Can you provide a Yolov5 model that is not based on YAML files

[williamlzw]

Can you provide a Yolov5 model that is not based on YAML files? I tried porting to libtorch.I can't understand the model based on yaml file.

[github-actions[bot]]

Hello @laizewei, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Google Colab Notebook, Docker Image, and GCP Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI surveillance systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

@laizewei yes this should be possible. We use the yaml file to load multiple types of yolo models with the same pytorch code.

[williamlzw]

Thank you!

[glenn-jocher]

@laizewei you may be able to load YOLOv5 models now directly with PyTorch Hub. This way you should not have to deal with any yaml files. See https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading

[williamlzw]

Can you offer Yolov5s.py that only use pytorch's base layer?I tried porting the libtorch version.

[williamlzw]

Like this https://github.com/laizewei/libtorch-mobilenetv3/blob/master/MobileNet.h

[sakshamjn]

Hey If I use Pytorch hub can I use my custom weights

[glenn-jocher]

@sakshamjn no. The purpose of hub is to make official pretrained weights available in an easy to access method.

[sakshamjn]

@glenn-jocher Thanks.

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[zhou-huan-1]

Hey If I use Pytorch hub can I use my custom weights

[glenn-jocher]

Hey @zhou-huan-1! Yes, you can use your custom weights with PyTorch Hub by specifying the path parameter when loading the model. Here's a quick example:

import torch

# Load your custom model weights
model = torch.hub.load('ultralytics/yolov5', 'custom', path='path/to/your/custom_weights.pt')

This will allow you to use your trained weights for inference. Happy coding! 😊