tensorflow / tensorflow/models

How to get val loss and save best checkpoint in the ssd_mobilenet_v1 tutorial

Open
#10,801 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Prerequisites

Please answer the following question for yourself before submitting an issue.

  • [ x ] I checked to make sure that this issue has not been filed already.

1. The entire URL of the documentation with the issue

https://colab.research.google.com/github/google-coral/tutorials/blob/master/retrain_detection_qat_tf1.ipynb#scrollTo=ImucOu0qgMv_

2. Describe the issue

Hi, Im doing transfer learning with the ssd mobilenet v1 and I would like to know how can I get the val loss during the training and how to save only the best checkpoint according to the best val loss. I only get the loss and by default the checkpoints saved are the first one and the last one.

Thank you.

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 with the training and checkpoint sections of retrain_detection_qat_tf1.ipynb at the linked Colab URL, and run the tutorial to confirm what loss values and checkpoint files it currently produces. Done means the tutorial explains how validation loss is obtained and how the best checkpoint is selected and saved.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.