tensorrtx yolov5 v1.0 v2.0 v3.0

[wang-xinyu]

Hi @glenn-jocher,

Just to let you know, we have updated our implementation to your v3.0 release.

Now we support your yolov5 v1.0(yolov5s only) v2.0 and v3.0. Refer to https://github.com/wang-xinyu/tensorrtx/tree/master/yolov5

And the speed of v3.0 is nearly the same as v2.0.

[github-actions[bot]]

Hello @wang-xinyu, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud 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 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 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]

@wang-xinyu oh, that's great, I'm glad to hear that! I haven't tested speed effects on the nn.Hardswish() activations other than in PyTorch, and I have not checked out export results either other than to see that export CI tests are passing.

We're trying to strike the right compromise between mAP improvements and speed improvements. It's a tricky balancing act.

[wang-xinyu]

@glenn-jocher I think hard swish is good, as least it should be faster than mish in yolov4.~~

[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.