Open HydrogenWasser opened 1 year ago
In your paper, about the part of attention output of I2P block, it said the query should be image feature.
but in your code, encoder_utils, line 284,
Q = lidar_feat[b,:,voxel_coor[:,2].long(),voxel_coor[:,3].long()].t().unsqueeze(1)
it seems the query is lidar feature but not image feature
In your paper, about the part of attention output of I2P block, it said the query should be image feature.
but in your code, encoder_utils, line 284,
Q = lidar_feat[b,:,voxel_coor[:,2].long(),voxel_coor[:,3].long()].t().unsqueeze(1)
it seems the query is lidar feature but not image feature