tensorflow / tensorflow/models

Tensorflow models ssd_resnet50_v1_fpn_1024x1024_coco17_tpu-8 Model training for object detection

Open
#9,272 15 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Sep 24, 2020.

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

Description

Hi everyone
I create an application that recognizes the names of my cats.
I would like to use the model "ssd_resnet50_v1_fpn_1024x1024_coco17_tpu-8" and train it using my data and tensorflow 2.3.0

Question 1.
How to configure pipeline.config file
What value should I give for "fine_tune_checkpoint"?
After unpacking the model in the checkpoint directory I have 3 files: checkpoint, ckpt-0.index, ckpt-0.data-00000-of-00001
Should I indicate any of these files or their directory?

Question 2.
Num_classes: 90. If my dataset has 4 classes, should num_classes be 94 or 4?

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.