def __init__(self, in_channels=32 + 32, out_channels=32):
super(AgentsMapFusion, self).__init__()
self._conv1 = conv2DBatchNormRelu(in_channels=in_channels,
n_filters=out_channels,
k_size=3,
stride=1,
padding=1,
dilation=1)
self._pool1 = nn.MaxPool2d((2, 2), stride=(2, 2))
self._conv2 = conv2DBatchNormRelu(in_channels=out_channels,
n_filters=out_channels,
k_size=3,
stride=1,
padding=1,
dilation=1)
self._pool2 = nn.MaxPool2d((2, 2), stride=(2, 2))
self._conv3 = conv2DBatchNormRelu(in_channels=out_channels,
n_filters=out_channels,
k_size=4,
stride=1,
padding=1,
dilation=1)
self._deconv2 = deconv2DBatchNormRelu(in_channels=out_channels,
n_filters=out_channels,
k_size=4,
stride=2,
padding=1)
def __init__(self, in_channels = 3, out_channels = 32):
super(SemanticImageEncoder, self).__init__()
self._encoder = nn.Sequential(
conv2DBatchNormRelu(in_channels = in_channels, n_filters = 16, \
k_size = 3, stride = 1, padding = 1),
conv2DBatchNormRelu(in_channels = 16, n_filters = 16, \
k_size = 4, stride = 1, padding = 2),
nn.MaxPool2d((2, 2), stride=(2, 2)),
conv2DBatchNormRelu(in_channels = 16, n_filters = out_channels, \
k_size = 5, stride = 1, padding = 2),
)
def __init__(self): # Output Size: 30 * 30
super(ResnetShallow, self).__init__()
self.trunk = torchvision.models.resnet18(pretrained=True)
self.upscale3 = nn.Sequential(
nn.ConvTranspose2d(256,
128,
3,
stride=2,
padding=1,
output_padding=1),
nn.BatchNorm2d(128),
nn.ReLU(inplace=True),
)
self.upscale4 = nn.Sequential(
nn.ConvTranspose2d(512,
128,
7,
stride=4,
padding=3,
output_padding=3),
nn.BatchNorm2d(128),
nn.ReLU(inplace=True),
)
self.shrink = conv2DBatchNormRelu(in_channels=384,
n_filters=32,
k_size=1,
stride=1,
padding=0)
def __init__(self,
n_classes=7,
block_config=[3, 4, 6, 3],
input_size=(800, 600),
version=None):
super(PSPnet, self).__init__()
self.block_config = (pspnet_specs[version]["block_config"]
if version is not None else block_config)
self.n_classes = pspnet_specs[version][
"n_classes"] if version is not None else n_classes
self.input_size = pspnet_specs[version][
"input_size"] if version is not None else input_size
# Encoder
self.convbnrelu1_1 = conv2DBatchNormRelu(in_channels=3,
k_size=3,
n_filters=64,
padding=1,
stride=2,
bias=False)
self.convbnrelu1_2 = conv2DBatchNormRelu(in_channels=64,
k_size=3,
n_filters=64,
padding=1,
stride=1,
bias=False)
self.convbnrelu1_3 = conv2DBatchNormRelu(in_channels=64,
k_size=3,
n_filters=128,
padding=1,
stride=1,
bias=False)
# Vanilla Residual Blocks
self.res_block2 = residualBlockPSP(self.block_config[0], 128, 64, 256,
1, 1)
self.res_block3 = residualBlockPSP(self.block_config[1], 256, 128, 512,
2, 1)
# Dilated Residual Blocks
self.res_block4 = residualBlockPSP(self.block_config[2], 512, 256,
1024, 1, 2)
self.res_block5 = residualBlockPSP(self.block_config[3], 1024, 512,
2048, 1, 4)
# Pyramid Pooling Module
self.pyramid_pooling = pyramidPooling(2048, [6, 3, 2, 1])
# Final conv layers
self.cbr_final = conv2DBatchNormRelu(4096, 512, 3, 1, 1, False)
self.dropout = nn.Dropout2d(p=0.1, inplace=False)
self.classification = nn.Conv2d(512, self.n_classes, 1, 1, 0)
# Auxiliary layers for training
self.convbnrelu4_aux = conv2DBatchNormRelu(in_channels=1024,
k_size=3,
n_filters=256,
padding=1,
stride=1,
bias=False)
self.aux_cls = nn.Conv2d(256, self.n_classes, 1, 1, 0)
# Define auxiliary loss function
self.loss = multi_scale_cross_entropy2d
self.load_pretrained_model("pspnet50_ADE20K.caffemodel")
def __init__(
self,
n_classes=19,
block_config=None,
input_size=(1025, 2049),
version=None,
is_batchnorm=True,
):
super(ICNet, self).__init__()
self._is_batchnorm = is_batchnorm
block_config = block_config or [3, 4, 6, 3]
bias = not is_batchnorm
self.block_config = (
icnet_specs[version]["block_config"] if version is not None else block_config
)
self.n_classes = icnet_specs[version]["n_classes"] if version is not None else n_classes
self.input_size = icnet_specs[version]["input_size"] if version is not None else input_size
# Encoder
self.convbnrelu1_1 = conv2DBatchNormRelu(
in_channels=3,
k_size=3,
n_filters=32,
padding=1,
stride=2,
bias=bias,
is_batchnorm=is_batchnorm,
)
self.convbnrelu1_2 = conv2DBatchNormRelu(
in_channels=32,
k_size=3,
n_filters=32,
padding=1,
stride=1,
bias=bias,
is_batchnorm=is_batchnorm,
)
self.convbnrelu1_3 = conv2DBatchNormRelu(
in_channels=32,
k_size=3,
n_filters=64,
padding=1,
stride=1,
bias=bias,
is_batchnorm=is_batchnorm,
)
# Vanilla Residual Blocks
self.res_block2 = residualBlockPSP(
self.block_config[0], 64, 32, 128, 1, 1, is_batchnorm=is_batchnorm
)
self.res_block3_conv = residualBlockPSP(
self.block_config[1],
128,
64,
256,
2,
1,
include_range="conv",
is_batchnorm=is_batchnorm,
)
self.res_block3_identity = residualBlockPSP(
self.block_config[1],
128,
64,
256,
2,
1,
include_range="identity",
is_batchnorm=is_batchnorm,
)
# Dilated Residual Blocks
self.res_block4 = residualBlockPSP(
self.block_config[2], 256, 128, 512, 1, 2, is_batchnorm=is_batchnorm
)
self.res_block5 = residualBlockPSP(
self.block_config[3], 512, 256, 1024, 1, 4, is_batchnorm=is_batchnorm
)
# Pyramid Pooling Module
self.pyramid_pooling = pyramidPooling(
1024, [6, 3, 2, 1], model_name="icnet", fusion_mode="sum", is_batchnorm=is_batchnorm
)
# Final conv layer with kernel 1 in sub4 branch
self.conv5_4_k1 = conv2DBatchNormRelu(
in_channels=1024,
k_size=1,
n_filters=256,
padding=0,
stride=1,
bias=bias,
is_batchnorm=is_batchnorm,
)
# High-resolution (sub1) branch
self.convbnrelu1_sub1 = conv2DBatchNormRelu(
in_channels=3,
k_size=3,
n_filters=32,
padding=1,
stride=2,
bias=bias,
is_batchnorm=is_batchnorm,
)
self.convbnrelu2_sub1 = conv2DBatchNormRelu(
in_channels=32,
k_size=3,
n_filters=32,
padding=1,
stride=2,
bias=bias,
is_batchnorm=is_batchnorm,
)
self.convbnrelu3_sub1 = conv2DBatchNormRelu(
in_channels=32,
k_size=3,
n_filters=64,
padding=1,
stride=2,
bias=bias,
is_batchnorm=is_batchnorm,
)
self.classification = nn.Conv2d(128, self.n_classes, 1, 1, 0)
# Cascade Feature Fusion Units
self.cff_sub24 = cascadeFeatureFusion(
self.n_classes, 256, 256, 128, is_batchnorm=is_batchnorm
)
self.cff_sub12 = cascadeFeatureFusion(
self.n_classes, 128, 64, 128, is_batchnorm=is_batchnorm
)