Tips & Tricks

Model Creation:

  • When collecting the data, quality is better than quantity.
  • Define a baseline before creating a model.
  • With pipelining( use of Machine Learning Pipeline), we can overcome CPU bottlenecks by overlapping the CPU pre-processing and model execution of accelerators
    Processing Speed:
  • Single Instruction Multiple Data(SIMD) refer to a program that is divided into sub-processes (or sometimes not even divided) that work in parallel on multiple data streams or threads.