tensorflow / tensorflow/models

training Centermodel - centernet_hg104_512x512_coco17_tpu-8

Open
#9,011 1 comment 1 reaction 3 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hi, I am quite new to tensorflow and I would like to fine-tune centernet_hg104_512x512_coco17_tpu-8 model from modelzoo on my own images.
I was following this tutorial:
https://github.com/tensorflow/models/blob/master/research/object_detection/colab_tutorials/eager_few_shot_od_training_tf2_colab.ipynb.
For SSD training is used attribute box_predictor, but centernet does not have this attribute.

I would like to ask, how to select trainable layers in Centernet. From model_builder.py I was not able to solve this question.

I would be grateful for any help

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.