detnet.py - why are features stacked with extra tiles ?
zisismp4 opened this issue · 1 comments
zisismp4 commented
class detnet(nn.Module):
def forward(self, x):
features = self.resnet50(x)
device = x.device
pos_tile = get_pose_tile_torch(features.shape[0]).to(device)
x = torch.cat([features, pos_tile], dim=1)
could you please explain what is the purpose of this pos_tile and why is needed to concat with features?
MengHao666 commented
Hi, it might not be useful for the results. But the offical project contain such process, u might remove it and see what would happen.