zhanghang1989 / zhanghang1989/PyTorch-Encoding
Modifying the loss and underlying models
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 448
- PR merge metrics
- No merged PRs in 30d
Description
How can I train a new model while modifying the loss function used in the encnet as well as the deeplab / fcn.. model cross-entropy loss ?
Also, how can I remove encnet from the structure and do an ablation study?
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 locating the encnet, deeplab, and fcn model entry points and the cross-entropy loss setup. The issue needs a concrete decision about the new loss behavior and how removing encnet should work for an ablation study. Done would mean the requested training configuration and ablation path are defined and reproducible.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100