performance drop when fintunning DMC model from ACMMM2022
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 25/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- machine-learning
Research direction
Start by reviewing the DMC test and training code, the provided pre-trained model, and the referenced Sheng et al. 2021 strategy. Reproduce fine-tuning with lr=1e-5, multi-frame forward loss averaging, and the regular rate-distortion loss, then determine why the RD curve drops and document or correct the cause.
Written by the indexing model from the issue text.
Description
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!
- Dominant language
- Python
- Stars
- 829
- Forks
- 138
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 1
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from microsoft/DCVC
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 45/100
-
Difficulty 4/5 3-5 days Newbie friendliness 45/100
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
syfoud/Simulated_Scepter#172 ·
-
A cancelled tests run makes the coverage comment workflow fail and reports it as a red check on main Openarea: ci bug perceived difficulty: 3
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Nitjsefnie-Harness-Commons/daedalus#921 · 1 comment ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 86/100
EleutherAI/lm-evaluation-harness#4207 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 92/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
ClickHouse/clickhouse-connect#1057 ·