NLL on test/train for SEQGan
Open
enhancement
- Dominant language
- Python
- Stars
- 2.4k
- Forks
- 367
- PR merge metrics
- No merged PRs in 30d
Description
Is it possible to add Likelihood-based Metrics on generated data for SeqGan evaluation? They are described in original paper and paper accompanying implementation you refer to (https://arxiv.org/pdf/1802.01886.pdf)
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reading the linked papers to identify the requested likelihood-based metrics, then locate the SeqGan evaluation entry point in the Python/TensorFlow repository. Determine how generated data is currently evaluated and what outputs the new metrics should produce; done means the metrics are integrated into SeqGan evaluation and verified on generated data.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100