Initialize the VAE instance. :param model_path: Path to the trained model. :param resized_img: The size to which images are

VGGFace model. Face recognition network. It takes as input a Bx3x224x224 batch of face images and gives as output a BxC score vector

Create a block with len(units) - 1 convolutions. convolution number i transforms the number of channels from units[i - 1] to units[i]

Initialize the AnalyzeFace class with the given device, config file, and checkpoint file. Parameters: device (Union[str, tor

appdata_dir(appname=None, roaming=False) Get the path to the application directory, where applications are allowed to write user specific fi

Center crops an image or set of heatmaps Arguments: image {numpy.array} -- an rgb image center {numpy.array} -- the center of the

Debug inpainting parameters, only process the first frame

Performs decoding of 30-second audio segment(s), provided as Mel spectrogram(s). Parameters ---------- model: Whisper the Wh

Timestamp tokens are above the special tokens' id range and are ignored by `decode()`. This method decodes given tokens with timestam

Detects faces from all the images present in a given directory. Arguments: path {string} -- a string containing a path that point

Detect the spoken language in the audio, and return them as list of strings, along with the ids of the most probable language tokens and the

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

Flip an image or a set of heatmaps left-right Arguments: tensor {numpy.array or torch.tensor} -- [the input image or heatmaps] Keywo