Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Models: deepen Neuron CV Object detection support (YOLO v3 YOLO v4) #40

Closed
AWSGH opened this issue Dec 18, 2019 · 1 comment
Closed

Comments

@AWSGH
Copy link
Contributor

AWSGH commented Dec 18, 2019

No description provided.

@AWSGH AWSGH added this to Coming soon in AWS Neuron roadmap (obsolete) Dec 18, 2019
@AWSGH AWSGH changed the title Models: add CV Object detection (Mask R-CNN) support Models: deepen Neuron CV Object detection support (Faster R-CNN) May 12, 2020
@AWSGH AWSGH changed the title Models: deepen Neuron CV Object detection support (Faster R-CNN) Models: deepen Neuron CV Object detection support Aug 13, 2020
@AWSGH AWSGH changed the title Models: deepen Neuron CV Object detection support Models: deepen Neuron CV Object detection support (SSD1200, YOLO) Aug 13, 2020
@aws-neuron aws-neuron deleted a comment from aws-zejdaj Aug 31, 2020
@AWSGH
Copy link
Contributor Author

AWSGH commented Sep 23, 2020

With Neuron 1.8.0 release, running YOLO v3 and YOLO v4 on Inf1 instances provides up to 1.85X higher throughput and 40% lower cost-per-inference compared to running the same models on the EC2 G4 GPU instances.

@AWSGH AWSGH changed the title Models: deepen Neuron CV Object detection support (SSD1200, YOLO) Models: deepen Neuron CV Object detection support (YOLO v3 YOLO v4) Sep 23, 2020
@AWSGH AWSGH closed this as completed Sep 23, 2020
@AWSGH AWSGH moved this from Coming soon to Completed in AWS Neuron roadmap (obsolete) Oct 7, 2020
@AWSGH AWSGH added the enhancement New feature or request label Nov 11, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request Inf1 inference
Development

No branches or pull requests

1 participant