def __init__(self,
renderer,
image_shape,
image_paths,
inputs_to_shape,
labels_to_shape,
num_occlusions=1):
super(DomainRandomization, self).__init__()
H, W = image_shape[:2]
self.add(pr.Render(renderer))
self.add(pr.ControlMap(RandomizeRender(image_paths), [0, 1], [0]))
self.add(pr.ControlMap(pr.NormalizeImage(), [0], [0]))
self.add(pr.ControlMap(pr.NormalizeImage(), [1], [1]))
self.add(pr.SequenceWrapper({0: inputs_to_shape},
{1: labels_to_shape}))
def __init__(self, detector, keypoint_estimator, radius=3):
super(ProbabilisticKeypointPrediction, self).__init__()
# face detector
RGB2GRAY = pr.ConvertColorSpace(pr.RGB2GRAY)
self.detect = pr.Predict(detector, RGB2GRAY, pr.ToBoxes2D(['face']))
# creating pre-processing pipeline for keypoint estimator
preprocess = SequentialProcessor()
preprocess.add(pr.ResizeImage(keypoint_estimator.input_shape[1:3]))
preprocess.add(pr.ConvertColorSpace(pr.RGB2GRAY))
preprocess.add(pr.NormalizeImage())
preprocess.add(pr.ExpandDims(0))
preprocess.add(pr.ExpandDims(-1))
# creating post-processing pipeline for keypoint esimtator
# postprocess = SequentialProcessor()
# postprocess.add(ToNumpyArray())
# postprocess.add(pr.Squeeze(1))
# keypoint estimator predictions
self.estimate_keypoints = PredictMeanDistribution(
keypoint_estimator, preprocess)
# self.estimate_keypoints = pr.Predict(
# keypoint_estimator, preprocess, postprocess)
# used for drawing up keypoints in original image
self.change_coordinates = pr.ChangeKeypointsCoordinateSystem()
self.denormalize_keypoints = pr.DenormalizeKeypoints()
self.crop_boxes2D = pr.CropBoxes2D()
self.num_keypoints = len(keypoint_estimator.output_shape)
self.draw = pr.DrawKeypoints2D(self.num_keypoints, radius, False)
self.draw_boxes2D = pr.DrawBoxes2D(['face'], colors=[[0, 255, 0]])
self.wrap = pr.WrapOutput(['image', 'boxes2D'])
def test_image_cropping():
handsegnet = HandSegmentationNet()
preprocess_image = SequentialProcessor(
[pr.NormalizeImage(),
pr.ResizeImage((320, 320)),
pr.ExpandDims(0)])
postprocess_segmentation = PostProcessSegmentation(320, 320)
localize_hand = pr.Predict(handsegnet, preprocess_image,
postprocess_segmentation)
image = load_image('./sample.jpg')
hand_crop, segmentation_map, center, boxes, crop_sizes = localize_hand(
image)
box = boxes[0]
xmin, ymin, xmax, ymax = box
crop_size = crop_sizes[0]
assert len(hand_crop.shape) == 4
assert hand_crop.shape == (1, 256, 256, 3)
assert len(segmentation_map.shape) == 4
assert segmentation_map.shape == (1, 320, 320, 1)
assert center == [[191.5, 194.5]]
assert len(box) == 4
assert box == [114, 153, 269, 236]
assert xmax > xmin and ymin > ymax
assert round(crop_size[0], 2) == 1.32
def __init__(self, renderer, image_paths, num_occlusions, split=pr.TRAIN):
super(DomainRandomizationProcessor, self).__init__()
self.copy = pr.Copy()
self.render = pr.Render(renderer)
self.augment = RandomizeRenderedImage(image_paths, num_occlusions)
preprocessors = [pr.ConvertColorSpace(pr.RGB2BGR), pr.NormalizeImage()]
self.preprocess = SequentialProcessor(preprocessors)
self.split = split
def __init__(self, shape, mean=pr.BGR_IMAGENET_MEAN):
super(PreprocessImage, self).__init__()
self.add(pr.ResizeImage(shape))
self.add(pr.CastImage(float))
if mean is None:
self.add(pr.NormalizeImage())
else:
self.add(pr.SubtractMeanImage(mean))
def test_preprocess_image():
preprocess_pipeline = SequentialProcessor(
[pr.NormalizeImage(),
pr.ResizeImage((320, 320)),
pr.ExpandDims(0)])
image = load_image('./sample.jpg')
processed_image = preprocess_pipeline(image)
assert len(processed_image.shape) == 4
assert processed_image.shape == (1, 320, 320, 3)
def __init__(self, model, draw=True):
super(GMMKeypoints, self).__init__()
self.num_keypoints = len(model.output_shape)
preprocess = SequentialProcessor()
preprocess.add(pr.ResizeImage(model.input_shape[1:3]))
preprocess.add(pr.ConvertColorSpace(pr.RGB2GRAY))
preprocess.add(pr.NormalizeImage())
preprocess.add(pr.ExpandDims(0))
preprocess.add(pr.ExpandDims(-1))
self.estimate_keypoints = PredictDistributions(model, preprocess)
self.to_grid = ToProbabilityGrid(GRID)
self.draw = draw
self.draw_probabilities = DrawProbabilities(self.num_keypoints)
self.wrap = pr.WrapOutput(['image', 'probabilities', 'distributions'])
def __init__(self, scene, keypoints, image_paths, num_occlusions):
super(RandomKeypointsRender, self).__init__()
H, W = scene.viewport_size
render = pr.Render(scene)
augment = RandomizeRenderedImage(image_paths, num_occlusions)
augment.add(pr.NormalizeImage())
self.add(RenderRandomSample(render, augment, keypoints))
self.add(
pr.SequenceWrapper({0: {
'image': [H, W, 3]
}}, {1: {
'keypoints': [len(keypoints), 3]
}}))
def test_segmentation_postprocess():
preprocess_pipeline = SequentialProcessor(
[pr.NormalizeImage(),
pr.ResizeImage((320, 320)),
pr.ExpandDims(0)])
image = load_image('./sample.jpg')
processed_image = preprocess_pipeline(image)
localization_pipeline = PostProcessSegmentation(HandSegNet)
localization_output = localization_pipeline(processed_image)
assert len(localization_output) == 5
assert localization_output[0].shape == (1, 256, 256, 3)
assert localization_output[1].shape == (1, 320, 320, 1)
assert localization_output[2].shape == (1, 2)
assert localization_output[3].shape == (1, 2, 2)
assert localization_output[4].shape == (1, 1)
def test_keypoints2D_process():
preprocess_pipeline = SequentialProcessor(
[pr.NormalizeImage(),
pr.ResizeImage((320, 320)),
pr.ExpandDims(0)])
image = load_image('./sample.jpg')
processed_image = preprocess_pipeline(image)
localization_pipeline = PostProcessSegmentation(HandSegNet)
localization_output = localization_pipeline(processed_image)
keypoints_pipeline = Process2DKeypoints(HandPoseNet)
score_maps_dict = keypoints_pipeline(
np.squeeze(localization_output[0], axis=0))
score_maps = score_maps_dict['score_maps']
assert score_maps.shape == (1, 32, 32, 21)
assert len(score_maps) == 1
def __init__(self,
phase,
rotation_range=30,
delta_scales=[0.2, 0.2],
num_keypoints=15):
super(AugmentKeypoints, self).__init__()
self.add(pr.UnpackDictionary(['image', 'keypoints']))
if phase == 'train':
self.add(pr.ControlMap(pr.RandomBrightness()))
self.add(pr.ControlMap(pr.RandomContrast()))
self.add(pr.RandomKeypointRotation(rotation_range))
self.add(pr.RandomKeypointTranslation(delta_scales))
self.add(pr.ControlMap(pr.NormalizeImage(), [0], [0]))
self.add(pr.ControlMap(pr.ExpandDims(-1), [0], [0]))
self.add(pr.ControlMap(pr.NormalizeKeypoints((96, 96)), [1], [1]))
self.add(
pr.SequenceWrapper({0: {
'image': [96, 96, 1]
}}, {1: {
'keypoints': [num_keypoints, 2]
}}))
def __init__(self,
handsegnet,
posenet,
posepriornet,
viewpointnet,
image_size=320,
crop_shape=(256, 256),
num_keypoints=21):
super(DetectHandKeypoints, self).__init__()
self.preprocess_image = SequentialProcessor([
pr.NormalizeImage(),
pr.ResizeImage((image_size, image_size)),
pr.ExpandDims(0)
])
postprocess_segmentation = PostProcessSegmentation(
image_size, crop_shape)
self.localize_hand = pr.Predict(handsegnet,
postprocess=postprocess_segmentation)
self.resize_scoremaps = ResizeScoreMaps(crop_shape)
self.merge_dictionaries = MergeDictionaries()
self.wrap_input = WrapToDictionary(['hand_side'])
self.predict_keypoints2D = pr.Predict(posenet)
self.predict_keypoints3D = pr.Predict(posepriornet)
self.predict_keypoints_angles = pr.Predict(viewpointnet)
self.postprocess_keypoints = PostProcessKeypoints()
self.resize = pr.ResizeImage(shape=crop_shape)
self.extract_2D_keypoints = ExtractKeypoints()
self.transform_keypoints = TransformKeypoints()
self.draw_keypoint = pr.DrawKeypoints2D(num_keypoints,
normalized=True,
radius=4)
self.denormalize = pr.DenormalizeImage()
self.wrap = pr.WrapOutput(['image', 'keypoints2D', 'keypoints3D'])
self.expand_dims = pr.ExpandDims(axis=0)
self.draw_boxes = pr.DrawBoxes2D(['hand'], [[0, 1, 0]])
def __init__(self,
phase,
rotation_range=30,
delta_scales=[0.2, 0.2],
with_partition=False,
num_keypoints=15):
super(AugmentKeypoints, self).__init__()
self.add(pr.UnpackDictionary(['image', 'keypoints']))
if phase == 'train':
self.add(pr.ControlMap(pr.RandomBrightness()))
self.add(pr.ControlMap(pr.RandomContrast()))
self.add(pr.RandomKeypointRotation(rotation_range))
self.add(pr.RandomKeypointTranslation(delta_scales))
self.add(pr.ControlMap(pr.NormalizeImage(), [0], [0]))
self.add(pr.ControlMap(pr.ExpandDims(-1), [0], [0]))
self.add(pr.ControlMap(pr.NormalizeKeypoints((96, 96)), [1], [1]))
labels_info = {1: {'keypoints': [num_keypoints, 2]}}
if with_partition:
outro_indices = list(range(1, 16))
self.add(pr.ControlMap(PartitionKeypoints(), [1], outro_indices))
labels_info = {}
for arg in range(num_keypoints):
labels_info[arg + 1] = {'keypoint_%s' % arg: [2]}
self.add(pr.SequenceWrapper({0: {'image': [96, 96, 1]}}, labels_info))
