Skip to content

Latest commit

 

History

History
20 lines (13 loc) · 1 KB

README.rst

File metadata and controls

20 lines (13 loc) · 1 KB

Example applications

These are 6 example models; in order of complexity

  • app_no_flash - a single model, no flash memory used. This is the fastest but most pressure on internal memory.
  • app_flash_single_model - a single model, with learned parameters in flash memory. This removes a lot of pressure on internal memory.
  • app_flash_two_models - two models, with learned parameters in flash memory.
  • app_flash_two_models_one_arena - two models, with learned parameters in flash memory. The models share a single tensor arena (scratch memory).
  • app_mobilenetv2 - exporting a MobileNetV2 model (with flash) via xformer, with example inference on host (via interpreter) and on device.
  • app_profiling - demonstrates how to enable and use profiling to speed up execution.