Skip to content
This repository has been archived by the owner on Nov 16, 2019. It is now read-only.

DataLayer use data_param instead of memory_data_param #294

Open
ooyanglinoo opened this issue Dec 29, 2017 · 2 comments
Open

DataLayer use data_param instead of memory_data_param #294

ooyanglinoo opened this issue Dec 29, 2017 · 2 comments

Comments

@ooyanglinoo
Copy link

ooyanglinoo commented Dec 29, 2017

Can I use data_param instead of memory_data_param to define DataSource in DataLayer? If not, how to apply different size images as training dataset?

@ooyanglinoo ooyanglinoo changed the title DataLayer use data_param instead memory_data_param DataLayer use data_param instead of memory_data_param Dec 29, 2017
@junshi15
Copy link
Collaborator

You can only use memory_data_param or cos_data_param to specify the input layers.

The data layers have simple resize function, but I don't think it handles encoded images (say JPEG) with variable sizes.

I would pre-processe the images (resize, rotate, etc) before feeding them to Caffe.

@ooyanglinoo
Copy link
Author

I want to train a object detection model based on CaffeOnSpark, whose training image size varies, and may not resize easily because tags on images is based on origin image size.

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

No branches or pull requests

2 participants