Skip to content

performance drop when fintunning DMC model from ACMMM2022 #2

Open

Description

@jinxixiang

Congratulations on such remarkable results that surpass VVC!

I ran the test code with the pre-trained model you provided and I reproduced the results you reported in the paper.

Unluckily, when I tried to finetune it for some steps following the training strategy (lr=1e-5, multi-frame forward loss averaging) in (sheng et al2021), the RD curve will drop around 0.7 dB after just hundreds of steps.

The training code is based on DVC and the regular rate-distortion loss is optimized.

Any suggestions will be appreciated.

Thank you!

Activity

  1. kesixcross commented on Sep 16, 2022

    @kesixcross

    I ran into the same problem. Performance drops just a few steps after fine-tuning.
    I wonder if the authors can release their train code.
    Any suggestions will be appreciated.
    Thank you!

  2. mosquitobite commented on Nov 14, 2022

    @mosquitobite

    Hi, do you solve the problem?

  3. kesixcross commented on Nov 16, 2022

    @kesixcross

    Hi, do you solve the problem?

    sorry, I have not solved the problem.

  4. tl32rodan commented on May 11, 2023

    @tl32rodan

    Same here.
    It's just fine to fine-tune DCVC-TCM, but fail on DCVC-HEM and DCVC-DC cases.
    I guess training "adaptive quantization" could be non-trivial, but there's no quite much training details mentioned in the papers.
    It'll be a lot helpful if the author by any chance can share more training details, thanks.

  5. guohf3 commented on May 17, 2023

    @guohf3

    Me too. It would be appreciated if anyone solved this problem and shared it.

  6. MingZwhy commented on Jun 2, 2023

    @MingZwhy

    Congratulations on such remarkable results that surpass VVC!

    I ran the test code with the pre-trained model you provided and I reproduced the results you reported in the paper.

    Unluckily, when I tried to finetune it for some steps following the training strategy (lr=1e-5, multi-frame forward loss averaging) in (sheng et al2021), the RD curve will drop around 0.7 dB after just hundreds of steps.

    The training code is based on DVC and the regular rate-distortion loss is optimized.

    Any suggestions will be appreciated.

    Thank you!

    Hi!
    I also want to fine-tune DCVC for my research, but I don't know how to train it.
    Could you share your training code with me?
    I will appreciate it if you can help me on fine-tune DCVC model !

  7. tl32rodan commented on Nov 23, 2023

    @tl32rodan
  8. YY-RR-ZZ commented on Apr 18, 2024

    @YY-RR-ZZ

    Same here. It's just fine to fine-tune DCVC-TCM, but fail on DCVC-HEM and DCVC-DC cases. I guess training "adaptive quantization" could be non-trivial, but there's no quite much training details mentioned in the papers. It'll be a lot helpful if the author by any chance can share more training details, thanks.

    Hello, I'm very interested in DCVC-TCM, but I don't have the ability to fully reproduce the training phase of the code. I'm wondering if you would be willing to share the training phase code with me. My email is 1059561754@qq.com. I would greatly appreciate it!

  9. shencuifeng commented on Jul 30, 2024

    @shencuifeng

    **YY-RR-ZZ ** commented Apr 18, 2024

    Have you got the training code?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions