关于该repo的一些疑问 about neural-rewriter HOT 11 OPEN

Hello @ldy8665, sorry for using English. I am using the computer in the library so I can only type English. I want to know did you reproduce any result of vrp or jsp? The training for vrp is also very slow in my workstation. Now I am trying to train for the jsp task but it does not converge in one epoch with 64 batch size and 5e-4. How many iters should the rewriter run to improve the result a lot?

from neural-rewriter.

@ldy8665 By the way, I modified the code to create the directory when it does not exist. Now you do not need to create folders by hand before running the code :)

from neural-rewriter.

Hi Bo,
I only check the vrp task of your repo.Because im doing reaserach on the vrp problem with RL/DRL. As the code is too slow when i run it to train vrp task, so i stop it early in several epoches. Now im trying to rewrite the code base your main idea but improve the framework of the code.
You can try 'DataLoader','torch.gather' in pytorch or something like these function. I think it can help instead of 'for' in 'for'.

from neural-rewriter.

Hi, I am not the author of this paper. In fact, I am an open-source contributor who modified some part of the code to make it better. Same as you, I also try to dive into this code and see some results but have some trouble. Maybe we can talk about this by email ([email protected]).
By the way, I also noticed some operations in code is not very efficient. If you improve the framework, it is also great to pull the request to contribute to this repo.

from neural-rewriter.

Ok Bo.when i finish my code and have some results,I`ll share with you.

from neural-rewriter.

Hi all, thanks for the interest and sorry for all the inconvenience.

For vehicle routing, we use a different version of the sampling code in PyTorch, which might cause some slowness. Xinyun mentioned that the training code takes ~10h to achieve a good performance with 8 GeForce GTX 1080 GPUs, after training for slightly more than an epoch (note that you don't need to train a lot of epochs to get good performance).

from neural-rewriter.

Any progress there? Hope we can add some visualization codes and make the training more efficient

from neural-rewriter.

Hi all, I succeeded to reproduce the result. According to my experience, I think everything goes well. The only problem is the outputs and logs for loss and reward in training are not instructive for some reason. So even you cannot see the convergence and good performance during training, it is fine to stop training after slightly more than one epoch and just run the evaluation.

About visualization, I believe it is easy to use tensorboad to get some visualization. I have plan to do it in my branch when I have time.

from neural-rewriter.

I think there are some mismatches between the code and paper in loss function.

from neural-rewriter.

I think there are some mismatches between the code and paper in loss function.

Yes, I agree. For example, the loss of value approximation in the paper is l2 but in code, it is smooth l1.

from neural-rewriter.

May I ask, how does this code run on multiple GPUs？

from neural-rewriter.