Megvii-BaseDetection / Megvii-BaseDetection/TreeFilter-Torch
Some questions about the code and equations in paper
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 144
- Forks
- 14
- PR merge metrics
- No merged PRs in 30d
Description
An excellent work! I've several questions.
- Why does the par appear in out_grad, while par_pos in out_data? https://github.com/Megvii-BaseDetection/TreeFilter-Torch/blob/4eed6b61f0f8688618a8563b98a1f21a5c1f9440/furnace/kernels/lib_tree_filter/src/refine/refine.cu#L184
- delta S(Ei,j)/delta wi,j in eq.9 seems to disappear in the code. https://github.com/Megvii-BaseDetection/TreeFilter-Torch/blob/4eed6b61f0f8688618a8563b98a1f21a5c1f9440/furnace/kernels/lib_tree_filter/src/refine/refine.cu#L367
- The paper says "uniformly sample a vertex as the root and perform breadth-first sorting (BFS) algorithm to obtain the topological order of tree G“. But it seems that the code always start from the index 0.
https://github.com/Megvii-BaseDetection/TreeFilter-Torch/blob/4eed6b61f0f8688618a8563b98a1f21a5c1f9440/furnace/kernels/lib_tree_filter/src/bfs/bfs.cu#L79
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
Read the paper alongside the linked sections of furnace/kernels/lib_tree_filter/src/refine/refine.cu at lines 184 and 367, and bfs/bfs.cu at line 79. Trace the relevant variables and tree-ordering logic, then compare the implementation with the paper; done means providing documented answers to all three questions.
Written by the indexing model from the issue text.
Assessment
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100