Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
P
PySegCNN
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor 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
Show more breadcrumbs
earth_observation_public
PySegCNN
Graph
36dc0df7c4771d26cc9c4f5096fe76bd456438a6
Select Git revision
Branches
1
master
default
protected
1 result
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
24
Feb
20
19
18
17
16
12
10
9
5
4
3
2
1
29
Jan
28
27
26
25
22
20
19
15
14
13
12
11
8
7
23
Dec
21
17
16
15
14
11
9
4
27
Nov
26
25
9
Oct
5
2
1
28
Sep
25
23
21
18
17
16
15
14
11
10
9
8
4
3
2
1
31
Aug
28
27
26
25
24
21
20
19
18
17
14
13
12
11
10
30
Jul
29
28
27
24
23
22
21
20
17
16
15
14
10
9
8
7
6
3
2
Check for projection in header files when converting hdf to tif.
Fixed selection of metrics in report dataframe.
Fixed typo that messed up aggregated confusion matrix.
Specify labels also for confusion matrix.
Drop micro average when specifying labels.
Handle case when a class is not present in either ground truth or prediction.
Added option to save or not save model evaluations.
Close figures after plotting.
Do not show legend in scene plots.
Consistent use of inference variable names.
Adjust counters starting from 0.
First check if an entire scene is already processed before appending.
Squeeze is required for multi-dimensional arrays.
Squeeze is required for multi-dimensional arrays.
Hiding axis ticks when plotting scenes.
Flatten arrays required.
Changed model evaluation strategy: process batch-wise rather than scene-wise.
Added ipython as dependency.
Added xarray and netcdf4 dependencies.
Removed torch as dependency.
Save scenes as pdf.
Adapted image size for Alcd to 20m resolution.
Changed default colormap.
Changed default colormap.
Changed default colormap.
Changed default image format to pdf.
Fixed a bug: continue iteration when model evaluation exists.
Fixed a bug: Add classification report after computing confusion matrix.
Avoid namespace confusion.
Avoid namespace confusion.
Avoid namespace confusion.
Read the labels from the classification reports.
Fixed a bug: concatenate the actual dataframes...
Initialize DataFrame with numeric type.
Changed default behaviour of dataset path.
Keep hdf metadata when converting to GeoTiff.
Changed default format from png to pdf.
Implemented efficient conversion of classification report to pandas DataFrame.
Improved visualizations of confusion matrix and classification report.
Added errors of commission and omission.
Loading