tensorflow / tensorflow/probability
Estimate prediction uncertainty in ResNet model using MC dropout
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
is there a tutorial on how to apply TFP with popular vision models such as ResNet using MC dropout, and extract aleatoric & epistemic uncertainties.
Perhaps something similar to this blog post Building a Bayesian deep learning classifier, or this notebook, based on Yarin Gal' work or similar
Contributor guide
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 reviewing the linked Building a Bayesian deep learning classifier post, the referenced Colab notebook, and the issue's references to TFP, ResNet, MC dropout, and Yarin Gal's work. Clarify whether the expected result is a tutorial or notebook and which uncertainty outputs it must demonstrate; done means a complete, reproducible walkthrough for both aleatoric and epistemic uncertainty.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook, tensorflow
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100