File size: 5,599 Bytes
ceb46c5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 |
import math
import torch.nn as nn
from transformers import PreTrainedModel
from .configuration_resnet import ResEncoderConfig
def conv3x3(in_planes, out_planes, stride=1):
return nn.Conv2d(
in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False
)
def downsample_basic_block(inplanes, outplanes, stride):
return nn.Sequential(
nn.Conv2d(inplanes, outplanes, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(outplanes),
)
def downsample_basic_block_v2(inplanes, outplanes, stride):
return nn.Sequential(
nn.AvgPool2d(
kernel_size=stride, stride=stride, ceil_mode=True, count_include_pad=False
),
nn.Conv2d(inplanes, outplanes, kernel_size=1, stride=1, bias=False),
nn.BatchNorm2d(outplanes),
)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, relu_type="relu"):
super(BasicBlock, self).__init__()
assert relu_type in ["relu", "prelu"]
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
if relu_type == "relu":
self.relu1 = nn.ReLU(inplace=True)
self.relu2 = nn.ReLU(inplace=True)
elif relu_type == "prelu":
self.relu1 = nn.PReLU(num_parameters=planes)
self.relu2 = nn.PReLU(num_parameters=planes)
else:
raise Exception("relu type not implemented")
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu1(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu2(out)
return out
class ResNet(nn.Module):
def __init__(
self,
block,
layers,
num_classes=1000,
relu_type="relu",
gamma_zero=False,
avg_pool_downsample=False,
):
self.inplanes = 64
self.relu_type = relu_type
self.gamma_zero = gamma_zero
self.downsample_block = (
downsample_basic_block_v2 if avg_pool_downsample else downsample_basic_block
)
super(ResNet, self).__init__()
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d(1)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2.0 / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
if self.gamma_zero:
for m in self.modules():
if isinstance(m, BasicBlock):
m.bn2.weight.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = self.downsample_block(
inplanes=self.inplanes,
outplanes=planes * block.expansion,
stride=stride,
)
layers = []
layers.append(
block(self.inplanes, planes, stride, downsample, relu_type=self.relu_type)
)
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, relu_type=self.relu_type))
return nn.Sequential(*layers)
def forward(self, x):
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
return x
class ResEncoder(PreTrainedModel):
def __init__(self, config: ResEncoderConfig):
super(ResEncoder, self).__init__(config=config)
self.frontend_nout = config.frontend_nout
self.backend_out = config.backend_out
frontend_relu = (
nn.PReLU(num_parameters=self.frontend_nout)
if config.relu_type == "prelu"
else nn.ReLU()
)
self.frontend3D = nn.Sequential(
nn.Conv3d(
1,
self.frontend_nout,
kernel_size=(5, 7, 7),
stride=(1, 2, 2),
padding=(2, 3, 3),
bias=False,
),
nn.BatchNorm3d(self.frontend_nout),
frontend_relu,
nn.MaxPool3d(kernel_size=(1, 3, 3), stride=(1, 2, 2), padding=(0, 1, 1)),
)
self.trunk = ResNet(BasicBlock, [2, 2, 2, 2], relu_type=config.relu_type)
def forward(self, x):
B, C, T, H, W = x.size()
x = self.frontend3D(x)
Tnew = x.shape[2]
x = self.threeD_to_2D_tensor(x)
x = self.trunk(x)
x = x.view(B, Tnew, x.size(1))
x = x.transpose(1, 2).contiguous()
return x
def threeD_to_2D_tensor(self, x):
n_batch, n_channels, s_time, sx, sy = x.shape
x = x.transpose(1, 2).contiguous()
return x.reshape(n_batch * s_time, n_channels, sx, sy)
|