Business Results

  • Up to 38% faster feature extraction inference in batch

  • Up to 193% faster segmentation inference

  • Up to 4% faster end-to-end pipeline after training optimization (quantization)

author-image

By

 

View All Reference Kits

Background

The demand for innovation in manufacturing is pushing engineers to adopt AI models to create a wide range of high-performance and complex component designs to reduce manufacturing costs and accelerate the product development process, resulting in a shorter the time-to-market.

Generative design is the next frontier in CAD design for engineers working in virtually all manufacturing industries. It harnesses the power of AI to develop new high-performance design iterations that help solve these complex challenges.

Solution

In collaboration with Accenture*, Intel developed an engineering design optimization AI reference kit, which may assist you with creating Generative Adversarial Networks that can be used to optimize and improve novelty in product design.

Using a bicycle designs dataset to retrain the model, the StyleGAN2 model can create new bicycle designs with unique frames and handles and generalize rare novelties to a broad set of designs, completely automatically and without requiring human intervention. As a post-processing step, a custom algorithm is applied on generated novel design images to suggest the most compact and novel designs.

End-to-End Flow Using Intel® AI Software Products

A state-of-the-art StyleGAN2 model is used to generate realistic designs. Other models (WideResNET, ResUNET) are then applied to automatically detect and locate the novel features in the generated designs, and to then rewrite the original StyleGAN2 model using the detected most novel features applying the concept of rewriting GANs. The custom StyleGAN2 is then used to regenerate novel and optimized designs.

This reference kit includes:

  • Training data
  • An open source, trained model
  • Libraries
  • User guides
  • Intel® AI software products

At a Glance

  • Industry: Manufacturing
  • Task: Feature extraction, image segmentation, model rewriting, image generation​
  • Dataset: Bicycle design images: 4512
  • Type of Learning: Deep learning
  • Models WideResNet model, ResUNet model, StyleGAN2
  • Output: Novel and optimized bike design image (512 x 512 x 3 size image)
  • Intel AI Software Products:
    • Intel® Extension for PyTorch* v1.13.0
    • Intel® Neural Compressor

Technology

Optimized with Intel AI Software Products for Better Performance

The engineering design model was optimized with Intel Extension for PyTorch v1.13.0. Intel Neural Compressor was used to quantize the FP32 model to the int8 model.

Intel Extension for PyTorch and Intel Neural Compressor allow you to reuse your model development code with minimal code changes for training and inferencing.

Performance benchmark tests were run on Microsoft Azure* Standard_D8_v5 using 3rd generation Intel® Xeon® processors to optimize the solution.

Benefits

This AI reference kit demonstrates the implementation of a performance-optimized approach for Generative Adversarial Networks that can be used to optimize and improve novelty in product design, completely automatically and without requiring human intervention.

This reference model can help solve complex challenges, reduce component weights and manufacturing costs, scale customization, optimize performance, and reduce product development cycle time.

With Intel® oneAPI components, little to no code change is required to attain the performance boost.

Download Kit

Stay Up to Date on AI Workload Optimizations

Sign up to receive hand-curated technical articles, tutorials, developer tools, training opportunities, and more to help you accelerate and optimize your end-to-end AI and data science workflows.

Take a chance and subscribe. You can change your mind at any time.

By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.
By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. You also agree to subscribe to stay connected to the latest Intel technologies and industry trends by email and telephone. You may unsubscribe at any time. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.