Webinar: How to Boost Inference Performance of Your YOLOX Model

YOLOX is an anchor-free version of YOLO and an improvement to the existing YOLO series. It features a simpler design but better performance.

In this hands-on webinar, our product manager, Lucy Kadets, walks you through a simple and fast way to optimize and deploy a YOLOX model (or any other deep learning model) in less than 15 minutes.

Watch now to learn how to:

  • Automate the compilation & quantization of the model with a click of a button
  • Benchmark the baseline and optimized models’ performance in various HW environments
  • Find the best inference HW for your application
  • Deploy the model in production using 3 lines of code

Try out the tips and boost your YOLOX model in no time, book a demo of the Deci platform today.

You May Also Like

Webinar: How to Fine-Tune LLMs with QLoRA

Webinar: Optimizing Pose Estimation for Real-Time Performance

Webinar: How to Optimize LLMs for Production

Add Your Heading Text Here
					from transformers import AutoFeatureExtractor, AutoModelForImageClassification

extractor = AutoFeatureExtractor.from_pretrained("microsoft/resnet-50")

model = AutoModelForImageClassification.from_pretrained("microsoft/resnet-50")