Spaces:
Runtime error
Runtime error
| [net] | |
| batch=64 | |
| subdivisions=8 | |
| # Training | |
| #width=512 | |
| #height=512 | |
| width=608 | |
| height=608 | |
| channels=3 | |
| momentum=0.949 | |
| decay=0.0005 | |
| angle=0 | |
| saturation = 1.5 | |
| exposure = 1.5 | |
| hue=.1 | |
| learning_rate=0.0013 | |
| burn_in=1000 | |
| max_batches = 500500 | |
| policy=steps | |
| steps=400000,450000 | |
| scales=.1,.1 | |
| #cutmix=1 | |
| mosaic=1 | |
| #:104x104 54:52x52 85:26x26 104:13x13 for 416 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=32 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=32 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -1,-7 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -1,-10 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -1,-28 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -1,-28 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=1024 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -1,-16 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=1024 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| ########################## | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=1024 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| ### SPP ### | |
| [maxpool] | |
| stride=1 | |
| size=5 | |
| [route] | |
| layers=-2 | |
| [maxpool] | |
| stride=1 | |
| size=9 | |
| [route] | |
| layers=-4 | |
| [maxpool] | |
| stride=1 | |
| size=13 | |
| [route] | |
| layers=-1,-3,-5,-6 | |
| ### End SPP ### | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=1024 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [upsample] | |
| stride=2 | |
| [route] | |
| layers = 85 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [route] | |
| layers = -1, -3 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [upsample] | |
| stride=2 | |
| [route] | |
| layers = 54 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [route] | |
| layers = -1, -3 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| ########################## | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=leaky | |
| [convolutional] | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| filters=255 | |
| activation=linear | |
| [yolo] | |
| mask = 0,1,2 | |
| anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 | |
| classes=80 | |
| num=9 | |
| jitter=.3 | |
| ignore_thresh = .7 | |
| truth_thresh = 1 | |
| scale_x_y = 1.2 | |
| iou_thresh=0.213 | |
| cls_normalizer=1.0 | |
| iou_normalizer=0.07 | |
| iou_loss=ciou | |
| nms_kind=greedynms | |
| beta_nms=0.6 | |
| max_delta=5 | |
| [route] | |
| layers = -4 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| filters=256 | |
| activation=leaky | |
| [route] | |
| layers = -1, -16 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=leaky | |
| [convolutional] | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| filters=255 | |
| activation=linear | |
| [yolo] | |
| mask = 3,4,5 | |
| anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 | |
| classes=80 | |
| num=9 | |
| jitter=.3 | |
| ignore_thresh = .7 | |
| truth_thresh = 1 | |
| scale_x_y = 1.1 | |
| iou_thresh=0.213 | |
| cls_normalizer=1.0 | |
| iou_normalizer=0.07 | |
| iou_loss=ciou | |
| nms_kind=greedynms | |
| beta_nms=0.6 | |
| max_delta=5 | |
| [route] | |
| layers = -4 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| filters=512 | |
| activation=leaky | |
| [route] | |
| layers = -1, -37 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=1024 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=1024 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=leaky | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=1024 | |
| activation=leaky | |
| [convolutional] | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| filters=255 | |
| activation=linear | |
| [yolo] | |
| mask = 6,7,8 | |
| anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401 | |
| classes=80 | |
| num=9 | |
| jitter=.3 | |
| ignore_thresh = .7 | |
| truth_thresh = 1 | |
| random=1 | |
| scale_x_y = 1.05 | |
| iou_thresh=0.213 | |
| cls_normalizer=1.0 | |
| iou_normalizer=0.07 | |
| iou_loss=ciou | |
| nms_kind=greedynms | |
| beta_nms=0.6 | |
| max_delta=5 | |