Megvii-BaseDetection / Megvii-BaseDetection/BEVDepth
Performance of MatrixVT
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 881
- Forks
- 124
- PR merge metrics
- No merged PRs in 30d
Description
Thanks for your great work about MatrixVT! I train the model with config matrixVT 24 epochs in 2 RTX 4090ti，and it seems that the performance(mAP 31.51 and NDS 38.55) is lower than your paper's results(mAP 33.7 and NDS 41.4 ) .
Is that reasonable result? Could you give me some suggestions?
Contributor guide
No contributing guide indexed for this repository
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.
Research direction
Start by comparing the MatrixVT 24-epoch configuration on two RTX 4090 Ti GPUs with the paper's reported setup and evaluation conditions. Check whether the mAP 31.51 and NDS 38.55 results are reproducible and identify the configuration or evaluation difference needed to explain the gap; the issue names no files or tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100