TuSimple / centerformer

Implementation for CenterFormer: Center-based Transformer for 3D Object Detection (ECCV 2022)
MIT License
294 stars 28 forks source link

example["times"] #41

Open ryanyej opened 3 months ago

ryanyej commented 3 months ago

In multi frame x_up_fuse = torch.cat((x_up, x_prev_cat), dim=1) + self.time_embedding( example["times"][:, :, None].to(x_up) ).reshape(x_up.shape[0], -1, 1, 1)

what does 'times' means? B*K, means time interval of this frame with last frame?

Looking forward to your reply.