Skip to content
This repository has been archived by the owner on Oct 18, 2019. It is now read-only.

About the input size of the Image #20

Closed
chibai opened this issue Oct 18, 2016 · 2 comments
Closed

About the input size of the Image #20

chibai opened this issue Oct 18, 2016 · 2 comments

Comments

@chibai
Copy link

chibai commented Oct 18, 2016

This is a very stupid question.

I saw you resize the image to 256*256 in python script

but in line 6 of deploy.prototxt, input_param { shape: { dim: 1 dim: 3 dim: 224 dim: 224 } },
which means the input images should be 3 channels with size 224*224

so, what's the exactly right input size of the image?? 256 or 224??
Or I just misunderstood the python script and caffe structure??

@XuefeiW
Copy link

XuefeiW commented Oct 20, 2016

The script does this:
load an image;
resize image to 256x256 (line 64)
centre crop resized image to 224x224 (line 71)

So the input image of the model is 3x224x224

@jay-mahadeokar
Copy link
Contributor

The resize to 256x256 and random crop to 224x224 is done during training for data augmentation. Refer the residual networks paper section 3.4. During runtime / test we take center crop after resize.

@chibai chibai closed this as completed Oct 28, 2016
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

3 participants