tensorflow / tensorflow/models

Can't converge Loss function in object detection API

Open
#8,114 1 comment 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since May 22, 2020.

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

Description

I receive these classification loss spikes and no convergence on my own data.
python3 train.py --logtostderr –train_dir=training/ -pipeline_config_path=ssd_mobilenet_pretrain/pipeline.config

Screenshot from 2020-01-31 17-52-04

the output tensorboard --logdir training/


Screenshot from 2020-01-31 17-57-36

Screenshot from 2020-01-31 17-57-46

What is the reason for this problem?

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.