Model Optimization Challenges
Lukas and Luis discuss the challenges of optimizing models for performance on devices like Raspberry Pi, highlighting the struggle to achieve target latency for models to be truly useful. They delve into techniques like quantization to improve performance and reduce model size, emphasizing the need for significant performance gains beyond just getting the model to run.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Luis Ceze — Accelerating Machine Learning Systems
Related Questions