def __init__(self,
in_channels,
num_anchors,
num_classes,
num_layers,
pyramid_levels=5,
onnx_export=False):
super(Classifier, self).__init__()
self.num_anchors = num_anchors
self.num_classes = num_classes
self.num_layers = num_layers
self.conv_list = nn.ModuleList([
SeparableConvBlock(in_channels,
in_channels,
norm=False,
activation=False) for i in range(num_layers)
])
self.bn_list = nn.ModuleList([
nn.ModuleList([
nn.BatchNorm2d(in_channels, momentum=0.01, eps=1e-3)
for i in range(num_layers)
]) for j in range(pyramid_levels)
])
self.header = SeparableConvBlock(in_channels,
num_anchors * num_classes,
norm=False,
activation=False)
self.swish = MemoryEfficientSwish() if not onnx_export else Swish()
def set_swish(self, memory_efficient=True):
"""Sets swish function as memory efficient (for training) or standard (for export)"""
self._swish = MemoryEfficientSwish() if memory_efficient else Swish()
for block in self._blocks:
block.set_swish(memory_efficient)
def __init__(self,
num_channels,
conv_channels,
first_time=False,
epsilon=1e-4,
onnx_export=False,
attention=True,
use_p8=False):
"""
Args:
num_channels:
conv_channels:
first_time: whether the input comes directly from the efficientnet,
if True, downchannel it first, and downsample P5 to generate P6 then P7
epsilon: epsilon of fast weighted attention sum of BiFPN, not the BN's epsilon
onnx_export: if True, use Swish instead of MemoryEfficientSwish
"""
super(BiFPN, self).__init__()
self.epsilon = epsilon
self.use_p8 = use_p8
# Conv layers
self.conv6_up = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
self.conv5_up = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
self.conv4_up = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
self.conv3_up = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
self.conv4_down = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
self.conv5_down = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
self.conv6_down = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
self.conv7_down = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
if use_p8:
self.conv7_up = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
self.conv8_down = SeparableConvBlock(num_channels,
onnx_export=onnx_export)
# Feature scaling layers
self.p6_upsample = nn.Upsample(scale_factor=2, mode='nearest')
self.p5_upsample = nn.Upsample(scale_factor=2, mode='nearest')
self.p4_upsample = nn.Upsample(scale_factor=2, mode='nearest')
self.p3_upsample = nn.Upsample(scale_factor=2, mode='nearest')
self.p4_downsample = MaxPool2dStaticSamePadding(3, 2)
self.p5_downsample = MaxPool2dStaticSamePadding(3, 2)
self.p6_downsample = MaxPool2dStaticSamePadding(3, 2)
self.p7_downsample = MaxPool2dStaticSamePadding(3, 2)
if use_p8:
self.p7_upsample = nn.Upsample(scale_factor=2, mode='nearest')
self.p8_downsample = MaxPool2dStaticSamePadding(3, 2)
self.swish = MemoryEfficientSwish() if not onnx_export else Swish()
self.first_time = first_time
if self.first_time:
self.p5_down_channel = nn.Sequential(
Conv2dStaticSamePadding(conv_channels[2], num_channels, 1),
nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3),
)
self.p4_down_channel = nn.Sequential(
Conv2dStaticSamePadding(conv_channels[1], num_channels, 1),
nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3),
)
self.p3_down_channel = nn.Sequential(
Conv2dStaticSamePadding(conv_channels[0], num_channels, 1),
nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3),
)
self.p5_to_p6 = nn.Sequential(
Conv2dStaticSamePadding(conv_channels[2], num_channels, 1),
nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3),
MaxPool2dStaticSamePadding(3, 2))
self.p6_to_p7 = nn.Sequential(MaxPool2dStaticSamePadding(3, 2))
if use_p8:
self.p7_to_p8 = nn.Sequential(MaxPool2dStaticSamePadding(3, 2))
self.p4_down_channel_2 = nn.Sequential(
Conv2dStaticSamePadding(conv_channels[1], num_channels, 1),
nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3),
)
self.p5_down_channel_2 = nn.Sequential(
Conv2dStaticSamePadding(conv_channels[2], num_channels, 1),
nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3),
)
# Weight
self.p6_w1 = nn.Parameter(torch.ones(2, dtype=torch.float32),
requires_grad=True)
self.p6_w1_relu = nn.ReLU()
self.p5_w1 = nn.Parameter(torch.ones(2, dtype=torch.float32),
requires_grad=True)
self.p5_w1_relu = nn.ReLU()
self.p4_w1 = nn.Parameter(torch.ones(2, dtype=torch.float32),
requires_grad=True)
self.p4_w1_relu = nn.ReLU()
self.p3_w1 = nn.Parameter(torch.ones(2, dtype=torch.float32),
requires_grad=True)
self.p3_w1_relu = nn.ReLU()
self.p4_w2 = nn.Parameter(torch.ones(3, dtype=torch.float32),
requires_grad=True)
self.p4_w2_relu = nn.ReLU()
self.p5_w2 = nn.Parameter(torch.ones(3, dtype=torch.float32),
requires_grad=True)
self.p5_w2_relu = nn.ReLU()
self.p6_w2 = nn.Parameter(torch.ones(3, dtype=torch.float32),
requires_grad=True)
self.p6_w2_relu = nn.ReLU()
self.p7_w2 = nn.Parameter(torch.ones(2, dtype=torch.float32),
requires_grad=True)
self.p7_w2_relu = nn.ReLU()
self.attention = attention