Skip to content

v1.0 Beta

Latest
Compare
Choose a tag to compare
@kedars kedars released this 13 Dec 08:01
· 30 commits to master since this release

ESP-NN release v1.0 Beta

Supported/Tested Espressif Chipsets:

  • ESP32-S3 (Assembly optimizations)
  • ESP32 (Generic optimizations)
  • ESP32-C3 (Generic optimizations)

ESP-NN is tested to work with following ML framework:

  • TFlite-Micro

This release provides optimizations for the following kernels (layers) from TFlite-Micro:

  1. Convolution
  2. Depthwise Convolution
  3. Fully Connected
  4. MaxPool, AvgPool
  5. SoftMax
  6. Add
  7. Mul
  8. Relu

Please find the details on how to use ESP-NN, and other useful info here.