def run(self, netout):
anchors = [
0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282,
3.52778, 9.77052, 9.16828
]
nms_threshold = 0.2
"""Convert Yolo network output to bounding box
# Args
netout : 4d-array, shape of (grid_h, grid_w, num of boxes per grid, 5 + n_classes)
YOLO neural network output array
# Returns
boxes : array, shape of (N, 4)
coordinate scale is normalized [0, 1]
probs : array, shape of (N, nb_classes)
"""
grid_h, grid_w, nb_box = netout.shape[:3]
boxes = []
# decode the output by the network
netout[..., 4] = _sigmoid(netout[..., 4])
netout[..., 5:] = netout[..., 4][..., np.newaxis] * _softmax(
netout[..., 5:])
netout[..., 5:] *= netout[..., 5:] > self._threshold
for row in range(grid_h):
for col in range(grid_w):
for b in range(nb_box):
# from 4th element onwards are confidence and class classes
classes = netout[row, col, b, 5:]
if np.sum(classes) > 0:
# first 4 elements are x, y, w, and h
x, y, w, h = netout[row, col, b, :4]
x = (col + _sigmoid(x)
) / grid_w # center position, unit: image width
y = (row + _sigmoid(y)
) / grid_h # center position, unit: image height
w = anchors[2 * b + 0] * np.exp(
w) / grid_w # unit: image width
h = anchors[2 * b + 1] * np.exp(
h) / grid_h # unit: image height
confidence = netout[row, col, b, 4]
box = BoundBox(x, y, w, h, confidence, classes)
boxes.append(box)
boxes = nms_boxes(boxes, len(classes), nms_threshold, self._threshold)
boxes, probs = boxes_to_array(boxes)
return boxes, probs
def detect(self, image, anchors, net_size=416):
image_h, image_w, _ = image.shape
new_image = preprocess_input(image, net_size)
# 3. predict
yolos = self.predict(new_image)
boxes_ = postprocess_ouput(yolos, anchors, net_size, image_h, image_w)
if len(boxes_) > 0:
boxes, probs = boxes_to_array(boxes_)
boxes = to_minmax(boxes)
labels = np.array([b.get_label() for b in boxes_])
else:
boxes, labels, probs = [], [], []
return boxes, labels, probs