STM32N6 NPU Deployment — Politecnico di Milano  1.0
Documentation for Neural Network Deployment on STM32N6 NPU - Politecnico di Milano 2024-2025
evaluate.py File Reference

Accuracy evaluation pipeline for pose estimation models. More...

Go to the source code of this file.

Namespaces

 evaluate
 

Functions

None evaluate.evaluate (DictConfig cfg=None, tf.data.Dataset eval_ds=None, Optional[str] model_path_to_evaluate=None, Optional[str] name_ds='test_set')
 

Detailed Description

Accuracy evaluation pipeline for pose estimation models.

Computes OKS (Object Keypoint Similarity) and AP metrics on a validation or test dataset for both float32 and INT8 quantized models.

Note
Politecnico di Milano, A.Y. 2024-2025. Multidisciplinary Project — Neural Network Deployment on STM32N6 NPU.

Definition in file evaluate.py.