Spaces:
Runtime error
Runtime error
| [net] | |
| batch=64 | |
| subdivisions=8 | |
| width=1280 | |
| height=1280 | |
| channels=3 | |
| momentum=0.949 | |
| decay=0.0005 | |
| angle=0 | |
| saturation = 1.5 | |
| exposure = 1.5 | |
| hue=.1 | |
| learning_rate=0.00261 | |
| burn_in=1000 | |
| max_batches = 500500 | |
| policy=steps | |
| steps=400000,450000 | |
| scales=.1,.1 | |
| mosaic=1 | |
| # ============ Backbone ============ # | |
| # Stem | |
| # 0 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=32 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # P1 | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=32 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=32 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Residual Block | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=32 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=32 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| # Transition first | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=32 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Merge [-1, -(3k+4)] | |
| [route] | |
| layers = -1,-7 | |
| # Transition last | |
| # 10 (previous+7+3k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # P2 | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [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 | |
| # Residual Block | |
| [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 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [shortcut] | |
| from=-3 | |
| activation=linear | |
| # Transition first | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=64 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Merge [-1, -(3k+4)] | |
| [route] | |
| layers = -1,-13 | |
| # Transition last | |
| # 26 (previous+7+3k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # P3 | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [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 | |
| # Residual Block | |
| [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 | |
| [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 | |
| # Transition first | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Merge [-1, -(3k+4)] | |
| [route] | |
| layers = -1,-49 | |
| # Transition last | |
| # 78 (previous+7+3k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # P4 | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [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 | |
| # Residual Block | |
| [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 | |
| [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 | |
| # Transition first | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Merge [-1, -(3k+4)] | |
| [route] | |
| layers = -1,-49 | |
| # Transition last | |
| # 130 (previous+7+3k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # P5 | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=1024 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [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 | |
| # Residual Block | |
| [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 | |
| [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 | |
| # Transition first | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Merge [-1, -(3k+4)] | |
| [route] | |
| layers = -1,-25 | |
| # Transition last | |
| # 158 (previous+7+3k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=1024 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # P6 | |
| # Downsample | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=1024 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [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 | |
| # Residual Block | |
| [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 | |
| [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 | |
| # Transition first | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Merge [-1, -(3k+4)] | |
| [route] | |
| layers = -1,-25 | |
| # Transition last | |
| # 186 (previous+7+3k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=1024 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # ============ End of Backbone ============ # | |
| # ============ Neck ============ # | |
| # CSPSPP | |
| [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 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| ### 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=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [route] | |
| layers = -1, -13 | |
| # 201 (previous+6+5+2k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # End of CSPSPP | |
| # FPN-5 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [upsample] | |
| stride=2 | |
| [route] | |
| layers = 158 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -1, -3 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| # Plain Block | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| # Merge [-1, -(2k+2)] | |
| [route] | |
| layers = -1, -8 | |
| # Transition last | |
| # 217 (previous+6+4+2k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # FPN-4 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [upsample] | |
| stride=2 | |
| [route] | |
| layers = 130 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -1, -3 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| # Plain Block | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=mish | |
| # Merge [-1, -(2k+2)] | |
| [route] | |
| layers = -1, -8 | |
| # Transition last | |
| # 233 (previous+6+4+2k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # FPN-3 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [upsample] | |
| stride=2 | |
| [route] | |
| layers = 78 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -1, -3 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| # Plain Block | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=128 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=128 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=128 | |
| activation=mish | |
| # Merge [-1, -(2k+2)] | |
| [route] | |
| layers = -1, -8 | |
| # Transition last | |
| # 249 (previous+6+4+2k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=128 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # PAN-4 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| filters=256 | |
| activation=mish | |
| [route] | |
| layers = -1, 233 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| # Plain Block | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=mish | |
| [route] | |
| layers = -1,-8 | |
| # Transition last | |
| # 262 (previous+3+4+2k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=256 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # PAN-5 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [route] | |
| layers = -1, 217 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| # Plain Block | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [route] | |
| layers = -1,-8 | |
| # Transition last | |
| # 275 (previous+3+4+2k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # PAN-6 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=2 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [route] | |
| layers = -1, 201 | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # Split | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [route] | |
| layers = -2 | |
| # Plain Block | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [route] | |
| layers = -1,-8 | |
| # Transition last | |
| # 288 (previous+3+4+2k) | |
| [convolutional] | |
| batch_normalize=1 | |
| filters=512 | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| activation=mish | |
| # ============ End of Neck ============ # | |
| # ============ Head ============ # | |
| # YOLO-3 | |
| [route] | |
| layers = 249 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=256 | |
| activation=mish | |
| [convolutional] | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| filters=340 | |
| activation=linear | |
| [yolo] | |
| mask = 0,1,2,3 | |
| anchors = 13,17, 31,25, 24,51, 61,45, 61,45, 48,102, 119,96, 97,189, 97,189, 217,184, 171,384, 324,451, 324,451, 545,357, 616,618, 1024,1024 | |
| classes=80 | |
| num=16 | |
| 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 | |
| # YOLO-4 | |
| [route] | |
| layers = 262 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=512 | |
| activation=mish | |
| [convolutional] | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| filters=340 | |
| activation=linear | |
| [yolo] | |
| mask = 4,5,6,7 | |
| anchors = 13,17, 31,25, 24,51, 61,45, 61,45, 48,102, 119,96, 97,189, 97,189, 217,184, 171,384, 324,451, 324,451, 545,357, 616,618, 1024,1024 | |
| classes=80 | |
| num=16 | |
| 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 | |
| # YOLO-5 | |
| [route] | |
| layers = 275 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=1024 | |
| activation=mish | |
| [convolutional] | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| filters=340 | |
| activation=linear | |
| [yolo] | |
| mask = 8,9,10,11 | |
| anchors = 13,17, 31,25, 24,51, 61,45, 61,45, 48,102, 119,96, 97,189, 97,189, 217,184, 171,384, 324,451, 324,451, 545,357, 616,618, 1024,1024 | |
| classes=80 | |
| num=16 | |
| 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 | |
| # YOLO-6 | |
| [route] | |
| layers = 288 | |
| [convolutional] | |
| batch_normalize=1 | |
| size=3 | |
| stride=1 | |
| pad=1 | |
| filters=1024 | |
| activation=mish | |
| [convolutional] | |
| size=1 | |
| stride=1 | |
| pad=1 | |
| filters=340 | |
| activation=linear | |
| [yolo] | |
| mask = 12,13,14,15 | |
| anchors = 13,17, 31,25, 24,51, 61,45, 61,45, 48,102, 119,96, 97,189, 97,189, 217,184, 171,384, 324,451, 324,451, 545,357, 616,618, 1024,1024 | |
| classes=80 | |
| num=16 | |
| 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 | |
| # ============ End of Head ============ # | |