S3FD

class plugins.extract.detect.s3fd.S3FD

Bases: ExtractPlugin

S3FD detector for face detection

Attributes Summary

device

The selected device to run torch ops on

Methods Summary

decode(location, priors)

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time.

from_torch(batch)

Run inference on a PyTorch model.

load_model()

Load the S3FD Model

load_torch_model(model, weights_path[, ...])

Load a PyTorch model, apply the weights and pass a warmup batch through

post_process(batch)

Process the output from the model to bounding boxes

pre_process(batch)

Compile the detection image(s) for prediction

process(batch)

Run model to get predictions

Attributes Documentation

device

The selected device to run torch ops on

Methods Documentation

static decode(location: ndarray, priors: ndarray) → ndarray

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time.

Parameters:

  • location (ndarray) – location predictions for location layers,

  • priors (ndarray) – Prior boxes in center-offset form.

Return type:

Decoded bounding box predictions

from_torch(batch: ndarray) → ndarray

Run inference on a PyTorch model.

This function does not need to be used, however it handles torch backend for better throughput, so it is recommended. Must have used self.load_torch_model to load the Torch model to use this function.

Parameters:

batch (ndarray) – The batch array to feed to the PyTorch model

Return type:

The result from the PyTorch model

load_model() → S3FDModel

Load the S3FD Model

Return type:

The loaded S3FD model

load_torch_model(model: Module, weights_path: str, return_indices: list[int] | None = None) → Module

Load a PyTorch model, apply the weights and pass a warmup batch through

This function does not need to be used, but some default Faceswap optimizations are performed here, so without using this function you will either need to apply them yourself or not have them applied

Parameters:

  • model (Module) – The Torch model to load

  • weights_path (str) – Full path to the weights file to load

  • return_indices (list[int] | None) – If the model outputs multiple items, but you only require some of them, the indices of the required items can be placed here so that when calling from_torch any extra data is not copied from the GPU. Default: None (return all data)

Return type:

The loaded model ready for inference

post_process(batch: ndarray) → ndarray

Process the output from the model to bounding boxes

Parameters:

batch (ndarray) – The output predictions from the S3FD model

Return type:

The processed detection bounding box from the model at model input size

pre_process(batch: ndarray) → ndarray

Compile the detection image(s) for prediction

Parameters:

batch (ndarray) – The input batch of images at model input size in the correct color order, dtype and scale

Return type:

The batch of images ready for feeding the model

process(batch: ndarray) → ndarray

Run model to get predictions

Parameters:

batch (ndarray) – A batch of images ready to feed the model

Return type:

The batch of detection results from the model

static decode(location: ndarray, priors: ndarray) → ndarray

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time.

Parameters:

  • location (ndarray) – location predictions for location layers,

  • priors (ndarray) – Prior boxes in center-offset form.

Return type:

Decoded bounding box predictions

load_model() → S3FDModel

Load the S3FD Model

Return type:

The loaded S3FD model

model: S3FDModel

The loaded model for the plugin

post_process(batch: ndarray) → ndarray

Process the output from the model to bounding boxes

Parameters:

batch (ndarray) – The output predictions from the S3FD model

Return type:

The processed detection bounding box from the model at model input size

pre_process(batch: ndarray) → ndarray

Compile the detection image(s) for prediction

Parameters:

batch (ndarray) – The input batch of images at model input size in the correct color order, dtype and scale

Return type:

The batch of images ready for feeding the model

process(batch: ndarray) → ndarray

Run model to get predictions

Parameters:

batch (ndarray) – A batch of images ready to feed the model

Return type:

The batch of detection results from the model