|
STM32N6 NPU Deployment — Politecnico di Milano
1.0
Documentation for Neural Network Deployment on STM32N6 NPU - Politecnico di Milano 2024-2025
|
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') |
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.
Definition in file evaluate.py.