Using resnet152 as a backbone of Faaster RCNN

1

Hi there,

For training pretrain detector, I usesd following code using resnet 101 as a backbone:

from torchvision.models.resnet import resnet101
self.features = load_resnet()
self.compress = nn.Sequential(
nn.Conv2d(1024, 256, kernel_size=1),
nn.ReLU(inplace=True),
nn.BatchNorm2d(256),
)
self.roi_fmap = nn.Sequential(
nn.Linear(256 * 7 * 7, 2048),
nn.RELU(inplace=True),
nn.Linear(2048, 2048),
nn.RELU(inplace=True),
nn.Dropout(p=0.05),
)
How can I replace resnet 152 instead of 101?