Predict

class scripts.convert.Predict(queue_size: int, arguments: Namespace)

Bases: object

Obtains the output from the Faceswap model.

Parameters:

queue_size (int) – The maximum size of the input queue
arguments (Namespace) – The arguments that were passed to the convert process as generated from Faceswap’s command line arguments

Attributes Summary

`centering`	The centering that the model was trained on ("head", "face" or "legacy")
`coverage_ratio`	The coverage ratio that the model was trained at.
`faces_count`	The total number of faces seen by the Predictor.
`has_predicted_mask`	`True` if the model was trained to learn a mask, otherwise `False`.
`in_queue`	The input queue to the predictor.
`out_queue`	The output queue from the predictor.
`output_size`	The size in pixels of the Faceswap model output.
`thread`	The thread that is running the prediction function from the Faceswap model.
`verify_output`	`True` if multiple faces have been found in frames, otherwise `False`.
`y_offset`	The selected model y-offset value

Methods Summary

`launch`(load_queue)	Launch the prediction process in a background thread.
`load_aligned`(item)	Load the model's feed faces and the reference output faces.

Attributes Documentation

centering: The centering that the model was trained on (“head”, “face” or “legacy”)

coverage_ratio

The coverage ratio that the model was trained at.

Type:: float

faces_count: The total number of faces seen by the Predictor.

has_predicted_mask: True if the model was trained to learn a mask, otherwise False.

in_queue: The input queue to the predictor.

out_queue: The output queue from the predictor.

output_size: The size in pixels of the Faceswap model output.

thread: The thread that is running the prediction function from the Faceswap model.

verify_output: True if multiple faces have been found in frames, otherwise False.

y_offset: The selected model y-offset value

Methods Documentation

launch(load_queue: EventQueue) → None

Launch the prediction process in a background thread.

Starts the prediction thread and returns the thread.

Parameters:: load_queue (EventQueue) – The queue that contains images and detected faces for feeding the model
Return type:: None

load_aligned(item: ConvertItem) → None

Load the model’s feed faces and the reference output faces.

For each detected face in the incoming item, load the feed face and reference face images, correctly sized for input and output respectively.

Parameters:: item (ConvertItem) – The convert media object, containing the FrameFaces for the current image
Return type:: None

property centering: CenteringType: The centering that the model was trained on (“head”, “face” or “legacy”)

property coverage_ratio: float