how to

[jngechong]

I prepare to use your launch to test multi-robot-slam with segmap，but how cloud I get the bag used in your launch？such as 2011_10_03_drive_27_30_113_na0.bag.Actually I have 2011_10_03_drive_27.bag

[gopi-erabati]

You can use the tools provided at [https://github.com/ethz-asl/segmap/tree/master/tools]

[jngechong]

Thank you very much for your answer. And now I meet other questions. I didn't use the tools that you tell me, because I'm not familiar with python. I browsed the website you provided and I guess the function of the program is to cut the original bag to new bags, so I did this job by using "rosbag fileter ...." and I got four bags. Then I run the launch named "cnn_kitti_loop_closure_multi.launch" and then I have some problems:

`_I1217 20:44:32.492146 8844 segmapper.cpp:86] Robot 0 subscribes to /na0//velodyne_points na0/world and na0/velodyne I1217 20:44:32.492166 8844 segmapper.cpp:89] Robot 0 publishes to na0/trajectory and na0/local_map I1217 20:44:32.504279 8844 segmapper.cpp:86] Robot 1 subscribes to /na1//velodyne_points na1/world and na1/velodyne I1217 20:44:32.504295 8844 segmapper.cpp:89] Robot 1 publishes to na1/trajectory and na1/local_map [ERROR] [1608209072.512528263]: Tried to advertise a service that is already advertised in this node [/segmapper/get_laser_track] [ERROR] [1608209072.512558849]: Tried to advertise a service that is already advertised in this node [/segmapper/export_trajectory] I1217 20:44:32.512585 8844 segmapper.cpp:86] Robot 2 subscribes to /na2//velodyne_points na2/world and na2/velodyne I1217 20:44:32.512607 8844 segmapper.cpp:89] Robot 2 publishes to na2/trajectory and na2/local_map [ERROR] [1608209072.518633659]: Tried to advertise a service that is already advertised in this node [/segmapper/get_laser_track] [ERROR] [1608209072.518663508]: Tried to advertise a service that is already advertised in this node [/segmapper/export_trajectory] I1217 20:44:32.518687 8844 segmapper.cpp:86] Robot 3 subscribes to /na3//velodyne_points na3/world and na3/velodyne I1217 20:44:32.518697 8844 segmapper.cpp:89] Robot 3 publishes to na3/trajectory and na3/local_map [ERROR] [1608209072.526571693]: Tried to advertise a service that is already advertised in this node [/segmapper/get_laser_track] [ERROR] [1608209072.526622288]: Tried to advertise a service that is already advertised in this node [/segmapper/export_trajectory] I1217 20:44:32.527637 8844 cnn.hpp:20] Loading CNN model in /home/iairloc/.segmap/trained_models/segmap64/ 2020-12-17 20:44:32.527693: I /home/iairloc/segmap_ws/src/segmap/tf_graph_executor/src/tf_graph_executor.cpp:17] Entering TensorflowGraphExecutor with path /home/iairloc/.segmap/trained_models/segmap64/model.ckpt.meta 2020-12-17 20:44:32.604537: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2020-12-17 20:44:32.604818: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1356] Found device 0 with properties: name: GeForce GTX 1050 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.392 pciBusID: 0000:01:00.0 totalMemory: 3.94GiB freeMemory: 3.65GiB 2020-12-17 20:44:32.604834: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1435] Adding visible gpu devices: 0 2020-12-17 20:44:32.802206: I tensorflow/core/common_runtime/gpu/gpu_device.cc:923] Device interconnect StreamExecutor with strength 1 edge matrix: 2020-12-17 20:44:32.802236: I tensorflow/core/common_runtime/gpu/gpu_device.cc:929] 0 2020-12-17 20:44:32.802242: I tensorflow/core/common_runtime/gpu/gpu_device.cc:942] 0: N 2020-12-17 20:44:32.802433: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1053] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3396 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1050 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1) Warning: TF_OLD_DATA ignoring data from the past for frame imu at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame velodyne at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame cam00 at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame cam01 at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame cam02 at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame imu at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame velodyne at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame cam00 at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame cam01 at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame cam02 at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame cam03 at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffer_core.cpp Warning: TF_OLD_DATA ignoring data from the past for frame imu at time 1.31738e+09 according to authority unknown_publisher Possible reasons are listed at http://wiki.ros.org/tf/Errors%20explained at line 277 in /tmp/binarydeb/ros-kinetic-tf2-0.5.20/src/buffercore.cpp

`

It seems like (1) When roboot 1~3 subscribe topics something is wrong. (2) The data in the package has aTF_OLD_DATA problem

How can I solve my problem? Looking forward to your reply！

[jngechong]

And I just cut the original bag into 4 new bags and didn't do remove tf or add header time ，I think maybe this is why I meet this problem？