google / google/uncertainty-baselines
Improve deterministic ImageNet baseline
Open
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 224
- Avg merge
- 15h 36m
- Merged PRs (30d)
- 2
Description
> @dustinvtran
> I'm thinking of efficientnet or assemble-resnet. Both have TF implementations:
>
> * https://github.com/clovaai/assembled-cnn
> * https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/tpu (which I believe is still in the process of converting to Keras/TF 2.0)
https://github.com/google/edward2/issues/207
Contributor guide
Research direction
Start by reading the discussion in google/edward2#207 and reviewing the linked assembled-cnn and EfficientNet TensorFlow implementations. Clarify which deterministic ImageNet baseline is expected, then establish the evaluation criteria and reproducible result that would define completion.
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
- 20/100