search

mlcommons / tiny

MLPerf™ Tiny is an ML benchmark suite for extremely low-power systems such as microcontrollers
https://mlcommons.org/en/groups/inference-tiny/
Apache License 2.0
344 stars 81 forks source link

kws_ref_model_float32.tflite is Hybrid Model #160

Open fabrizioaymone opened 3 months ago

fabrizioaymone commented 3 months ago

I removed the TFLite Optimization flag during the conversion of the Keras model to the FP32 TFLite version, which produces kws_ref_model_float32.tflite. Previously, kws_ref_model_float32.tflite was a hybrid model, featuring both INT8 and FP32 operations, which are not supported by TFLM. To align with the goals of this benchmark and the other three use cases (anomaly detection, image classification, and visual wake words), kws_ref_model_float32.tflite should use only FP32 operations. My commit ensures this.

github-actions[bot] commented 3 months ago

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅