results = F.concat(id, score, bbox, dim=-1) # (b, 169, 3, 6)
return F.reshape(results, shape=(0, -1, 6)) # (b, -1, 6)
# test
if __name__ == "__main__":
from core import Yolov3, YoloTrainTransform, DetectionDataset
import os
input_size = (416, 416)
root = os.path.dirname(
os.path.dirname(
os.path.dirname(
os.path.dirname(os.path.dirname(os.path.abspath(__file__))))))
transform = YoloTrainTransform(input_size[0], input_size[1])
dataset = DetectionDataset(path=os.path.join(root, 'Dataset', 'train'),
transform=transform)
num_classes = dataset.num_class
image, label, _ = dataset[0]
net = Yolov3(
Darknetlayer=53,
input_size=input_size,
anchors={
"shallow": [(10, 13), (16, 30), (33, 23)],
"middle": [(30, 61), (62, 45), (59, 119)],
"deep": [(116, 90), (156, 198), (373, 326)]
},
num_classes=num_classes, # foreground만
scores = F.slice_axis(results, axis=-1, begin=1, end=2)
bboxes = F.slice_axis(results, axis=-1, begin=2, end=6)
return ids, scores, bboxes
# test
if __name__ == "__main__":
from core import Yolov3, YoloTrainTransform, DetectionDataset
import os
input_size = (416, 416)
root = os.path.dirname(
os.path.dirname(
os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
transform = YoloTrainTransform(input_size[0],
input_size[1],
make_target=False)
dataset = DetectionDataset(path=os.path.join(root, 'Dataset', 'train'),
transform=transform)
num_classes = dataset.num_class
image, label, _, _, _ = dataset[0]
label = mx.nd.array(label)
net = Yolov3(
Darknetlayer=53,
input_size=input_size,
anchors={
"shallow": [(10, 13), (16, 30), (33, 23)],
"middle": [(30, 61), (62, 45), (59, 119)],
"deep": [(116, 90), (156, 198), (373, 326)]