Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
deepdraw
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
This is an archived project. Repository and other project resources are read-only.
Show more breadcrumbs
medai
software
deepdraw
Commits
13d18254
Commit
13d18254
authored
4 years ago
by
André Anjos
Browse files
Options
Downloads
Patches
Plain Diff
[doc] Adjustments for REFUGE dataset
parent
d0e95d34
No related branches found
No related tags found
1 merge request
!12
Streamlining
Pipeline
#38934
passed
4 years ago
Stage: build
Changes
3
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
bob/ip/binseg/data/refuge/__init__.py
+20
-21
20 additions, 21 deletions
bob/ip/binseg/data/refuge/__init__.py
doc/api.rst
+4
-0
4 additions, 0 deletions
doc/api.rst
doc/datasets.rst
+4
-15
4 additions, 15 deletions
doc/datasets.rst
with
28 additions
and
36 deletions
bob/ip/binseg/data/refuge/__init__.py
+
20
−
21
View file @
13d18254
...
...
@@ -8,29 +8,28 @@ challenge. The goal of the challenge is to evaluate and compare automated
algorithms for glaucoma detection and optic disc/cup segmentation on a common
dataset of retinal fundus images.
* Reference: [REFUGE-2018]_
* Reference
(including train/dev/test split)
: [REFUGE-2018]_
* Protocols ``optic-disc`` and ``cup``:
* Training samples:
* 400
* includes optic-disc and cup labels
* includes label: glaucomatous and non-glaucomatous
* original resolution: 2056 x 2124
* Validation samples: 400:
* 400
* includes optic-disc and cup labels
* original resolution: 1634 x 1634
* Test samples:
* 400
* includes optic-disc and cup labels
* includes label: glaucomatous and non-glaucomatous
* original resolution:
* Split reference: [REFUGE-2018]_
.. warning:
Notice that the data cropping/resizing algorithm applied on training and
"
validation
"
data are slightly different and need to be cross-checked.
* Training samples:
* 400
* includes optic-disc and cup labels
* includes label: glaucomatous and non-glaucomatous
* original resolution: 2056 x 2124
* Validation samples:
* 400
* includes optic-disc and cup labels
* original resolution: 1634 x 1634
* Test samples:
* 400
* includes optic-disc and cup labels
* includes label: glaucomatous and non-glaucomatous
* original resolution:
"""
import
os
...
...
This diff is collapsed.
Click to expand it.
doc/api.rst
+
4
−
0
View file @
13d18254
...
...
@@ -36,6 +36,7 @@ Datasets
bob.ip.binseg.data.chasedb1
bob.ip.binseg.data.hrf
bob.ip.binseg.data.iostar
bob.ip.binseg.data.refuge
Engines
...
...
@@ -171,8 +172,11 @@ Datasets
bob.ip.binseg.configs.datasets.dristhigs1_od_test
bob.ip.binseg.configs.datasets.refuge_cup
bob.ip.binseg.configs.datasets.refuge_cup_dev
bob.ip.binseg.configs.datasets.refuge_cup_test
bob.ip.binseg.configs.datasets.refuge_cup_test
bob.ip.binseg.configs.datasets.refuge_od
bob.ip.binseg.configs.datasets.refuge_od_dev
bob.ip.binseg.configs.datasets.refuge_od_test
bob.ip.binseg.configs.datasets.rimoner3_cup
...
...
This diff is collapsed.
Click to expand it.
doc/datasets.rst
+
4
−
15
View file @
13d18254
...
...
@@ -113,27 +113,16 @@ to generate iterators for training and testing.
- [DRISHTIGS1-2014]_
- 50
- 51
* - REFUGE_
(train)
* - REFUGE_
- [REFUGE-2018]_
- 2056 x 2124
-
400
- 2056 x 2124
(1634 x 1634)
-
1200 (400+400+400)
-
-
- x
- x
- [REFUGE-2018]_
- 400
-
* - REFUGE_ (val)
- [REFUGE-2018]_
- 1634 x 1634
- 400
-
-
- x
- x
- [REFUGE-2018]_
-
- 400 (+400)
- 400
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment