tensorflow / tensorflow/probability
Bayesian Neural network cifar10 example not converging
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
I tried cifar10_bnn example with bayesian_vgg as an example architecture with default hyper-parameters. However, the loss seems to increase and model results are not consistent. I ran the bayesian_neural_network example of MNIST, which works well. Also, I ran a small network and that seems to work as well. I think something wrong in the models implementation of bayesian_vgg or am I missing something.
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 with the cifar10_bnn example and its bayesian_vgg architecture, then compare them with the working bayesian_neural_network MNIST example and the reported small network. Investigate why the default hyper-parameters produce increasing loss and inconsistent results; the issue is done when the CIFAR10 example trains consistently.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100