|
STM32N6 NPU Deployment — Politecnico di Milano
1.0
Documentation for Neural Network Deployment on STM32N6 NPU - Politecnico di Milano 2024-2025
|
Dataset preprocessing pipeline for pose estimation. More...
Go to the source code of this file.
Namespaces | |
| preprocess | |
Functions | |
| Tuple | preprocess.preprocess (DictConfig cfg=None) |
| def | preprocess.apply_rescaling (tf.data.Dataset dataset=None, float scale=None, float offset=None) |
| tf.Tensor | preprocess.preprocess_input (np.ndarray image, dict input_details) |
Dataset preprocessing pipeline for pose estimation.
Loads, resizes, normalizes and batches images and keypoint annotations from COCO-format datasets. Returns TensorFlow Dataset objects for training, validation, quantization calibration, and test splits.
Definition in file preprocess.py.