FaceSwap-DAN modifications for multiple faces

getFaceKeypoints.py

def getFaceKeypoints(img, detector, predictor, inputLandmarks=None, frameCounter=0):
    shapes2D = []

    # if inputLandmarks is None or frameCounter % 10 == 0:
        #detekcja twarzy
    dets = detector(img, 1)

    if len(dets) == 0:
        return None

    if len(img.shape) > 2:
        img = np.mean(img, axis=2)

    for i, det in enumerate(dets):
        inputLandmarks = bestFitRect(None, predictor.initLandmarks, [det.left(), det.top(), det.right(), det.bottom()])
        shape2D = predictor.processImg(img[np.newaxis], inputLandmarks)
        shape2D = shape2D.T
        shapes2D.append(shape2D)


    #transpozycja, zeby ksztalt byl 2 x n a nie n x 2, pozniej ulatwia to obliczenia

    return shapes2D
    

zad2.py

while True:
    frameCounter += 1
    cameraImg = cap.read()[1]
    shapes2D = utils.getFaceKeypoints(cameraImg, detector, predictor, prevShape2D, frameCounter=frameCounter)


    if shapes2D is not None:
        for shape2D in shapes2D:
            prevShape2D = shape2D.T
            #3D model parameter initialization
            modelParams = projectionModel.getInitialParameters(
                mean3DShape[:, idxs3D], shape2D[:, idxs2D])

            #3D model parajeter optimization
            modelParams = NonLinearLeastSquares.GaussNewton(
                modelParams, projectionModel.residual, projectionModel.jacobian,
                ([mean3DShape[:, idxs3D], blendshapes[:, :, idxs3D]], shape2D[:, idxs2D]), verbose=0)

            #rendering the model to an image
            shape3D = utils.getShape3D(mean3DShape, blendshapes, modelParams)
            renderedImg = renderer.render(shape3D)

            #blending of the rendered face with the image
            mask = np.copy(renderedImg[:, :, 0])
            renderedImg = ImageProcessing.colorTransfer(cameraImg, renderedImg, mask)
            cameraImg = ImageProcessing.blendImages(renderedImg, cameraImg, mask)