Skip to content
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

If I don't have a camera, can I still run this? #5

Open
johnny5550822 opened this issue Oct 31, 2016 · 5 comments
Open

If I don't have a camera, can I still run this? #5

johnny5550822 opened this issue Oct 31, 2016 · 5 comments

Comments

@johnny5550822
Copy link

@Aysegul Instead of a camera, can I just input an image and see the deconvolution of it? Do you have the related code?

Thanks!
Johnny

@Aysegul
Copy link
Owner

Aysegul commented Oct 31, 2016

You can change the line 18 in display.lua
state.rawFrame = image.load('your_image')
and delete parts that use camera:
require 'camera'
local source = image.Camera{}

@johnny5550822
Copy link
Author

@Aysegul great, I will try that out.

@johnny5550822
Copy link
Author

@Aysegul one more question. If I want to change the network (let say using vgg, not overfeat), what should I do?

@johnny5550822
Copy link
Author

@Aysegul I have some questions about the guided back-propagation of ReLU that you implemented in the display.lua, would you have some time to help me with that? Thanks! Really appreciate with it

@KangolHsu
Copy link

@Aysegul I do as you said,but an erro occurred like this ‘qlua: run.lua:79: attempt to call field 'begin' (a nil value)’

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

3 participants