Skip to content
This repository has been archived by the owner on Mar 17, 2021. It is now read-only.

explanation of theload_image function and the dataflow #36

Closed
wyli opened this issue Jan 27, 2018 · 3 comments
Closed

explanation of theload_image function and the dataflow #36

wyli opened this issue Jan 27, 2018 · 3 comments
Assignees

Comments

@wyli
Copy link
Member

wyli commented Jan 27, 2018

#31 and #34 asked for clarifications of load_image(filename):

how the image data is transferred to the network?
I can't find where the load_image(filename) function is called in the application_driver.py.

I know the niftynet defines the load_image(filename) function in niftynet/io/misc_io.py. However, I don't find how the load_image is called in promise 2012 demo.
there is no load_image function in both application_driver.py and segmentation_application.py.

@JunMa11
Copy link

JunMa11 commented Feb 13, 2018

A brief overview of NiftyNet components in the published paper.
A brief overview of NiftyNet components

@kwang-greenhand
Copy link

Yes in the application you call the sampler and load the image using Sampler's "pop_batch_op", instead of feeding data in "sess.run(variables, feed_data_dict = data_dict)".

Although I haven't found how the image augmentation is implemented...

@ericspod
Copy link
Collaborator

The load_image function is use in image_type.py ultimately in the implementation of ImageFactory. This is used eventually by ImageReader in image_reader.py which does the actual work of loading images and creating the image dictionary passed onto the network. In the application definitions ImageReader is instantiated for each set of input and stored in self.readers.

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

No branches or pull requests

5 participants