CenterFusion 改进DLAseg模型 卷积层

DLASeg(
(hm): Sequential(
(0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 10, kernel_size=(1, 1), stride=(1, 1))
)
(reg): Sequential(
(0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 2, kernel_size=(1, 1), stride=(1, 1))
)
(wh): Sequential(
(0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 2, kernel_size=(1, 1), stride=(1, 1))
)
(dep): Sequential(
(0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 1, kernel_size=(1, 1), stride=(1, 1))
)
(rot): Sequential(
(0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 8, kernel_size=(1, 1), stride=(1, 1))
)
(dim): Sequential(
(0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
)
(amodel_offset): Sequential(
(0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 2, kernel_size=(1, 1), stride=(1, 1))
)
(dep_sec): Sequential(
(0): Conv2d(67, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(3): ReLU(inplace=True)
(4): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(5): ReLU(inplace=True)
(6): Conv2d(256, 1, kernel_size=(1, 1), stride=(1, 1))
)
(rot_sec): Sequential(
(0): Conv2d(67, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(3): ReLU(inplace=True)
(4): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(5): ReLU(inplace=True)
(6): Conv2d(256, 8, kernel_size=(1, 1), stride=(1, 1))
)
(nuscenes_att): Sequential(
(0): Conv2d(67, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(3): ReLU(inplace=True)
(4): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(5): ReLU(inplace=True)
(6): Conv2d(256, 8, kernel_size=(1, 1), stride=(1, 1))
)
(velocity): Sequential(
(0): Conv2d(67, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(3): ReLU(inplace=True)
(4): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(5): ReLU(inplace=True)
(6): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
)
(base): DLA(
(base_layer): Sequential(
(0): Conv2d(3, 16, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(level0): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(level1): Sequential(
(0): Conv2d(16, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
)
(level2): Tree(
(tree1): BasicBlock(
(conv1): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(tree2): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(root): Root(
(conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(downsample): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(project): Sequential(
(0): Conv2d(32, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(level3): Tree(
(tree1): Tree(
(tree1): BasicBlock(
(conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(tree2): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(root): Root(
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(downsample): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(project): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(tree2): Tree(
(tree1): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(tree2): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(root): Root(
(conv): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(downsample): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(project): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(level4): Tree(
(tree1): Tree(
(tree1): BasicBlock(
(conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(tree2): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(root): Root(
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(downsample): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(project): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(tree2): Tree(
(tree1): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(tree2): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(root): Root(
(conv): Conv2d(896, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
)
(downsample): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(project): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(level5): Tree(
(tree1): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(tree2): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(root): Root(
(conv): Conv2d(1280, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
)
(downsample): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(project): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
)
(dla_up): DLAUp(
(ida_0): IDAUp(
(proj_1): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(512, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(up_1): ConvTranspose2d(256, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), groups=256, bias=False)
(node_1): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
)
(ida_1): IDAUp(
(proj_1): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(up_1): ConvTranspose2d(128, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), groups=128, bias=False)
(node_1): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(128, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(proj_2): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(up_2): ConvTranspose2d(128, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), groups=128, bias=False)
(node_2): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(128, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
)
(ida_2): IDAUp(
(proj_1): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(128, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(up_1): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), groups=64, bias=False)
(node_1): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(64, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(proj_2): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(128, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(up_2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), groups=64, bias=False)
(node_2): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(64, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(proj_3): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(128, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(up_3): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), groups=64, bias=False)
(node_3): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(64, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
)
)
(ida_up): IDAUp(
(proj_1): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(128, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(up_1): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), groups=64, bias=False)
(node_1): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(64, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(proj_2): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(256, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
(up_2): ConvTranspose2d(64, 64, kernel_size=(8, 8), stride=(4, 4), padding=(2, 2), groups=64, bias=False)
(node_2): DeformConv(
(actf): Sequential(
(0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU(inplace=True)
)
(conv): DCN(
(conv_offset_mask): Conv2d(64, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
)
)