tensorflow / tensorflow/models

Question on the mobileNetV2 convergence time.

Open
#9,719 0 comments 0 reactions 2 assignees View on GitHub

@marksandler2 is already working on this.

Since Feb 9, 2021.

models:research type:support
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

I found this information in https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/README.md The numbers above can be reproduced using slim's train_image_classifier. Below is the set of parameters that achieves 72.0% for full size MobileNetV2, after about 700K when trained on 8 GPU. If trained on a single GPU the full convergence is after 5.5M steps. Also note that learning rate and num_epochs_per_decay both need to be adjusted depending on how many GPUs are being used due to slim's internal averaging.
I wonder what is run time to achieve this convergence?

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.