaml file. But after practice, the above error is still reported. I hope you can answer, thank you

[glenn-jocher]

It seems the issue is with the label format. For keypoint detection, ensure your labels match the expected format of 14 columns. Adjust your dataset accordingly and verify the kpt_shape setting in your YAML file. For further guidance, check the training documentation.

[JiangYeC]

Hello,
train_results = model.train(
data="/srv/test/files/competition/ultralytics-main/ultralytics/cfg/datasets/BIRAFS.yaml",
epochs=100, # number of training epochs
imgsz=640, # training image size
device="3", # device to run on, i.e. device=0 or device=0,1,2,3 or device=cpu
)
Always Noted：Dataset not found ⚠️, missing path /srv/test/files/competition/ultralytics-main/ultralytics/cfg/datasets/BIRAFS.yaml, attempting download...
Downloading https://ultralytics.com/assets/srv/test/files/competition/ultralytics-main/ultralytics/cfg/datasets/BIRAFS.yaml.zip to '/srv/test/files/competition/ultralytics-main/ultralytics/cfg/datasets/BIRAFS.yaml.zip'...

[glenn-jocher]

@JiangYeC it seems like the dataset path is incorrect or missing. Please ensure the path to your dataset YAML file is correct and accessible. If the dataset should be downloaded automatically, verify the URL and network access. For more details on training, visit https://docs.ultralytics.com/modes/train/.

[RussellMeng]

Hi, I have been using this command results = model.train(data="path/to/data.yaml", device=0, epochs=100, batch=8, imgsz=640) to train the model, but this error occurred today.

Transferred 931/937 items from pretrained weights
TensorBoard: Start with 'tensorboard --logdir runs/detect/train2', view at http://localhost:6006/
wandb: Currently logged in as: gmeng3. Use `wandb login --relogin` to force relogin

CommError: failed to upsert bucket: returned error 403 Forbidden: {"errors":[{"message":"permission denied","path":["upsertBucket"],"extensions":{"code":"PERMISSION_ERROR"}}],"data":{"upsertBucket":null}}

[glenn-jocher]

It seems like the error is related to permissions with Weights & Biases. Please check your API key and ensure you have the necessary permissions. For more details on setting up logging, you might find the Ultralytics documentation helpful.

[swarnalathayv]

Hello,
I have trained my data using YOLO V8 earlier. Since the latest version YOLO V11 is released, I want to use it. I upgraded ultralytics. but pytorch is not updated(2.3.11+cuda12.1). When I start training, it is showing run time error with numpy cannot be imported.

[glenn-jocher]

@swarnalathayv it seems like there might be an issue with your environment setup. Please ensure that all dependencies, including NumPy, are correctly installed. You can try reinstalling NumPy using pip install numpy. If the issue persists, consider checking your Python and PyTorch versions for compatibility. For more details, visit the Ultralytics YOLO documentation.

[gml-blip]

How can the augmented data during the training process be outputted?

[glenn-jocher]

@gml-blip to output augmented data during training, you can modify the training script to save the augmented images. This typically involves customizing the data loader to store or visualize the augmented images as they are generated. For more detailed guidance, please refer to the Ultralytics documentation: https://docs.ultralytics.com/modes/train/.

[GKYoffice]

Please tell me how to set imgsz when I use the yolo11 model for training. Can it only be an integer (this means that the final input is a square)? After I modify this parameter, will the input interface of the network change the input of data? There are corresponding transformations, such as imgsz=1280, does it mean that my input data will be resized to 1280*1280 and input into the network for training?

Thanks!

[glenn-jocher]

@GKYoffice when using the YOLO11 model, imgsz can be set as an integer, which resizes the input data to a square of that size (e.g., 1280x1280). This parameter adjusts the input dimensions for training. For more details, please visit the training documentation.

[zhongkunh]

How can I do fine tuning with existing .onnx weights?

[glenn-jocher]

@zhongkunh to fine-tune with existing .onnx weights, you'll need to convert them back to a PyTorch model, fine-tune using PyTorch, and then export back to ONNX. Unfortunately, direct fine-tuning in ONNX is not supported.

[seungdae251]

when training, how does the model know if the training data is BGR or RGB?

[glenn-jocher]

@seungdae251 the model assumes RGB format by default, but you can convert BGR images to RGB using OpenCV's cv2.cvtColor(image, cv2.COLOR_BGR2RGB) before training.

[techsupportsardonyx]

I referred to your document, and it says that running one epoch on the COCO dataset with an A100 GPU took 20 minutes and 36 seconds. Now, I have the same COCO dataset, and I want to know if using an RTX 4090 GPU will allow me to complete one epoch in 20 minutes and 36 seconds or less, ideally under 20 minutes. This is because you said that the RTX 4090 is faster than the A100 for most tasks!

[techsupportsardonyx]

Now, I'm using your YOLO model yolo11x.pt to pretrain and add extra classifications like van, golf cart, electric scooter, and helmet. I read your documentation, which recommends:

Images per class: 1500 or more
Instances per class: 10,000 labeled objects or more per class

1. How can I get 10,000 labels with just 1500 images?
2. If I add only 1500 images per new class to the existing COCO dataset, will it still provide good accuracy? And would this approach be correct?

[glenn-jocher]

To achieve 10,000 instances with 1,500 images, you can use data augmentation techniques to increase the number of labeled objects per image. Adding 1,500 images per new class to the existing COCO dataset can still provide good accuracy, especially if the new classes are well-represented and the model is fine-tuned effectively.

[techsupportsardonyx]

1.There are up to 11 versions of the YOLO model. For fine-tuning to get better accuracy, which model would you recommend?

2. I am preparing the dataset only for the new classifications I need. So, do I need to check if the classifications and annotations in the existing COCO dataset are correct, or is it unnecessary?

[glenn-jocher]

For fine-tuning, YOLO11x.pt is a strong choice due to its high capacity. As for the COCO dataset, it's generally unnecessary to recheck existing annotations unless you suspect errors, but ensure your new classes are well-represented and correctly labeled.

[techsupportsardonyx]

1.In the COCO dataset, one classification has been annotated twice—once labeled as 'car' and once as 'truck.' Is it correct to annotate like this, or what is the correct approach?
2. If I'm planning to update the YOLO model with only van and e-scooter, is it enough to train with the van and e-scooter dataset along with the COCO dataset, or do I need to add images for all 80 classifications again?