RNetRunner

class plugins.extract.detect.mtcnn.RNetRunner(weights_path: str, device: device, input_size: int, threshold: float)

Bases: object

Runner for PyTorch R-Net for MTCNN

Parameters:

  • weights_path (str) – The path to the torch model file

  • device (torch.device) – The device to run inference on

  • input_size (int) – The input size of the model

  • threshold (float) – Threshold for R-Net

Methods Summary

__call__(images, rectangle_batch)

second stage - refinement of face candidates with r-net

Methods Documentation

__call__(images: ndarray, rectangle_batch: list[ndarray]) → list[ndarray]

second stage - refinement of face candidates with r-net

Parameters:

  • images (ndarray) – The batch of images to detect faces in

  • rectangle_batch (list[ndarray]) – face candidates from P-Net

Return type:

Refined face candidates from R-Net

__call__(images: ndarray, rectangle_batch: list[ndarray]) → list[ndarray]

second stage - refinement of face candidates with r-net

Parameters:

  • images (ndarray) – The batch of images to detect faces in

  • rectangle_batch (list[ndarray]) – face candidates from P-Net

Return type:

Refined face candidates from R-Net