Deep Learning Optimizer
What is the EYYES Deep Learning Optimizer?
The Deep Learning Optimizer is a neural network optimization service. Neural networks require a lot of memory and computing power when deployed. For many applications, especially in the embedded systems area, this has long been a hurdle. Today, through the targeted use of arithmetic and topological optimization methods such as quantization and pruning, the complexity can (usually) be reduced many times over without negative effects on the quality.
How does the EYYES Deep Learning Optimizer work?
The Deep Learning Optimizer receives an already trained network. The complexity of the model is reduced by means of so-called post-training optimization procedures. An automated evaluation shows the achieved reduction. If use-case image data is available, the evaluation also shows the quality results compared to the unoptimized model. As a result, the optimized model and a binary model for the EYYES Deep Learning Accelerator are returned.
Benefit and Advantage of the Optimizer
Neural network optimization allows cheaper or more energy-efficient hardware to be used for the application, such as our EYYES Deep Learning Accelerator. Post-training optimization allows the costly and time-consuming model training to take place normally:
- No costly experiments during the training process
- Full focus on quality
- No additional image data is needed for optimization
- 17-50% lower quantization losses