Tensorflow Object Detection With Custom Model

Question

I follow this tut on this page: https://github.com/tensorflow/models/blob/master/object_detection/object_detection_tutorial.ipynb

this tut use pre trained model graph 'frozen_inference_graph.pb'. Now I want to build my custom model, for my dataset

Is there a straightforward example to do this? I dont want to use Google Cloud Services at all for training, all action must be done on my local machine

Jonathan Huang · Accepted Answer · 2017-07-31 04:26:50Z

1

Sure! You can definitely train locally using the command lines here: https://github.com/tensorflow/models/blob/master/object_detection/g3doc/running_locally.md

I would recommend that you use a GPU if you train locally. Someone also wrote up a nice guide about how to train on a custom dataset here: https://medium.com/towards-data-science/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9 In this case he used Cloud, but many of the tips will still be relevant even if training locally.

answered Jul 31, 2017 at 4:26

Jonathan Huang

1,55810 silver badges12 bronze badges

Sign up to request clarification or add additional context in comments.

Comments

Jorgeeadan · Accepted Answer · 2017-12-14 15:14:40Z

0

I've followed this guide, is awesome and practically easy, he shows how to train a Mac and cheese detector, hope it helps!

answered Dec 14, 2017 at 15:14

Jorgeeadan

3418 silver badges21 bronze badges

Collectives™ on Stack Overflow

Tensorflow Object Detection With Custom Model

2 Answers 2

Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related