Wenjing Ke

Do you have plan to add some light-weight model in this repo?

4

Hello, thank you for sharing your great work on action recognition. Do you have plan to add some light-weight model, for example, C3D with shallow backbone, or recently released [X3D](https://arxiv.org/abs/2004.04730)...

strange result with mono_sc depth model

1

Hi, I got the normal result with the kitti_odom/stereo model, but when I did the evaluation with command `python run.py -c options/kitti/kitti_mono_sc_0.yml` Here's the result I got: ``` Evaluate result...

What the corresponding relation between config files and checkpoints?

1

Hi, I noticed there're several config files and checkpoints for each dataset. Take KITTI as an example, what's the corresponding relation between config files `kitti15_ft_ar.json kitti15_ft.json kitti_raw.json` and checkpoints `pwclite_ar_mv.tar...

How to get the reconstructed results on Kitti?

1

Hi, may I ask how to get the visulized reconstructed results on Kitti as you showed in the [demo video ](https://www.youtube.com/watch?v=OkfK3wmMnpo) ?

cannot reproduce VO accuracy when I try to train the pose model on KITTI Odometry

2

Hi, I've tried to train the pose model on KITTI Odometry by running `sh scripts/train_resnet50_pose_256.sh` , here's the accuracy I get: ``` Sequence: 9 Translational error (%): 11.425453298024262 Rotational error...

Have you fine-tune the Reid model on MOT dataset?

27

Hi @longcw , I've replaced the Reid part of extracting features by my own trained model, the evaluation result gets worse. Have your fine-tune the Reid model on the MOT...

HI, i'm trying to use your code to reproduce the experiments in your paper. I use the given command line and pretrained float model, while it reports the error of...