Video

Webinar: How to Boost Inference Performance of Your YOLOX Model

By Deci User
Deep Learning Engineer

June 29, 2022
2 min read

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.

[Webinar] How to Speed Up YOLO Models on Snapdragon: Beyond Naive Quantization

[Webinar] How to Evaluate LLMs: Benchmarks, Vibe Checks, Judges, and Beyond

[Webinar] How to Boost Accuracy & Speed in Satellite & Aerial Image Object Detection

Add Your Heading Text Here

				
					from transformers import AutoFeatureExtractor, AutoModelForImageClassification

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

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

Webinar: How to Boost Inference Performance of Your YOLOX Model

You May Also Like

[Webinar] How to Speed Up YOLO Models on Snapdragon: Beyond Naive Quantization

[Webinar] How to Evaluate LLMs: Benchmarks, Vibe Checks, Judges, and Beyond

[Webinar] How to Boost Accuracy & Speed in Satellite & Aerial Image Object Detection

Share

Add Your Heading Text Here