Change in the anchor boxes about yolov3 HOT 10 CLOSED

👋 Hello @Venatus6401, thank you for your interest in YOLOv3 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov3  # clone
cd yolov3
pip install -r requirements.txt  # install

Environments

YOLOv3 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv3 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv3 training, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

Introducing YOLOv8 🚀

We're excited to announce the launch of our latest state-of-the-art (SOTA) object detection model for 2023 - YOLOv8 🚀!

Designed to be fast, accurate, and easy to use, YOLOv8 is an ideal choice for a wide range of object detection, image segmentation and image classification tasks. With YOLOv8, you'll be able to quickly and accurately detect objects in real-time, streamline your workflows, and achieve new levels of accuracy in your projects.

Check out our YOLOv8 Docs for details and get started with:

pip install ultralytics

from yolov3.

My dataset would be the logodet-3k dataset. im planning on building a model for logo detection with increased number of anchor boxes to 4 or 5. Im familar on how to do with custom dataset i just need to know how to change it

from yolov3.

@Venatus6401 sure! To change the number of anchor boxes for YOLOv3, you will need to modify the model architecture and the corresponding anchor values.

1. Model architecture: In the cfg file (e.g., yolov3.cfg), you need to adjust the num_anchors parameter. For each scale, the num_anchors value represents the number of anchor boxes. Make sure to update it accordingly based on the number of anchor boxes you want (e.g., to 4 or 5).

2. Anchor values: In the same cfg file, you will find the anchors parameter. Update the values to match the shape of your anchor boxes. For example, if you have 4 anchor boxes, each represented by width and height, the anchors parameter should be set accordingly.

Please note that after modifying the cfg file, you will also need to adjust the code to handle the new anchor configurations. Make sure to update the model creation and training scripts accordingly.

I hope this helps! Let me know if you have any further questions.

from yolov3.

yea so here this is the only cfg file available this is where im finding trouble
and also if u dont mind can u give me some more information on what to change after i do my changes in my cfg file

from yolov3.

Hi @Venatus6401, thank you for reaching out!

To change the number of anchor boxes in YOLOv3, you will need to modify the model architecture and the corresponding anchor values.

In the provided screenshot, the yolov3.cfg file is open. To change the number of anchor boxes, you need to update the num_anchors parameter in the yolov3.cfg file. This parameter specifies the number of anchor boxes for each scale. For example, if you want to increase the number to 4 or 5, you would update the num_anchors value accordingly.

After making changes in the cfg file, you also need to modify the code to handle the new anchor configurations. This includes updating the model creation and training scripts to align with the new anchor settings.

Please let me know if you have any further questions or need more information. I'm here to help!

Glenn Jocher

from yolov3.

there is no such thing as that but in the yaml file it is present

should i change it here

and how to check which yaml file in my train.py file

from yolov3.

@Venatus6401 the yolov3.cfg file you are referring to is written in a plain text format and not a YAML file. The .cfg files in YOLOv3 are used to define the model architecture and settings.

To change the number of anchor boxes, you need to update the num_anchors parameter in the yolov3.cfg file. This parameter specifies the number of anchor boxes for each scale. However, note that modifying the number of anchor boxes requires further code modifications to handle the new anchor configurations.

Regarding your second question, the YAML file you mentioned seems to be unrelated to the YOLOv3 model architecture. Therefore, you don't need to modify anything in that YAML file for changing the anchor boxes in YOLOv3.

If you need to check which YAML file is used in your train.py script, you should look for the command that loads the YAML file using a YAML parser. You can search for yaml.load or similar functions in your train.py script to identify the specific file being loaded.

I hope this clarifies your concerns. Let me know if you have any further questions.

from yolov3.

https://github.com/ultralytics/yolov3 in this repo can u find me the yolov3.cfg file. there is only a setup.cfg file

from yolov3.

@Venatus6401 the yolov3.cfg file is not present in the Ultralytics YOLOv3 repository. You can refer to the official YOLOv3 repository for the yolov3.cfg file. Here is the link to the official repository: https://github.com/AlexeyAB/darknet

YOLOv3 and its variants have several implementations available, and the Ultralytics YOLOv3 repository may have slight differences compared to the original implementation. Therefore, for the yolov3.cfg file, it is recommended to refer to the official repository for the most up-to-date and accurate version.

If you have any further questions or need assistance, feel free to ask.

from yolov3.

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐

from yolov3.