Skip to content
This repository has been archived by the owner on Feb 22, 2020. It is now read-only.

Made casepleauralspaces not nullable #317

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Made casepleauralspaces not nullable #317

wants to merge 1 commit into from

Conversation

askalik
Copy link

@askalik askalik commented Oct 6, 2019

per open item #200 made casepleauralspace not nullable. Updated template and model

Description

changd the casepleauralspace so that is not nullable

Reference to official issue

Motivation and Context

How Has This Been Tested?

Screenshots (if appropriate):

Metrics (if appropriate):

If you submitting a PR for a prediction algorithm (segmentation, identification,
or classification) please fill in values for as many as the below statistics as
are relevant.

algorithms by metric

metric relevant algorithms
accuracy 1 2 classification, identification
data IO classification, identification, segmentation
Dice coefficient 3 segmentation
disk space usage classification, identification, segmentation
Hausdorff distance 3 segmentation
Jaccard index segmentation
Log Loss classification, identification 4
memory usage classification, identification, segmentation
prediction time 2 classification, identification, segmentation
sensitivity 3 segmentation
specificity 3 segmentation
training time 2 classification, identification, segmentation

notes

  1. Use 5-fold cross validation if there is enough time and computational power available, otherwise use a holdout set
  2. This metric may be automatically calculated by the machine learning architecture, e.g., Keras
  3. The calculations for these metrics are available here
  4. In order to calculate Log Loss for identification, the data needs to be arranged in a way that shows for each pixel, whether or not it is a nodule centriod. Restated, the pixel level labels of 1/0 would correspond to centriod/not-centriod.

metrics by algorithm

algorithm relevant metrics
classification accuracy, data IO, disk space usage, Log Loss, memory usage, prediction time, training time
identification accuracy, data IO, disk space usage, Log Loss, memory usage, prediction time, training time
segmentation data IO, Dice coefficient, disk space usage, Hausdorff distance, Jaccard index, memory usage, prediction time, sensitivity, specificity, training time

When reporting your values, please use a format similar to the following example.

algorithm metric value
segmentation accuracy 99.5
segmentation Jaccard index 0.5
segmentation prediction time (s) 45.3
segmentation memory usage (MB) 5.4

CLA

  • I have signed the CLA; if other committers are in the commit history, they have signed the CLA as well

per open item #200 made casepleauralspace not nullable.  Updated template and model
@askalik
Copy link
Author

askalik commented Oct 6, 2019

I believe this pull request resolves the issue in the bug

@askalik askalik closed this Oct 7, 2019
@askalik askalik reopened this Oct 7, 2019
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant