FaceChannel.FaceChannelV1 Model Definition
FaceChannel.FaceChannelV1.FaceChannelV1 module
FaceChannelV1.py
Version1 of the FaceChannel model.
- class FaceChannel.FaceChannelV1.FaceChannelV1.FaceChannelV1(type='Cat', loadModel=True, numberClasses=7)
Bases:
object- BATCH_SIZE = 32
Batch size used by FaceChannelV1
- CAT_CLASS_COLOR = [(255, 255, 255), (0, 255, 0), (0, 222, 255), (255, 0, 0), (0, 0, 255), (255, 0, 144), (0, 144, 255), (75, 75, 96)]
Color associated with each output of the pre-trained categorical model
- CAT_CLASS_ORDER = ['Neutral', 'Happiness', 'Surprise', 'Sadness', 'Anger', 'Disgust', 'Fear', 'Contempt']
Order of the pre-trained categorical model’s output
- DIM_CLASS_COLOR = [(0, 255, 0), (255, 0, 0)]
Color associated with each output of the pre-trained dimensional model
- DIM_CLASS_ORDER = ['Arousal', 'Valence']
Order of the pre-trained dimensional model’s output
- DOWNLOAD_FROM = 'https://github.com/pablovin/FaceChannel/raw/master/src/FaceChannel/FaceChannelV1/trainedNetworks.tar.xz'
URL where the model is stored
- IMAGE_SIZE = (64, 64)
Image size used as input used by FaceChannelV1
- buildFaceChannel()
This method returns a Keras model of the FaceChannelV1.rst feature extractor.
- Returns
a Keras model of the FaceChannelV1.rst feature extractor
- Return type
tensorflow model
- getCategoricalModel(numberClasses)
This method returns a categorical FaceChannelV1.rst.
- Returns
a dimensional FaceChannelV1.rst
- Return type
tensorflow model
- getDimensionalModel()
This method returns a dimensional FaceChannelV1.rst.
- Returns
a dimensional FaceChannelV1.rst
- Return type
tensorflow model
- loadModel(modelDirectory)
This method returns a loaded FaceChannelV1.rst.
- Parameters
modelDirectory – The directory where the loaded model is.
- Returns
The loaded model as a tensorflow-keras model
- Return type
tensorflow model
- predict(images, preprocess=True)
This method returns the prediction for one or more images.
- Parameters
images – The images as one or a list of ndarray.
preprocess – If the image is already pre-processed or not. a pre-processed image has a format of (64,64,1).
- Returns
The prediction of the given image(s) as a ndarray
- Return type
ndarray