Skip to content

training on my own pictures #30

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Iric2018 opened this issue Oct 10, 2018 · 4 comments
Open

training on my own pictures #30

Iric2018 opened this issue Oct 10, 2018 · 4 comments

Comments

@Iric2018
Copy link

If I want to train the model with my own images,how can I get the json file of annotations,such as instances_minival2014.json,instances_testval2014.json and instances_trainval2014.json?

@heilaw
Copy link
Collaborator

heilaw commented Oct 11, 2018

There's an alternative to preparing JSON files.

You can change the _load_data function in db/coco.py to read your own dataset. self._image_ids is a list of image names, while self._detections is a dictionary where the keys are the image names and the values are the bounding boxes and category ids.

@maggiequan
Copy link

how to change the _load_data function in db/coco.py? just need to save your image file names to the _image_ids variable and just set _detections to be an empty list. i can not understand.

@mrlaiii
Copy link

mrlaiii commented Apr 7, 2019

e

do you know how to change the function _load_data?i am in the same case as you.thank you!

@kszqq
Copy link

kszqq commented Aug 20, 2019

How to display the test result of single picture?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants