Megvii-BaseDetection / Megvii-BaseDetection/BEVDepth
Kronecker product in the Eq.1
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 881
- Forks
- 124
- PR merge metrics
- No merged PRs in 30d
Description
Hi, thanks for the work. In Eq.1 in the main paper, there is a Kronecker product between F2d_i and Dpred_i. The shape of F2d_i is (C_F, H, W) and the shape of Dpred_i is (C_D, H, W). However, based on the definition of the Kronecker product (e.g., https://pytorch.org/docs/stable/generated/torch.kron.html), the shape of output F3d_i might be (C_F * C_D, H * H, W * W) instead of (C_F, C_D, H, W). Am I missing something? Note that I understand the motivation and the logic of Eq.1 but I'm just confused about whether it is called Kronecker product. Thanks so much.
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 reading Eq.1 in the main paper and compare its notation with the linked PyTorch torch.kron definition. Confirm whether the operation and resulting shape are described correctly; done means resolving the terminology or identifying the needed paper clarification.
Written by the indexing model from the issue text.
Assessment
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 32/100