[net] # Training batch=120 subdivisions=4 # Testing #batch=1 #subdivisions=1 height=224 width=224 channels=3 momentum=0.9 decay=0.0005 max_crop=256 #mixup=4 blur=1 cutmix=1 mosaic=1 burn_in=1000 #burn_in=100 learning_rate=0.256 policy=poly power=4 max_batches=800000 momentum=0.9 decay=0.00005 angle=7 hue=.1 saturation=.75 exposure=.75 aspect=.75 ### CONV1 - 1 (1) # conv1 [convolutional] filters=32 size=3 pad=1 stride=2 batch_normalize=1 activation=swish ### CONV2 - MBConv1 - 1 (1) # conv2_1_expand [convolutional] filters=32 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv2_1_dwise [convolutional] groups=32 filters=32 size=3 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=4 (recommended r=16) [convolutional] filters=8 size=1 stride=1 activation=swish # excitation [convolutional] filters=32 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv2_1_linear [convolutional] filters=16 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV3 - MBConv6 - 1 (2) # conv2_2_expand [convolutional] filters=96 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv2_2_dwise [convolutional] groups=96 filters=96 size=3 pad=1 stride=2 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=8 (recommended r=16) [convolutional] filters=16 size=1 stride=1 activation=swish # excitation [convolutional] filters=96 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv2_2_linear [convolutional] filters=24 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV3 - MBConv6 - 2 (2) # conv3_1_expand [convolutional] filters=144 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv3_1_dwise [convolutional] groups=144 filters=144 size=3 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=8 size=1 stride=1 activation=swish # excitation [convolutional] filters=144 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv3_1_linear [convolutional] filters=24 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV4 - MBConv6 - 1 (2) # dropout only before residual connection [dropout] probability=.2 # block_3_1 [shortcut] from=-9 activation=linear # conv_3_2_expand [convolutional] filters=144 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_3_2_dwise [convolutional] groups=144 filters=144 size=5 pad=1 stride=2 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=8 size=1 stride=1 activation=swish # excitation [convolutional] filters=144 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_3_2_linear [convolutional] filters=40 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV4 - MBConv6 - 2 (2) # conv_4_1_expand [convolutional] filters=192 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_4_1_dwise [convolutional] groups=192 filters=192 size=5 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=16 size=1 stride=1 activation=swish # excitation [convolutional] filters=192 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_4_1_linear [convolutional] filters=40 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV5 - MBConv6 - 1 (3) # dropout only before residual connection [dropout] probability=.2 # block_4_2 [shortcut] from=-9 activation=linear # conv_4_3_expand [convolutional] filters=192 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_4_3_dwise [convolutional] groups=192 filters=192 size=3 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=16 size=1 stride=1 activation=swish # excitation [convolutional] filters=192 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_4_3_linear [convolutional] filters=80 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV5 - MBConv6 - 2 (3) # conv_4_4_expand [convolutional] filters=384 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_4_4_dwise [convolutional] groups=384 filters=384 size=3 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=24 size=1 stride=1 activation=swish # excitation [convolutional] filters=384 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_4_4_linear [convolutional] filters=80 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV5 - MBConv6 - 3 (3) # dropout only before residual connection [dropout] probability=.2 # block_4_4 [shortcut] from=-9 activation=linear # conv_4_5_expand [convolutional] filters=384 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_4_5_dwise [convolutional] groups=384 filters=384 size=3 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=24 size=1 stride=1 activation=swish # excitation [convolutional] filters=384 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_4_5_linear [convolutional] filters=80 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV6 - MBConv6 - 1 (3) # dropout only before residual connection [dropout] probability=.2 # block_4_6 [shortcut] from=-9 activation=linear # conv_4_7_expand [convolutional] filters=384 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_4_7_dwise [convolutional] groups=384 filters=384 size=5 pad=1 stride=2 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=24 size=1 stride=1 activation=swish # excitation [convolutional] filters=384 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_4_7_linear [convolutional] filters=112 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV6 - MBConv6 - 2 (3) # conv_5_1_expand [convolutional] filters=576 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_5_1_dwise [convolutional] groups=576 filters=576 size=5 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=32 size=1 stride=1 activation=swish # excitation [convolutional] filters=576 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_5_1_linear [convolutional] filters=112 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV6 - MBConv6 - 3 (3) # dropout only before residual connection [dropout] probability=.2 # block_5_1 [shortcut] from=-9 activation=linear # conv_5_2_expand [convolutional] filters=576 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_5_2_dwise [convolutional] groups=576 filters=576 size=5 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=32 size=1 stride=1 activation=swish # excitation [convolutional] filters=576 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_5_2_linear [convolutional] filters=112 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV7 - MBConv6 - 1 (4) # dropout only before residual connection [dropout] probability=.2 # block_5_2 [shortcut] from=-9 activation=linear # conv_5_3_expand [convolutional] filters=576 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_5_3_dwise [convolutional] groups=576 filters=576 size=5 pad=1 stride=2 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=32 size=1 stride=1 activation=swish # excitation [convolutional] filters=576 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_5_3_linear [convolutional] filters=192 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV7 - MBConv6 - 2 (4) # conv_6_1_expand [convolutional] filters=960 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_6_1_dwise [convolutional] groups=960 filters=960 size=5 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=64 size=1 stride=1 activation=swish # excitation [convolutional] filters=960 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_6_1_linear [convolutional] filters=192 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV7 - MBConv6 - 3 (4) # dropout only before residual connection [dropout] probability=.2 # block_6_1 [shortcut] from=-9 activation=linear # conv_6_2_expand [convolutional] filters=960 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_6_2_dwise [convolutional] groups=960 filters=960 size=5 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=64 size=1 stride=1 activation=swish # excitation [convolutional] filters=960 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_6_2_linear [convolutional] filters=192 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV7 - MBConv6 - 4 (4) # dropout only before residual connection [dropout] probability=.2 # block_6_1 [shortcut] from=-9 activation=linear # conv_6_2_expand [convolutional] filters=960 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_6_2_dwise [convolutional] groups=960 filters=960 size=5 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=64 size=1 stride=1 activation=swish # excitation [convolutional] filters=960 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_6_2_linear [convolutional] filters=192 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV8 - MBConv6 - 1 (1) # dropout only before residual connection [dropout] probability=.2 # block_6_2 [shortcut] from=-9 activation=linear # conv_6_3_expand [convolutional] filters=960 size=1 stride=1 pad=0 batch_normalize=1 activation=swish # conv_6_3_dwise [convolutional] groups=960 filters=960 size=3 stride=1 pad=1 batch_normalize=1 activation=swish #squeeze-n-excitation [avgpool] # squeeze ratio r=16 (recommended r=16) [convolutional] filters=64 size=1 stride=1 activation=swish # excitation [convolutional] filters=960 size=1 stride=1 activation=logistic # multiply channels [scale_channels] from=-4 # conv_6_3_linear [convolutional] filters=320 size=1 stride=1 pad=0 batch_normalize=1 activation=linear ### CONV9 - Conv2d 1x1 # conv_6_4 [convolutional] filters=1280 size=1 stride=1 pad=0 batch_normalize=1 activation=swish [avgpool] [dropout] probability=.2 [convolutional] filters=1000 size=1 stride=1 pad=0 activation=linear [softmax] groups=1 #[cost] #type=sse