Skip to content

Tags: IGNF/myria3d

Tags

V3.8.2

Toggle V3.8.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Merge pull request #114 from IGNF/fix-subsample

Fix edgecase with 1 input value that is not selected in subsample_data

poc_foret_bdv3/single-tree-modeling-block-aggregation-nocolor-GenericDA-TreeStatsOnly

Toggle poc_foret_bdv3/single-tree-modeling-block-aggregation-nocolor-GenericDA-TreeStatsOnly's commit message
Remove features to consider onl tree statistics

poc_foret_bdv3/single-tree-modeling-block-aggregation-nocolor-GenericDA

Toggle poc_foret_bdv3/single-tree-modeling-block-aggregation-nocolor-GenericDA's commit message
Barplot of errors in polygon

poc_foret_bdv3/forest-classification-explo

Toggle poc_foret_bdv3/forest-classification-explo's commit message
Remove nan and duplicate header in load_predictions for cm polygon

poc_foret_bdv3/forest-classification-explo-DYNAMIC-CLASS-REBALANCING

Toggle poc_foret_bdv3/forest-classification-explo-DYNAMIC-CLASS-REBALANCING's commit message
Use inverse frequency to fully reequilibrate

V3.4.12

Toggle V3.4.12's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
Merge pull request #87 from IGNF/65-remove-copc

chore: Remove COPC datasets and dataloaders since they were abandonned

prod-release-tag

Toggle prod-release-tag's commit message
Functionnal pacasam config: 20230601_lidarhd_pacasam_dataset

pro-release-tag

Toggle pro-release-tag's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
20230116 A Transform to ignore artefact points (#52)

* Points Budget is the new defaut config

* Implement DropPointsByClass as well as its tests - make it the defaut behavior

Tests pass for DropPointsByClass

Copy full position BEFORE droping by class to avoid error at knn_interpolate

More test for DropPointsByClass creation

Flake8

* Givre access to input classification during inference for DropPointsByClass

* Do not map code for artefact to unclassified class in order to ignore it

* C=65 is default code to be ignored. Its class will remain an artefact

* Update default config

* Update default config call in cicd

* Update unit test for DropPointsByClass

* Change typing of reduce_predicted_logits

* Update documentation for making inference

V3.3.0

Toggle V3.3.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
20230116 A Transform to ignore artefact points (#52)

* Points Budget is the new defaut config

* Implement DropPointsByClass as well as its tests - make it the defaut behavior

Tests pass for DropPointsByClass

Copy full position BEFORE droping by class to avoid error at knn_interpolate

More test for DropPointsByClass creation

Flake8

* Givre access to input classification during inference for DropPointsByClass

* Do not map code for artefact to unclassified class in order to ignore it

* C=65 is default code to be ignored. Its class will remain an artefact

* Update default config

* Update default config call in cicd

* Update unit test for DropPointsByClass

* Change typing of reduce_predicted_logits

* Update documentation for making inference

V3.2.5

Toggle V3.2.5's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
Optimize memory usage during interpolation saving (#50)

* Delete variables with high memory usage

* Delay las loading when saving results

Co-authored-by: GLiegard <[email protected]>