diff --git a/build/darknet/x64/cfg/darknet53_448_xnor.cfg b/build/darknet/x64/cfg/darknet53_448_xnor.cfg new file mode 100644 index 00000000..a48ef698 --- /dev/null +++ b/build/darknet/x64/cfg/darknet53_448_xnor.cfg @@ -0,0 +1,619 @@ +[net] +# Training - start training with darknet53.weights +batch=120 +subdivisions=20 + +# Testing +#batch=1 +#subdivisions=1 + +height=448 +width=448 +channels=3 +min_crop=448 +max_crop=512 + +burn_in=1000 +learning_rate=0.1 +policy=poly +power=4 +max_batches=100000 +momentum=0.9 +decay=0.0005 + + +[convolutional] +batch_normalize=1 +filters=32 +size=3 +stride=1 +pad=1 +activation=leaky + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=64 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=32 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[avgpool] + +[convolutional] +filters=1000 +size=1 +stride=1 +pad=1 +activation=linear + +[softmax] +groups=1 + diff --git a/build/darknet/yolo_cpp_dll.vcxproj b/build/darknet/yolo_cpp_dll.vcxproj index b1476699..b4d19765 100644 --- a/build/darknet/yolo_cpp_dll.vcxproj +++ b/build/darknet/yolo_cpp_dll.vcxproj @@ -228,6 +228,7 @@ + @@ -288,6 +289,7 @@ + diff --git a/cfg/darknet53_448_xnor.cfg b/cfg/darknet53_448_xnor.cfg new file mode 100644 index 00000000..a48ef698 --- /dev/null +++ b/cfg/darknet53_448_xnor.cfg @@ -0,0 +1,619 @@ +[net] +# Training - start training with darknet53.weights +batch=120 +subdivisions=20 + +# Testing +#batch=1 +#subdivisions=1 + +height=448 +width=448 +channels=3 +min_crop=448 +max_crop=512 + +burn_in=1000 +learning_rate=0.1 +policy=poly +power=4 +max_batches=100000 +momentum=0.9 +decay=0.0005 + + +[convolutional] +batch_normalize=1 +filters=32 +size=3 +stride=1 +pad=1 +activation=leaky + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=64 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=32 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=64 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=64 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=128 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=256 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +# Downsample + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=2 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +xnor=1 +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[convolutional] +xnor=1 +batch_normalize=1 +filters=1024 +size=3 +stride=1 +pad=1 +activation=leaky + +[shortcut] +from=-3 +activation=linear + +[convolutional] +batch_normalize=1 +filters=512 +size=1 +stride=1 +pad=1 +activation=leaky + +[avgpool] + +[convolutional] +filters=1000 +size=1 +stride=1 +pad=1 +activation=linear + +[softmax] +groups=1 +