Training & data generation code?

[haofengac]

Thanks for releasing the demo code! I'm wondering if you are planning to release training and the code to generate simulated data?

[bhack]

Any news on this?

[tzt101]

Hi! I try to train the network and find that the error from previous segmentation mask will influence the performance. I'm wondering the details for training if you don't mind.

[haofengac]

FYI, I forked this repo and implemented my own training code at https://github.com/xanderchf/RGMP

[seoungwugoh]

Hi, all.
Sorry for late response.
The training code written by @xanderchf looks great !.
However, It will be very hard to reproduce our results on paper without proper pre-training on simulation data generated from static images.
It is because DAVIS set is too small to train out network by itself and it lead to severe over-fitting even though encoder is initialized by ImageNet training. (Heavy data augmentation is also recommended.)

Unfortunately, we have no plan to release our training code :(

[sycztrf]

Hi! Can you tell me how to use the 'bptt_hsm' function in the train.py file? @xanderchf

[dwqy11]

Hi！ How do you deal with different length of videos in a mini-batch? In your train.py file, you used batch_size=1 when training, and if I revised it to more than 1, the error about length of video is not same shown up. @xanderchf

[seoungwugoh]

Hi！ How do you deal with different length of videos in a mini-batch? In your train.py file, you used batch_size=1 when training, and if I revised it to more than 1, the error about length of video is not same shown up. @xanderchf

In our implementation, we make sure that each training sample has same temporal length by sampling a fixed number frames from video clips.

[dwqy11]

Hi！ How do you deal with different length of videos in a mini-batch? In your train.py file, you used batch_size=1 when training, and if I revised it to more than 1, the error about length of video is not same shown up. @xanderchf

In our implementation, we make sure that each training sample has same temporal length by sampling a fixed number frames from video clips.

Got it ! Thanks!

[XiandaGuo]

FYI, I forked this repo and implemented my own training code at https://github.com/xanderchf/RGMP

Hi!Thanks for releasing your code! I am wondering why do not you use bptt_hsm in train.py? what is the meaning of ntokens in line 134 of train.py? looking forward your replay!Thank you very much

[XiandaGuo]

Hi! Can you tell me how to use the 'bptt_hsm' function in the train.py file? @xanderchf

Hi! I want to know if you have know how to use the 'bptt_hsm' function in the train.py file? thanks

[Starboy-at-earth]

Why do the authors always keep their training code under the desk? Maybe it is the key to the implementation of the proposed network, rather than the fancy structure.

[zgf6781882]

Why do the authors always keep their training code under the desk? Maybe it is the key to the implementation of the proposed network, rather than the fancy structure.

What you said is excellent!

[seoungwugoh]

@Starboy-at-earth @zgf6781882
This work was done during an internship at company. And, I am not able to make available the entire source code other than demo scripts due to potential conflicts with the company's intellectual properties. There is no secret recipe for this method to work. I will be happy to help if you have any difficulty in reproducing our results.

[zgf6781882]

@Starboy-at-earth @zgf6781882
This work was done during an internship at company. And, I am not able to make available the entire source code other than demo scripts due to potential conflicts with the company's intellectual properties. There is no secret recipe for this method to work. I will be happy to help if you have any difficulty in reproducing our results.

Thank you for your help and contribution to this field. It is expected that one day a paper with complete code can be published, which will bring great help to beginners.