tensorflow / tensorflow/probability

Simple network with fipout layers does not work with mixed precision

Open
#1,315 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
4.4k
Forks
1.1k
PR merge metrics
No merged PRs in 30d

Description

Dear tfp devs

Firstly, thank you for this magnificent package!

I have tried using mixed precision the same way as with base tf(it works on tf). Unfortunately an error occurs:
Tensor conversion requested dtype float32 for Tensor with dtype float16: <tf.Tensor 'Cast:0' shape=(None, 300, 300, 1) dtype=float16>

Model consist of conv and dense flipout layers.

tfp: 0.12.1
tensorflow running on an official docker container

Regards, Jakub

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the reported mixed-precision setup with convolutional and dense Flipout layers using tfp 0.12.1 and the official TensorFlow Docker container. Trace the float16-to-float32 conversion that produces the reported error; the issue is done when this model runs under mixed precision without that dtype error.

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
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.