20230116 A Transform to ignore artefact points

.github/workflows/cicd.yaml

@@ -36,42 +36,39 @@ jobs:
         pytest -rA -v
         --ignore=actions-runner
 
-
-    # Always run with --ipc=host and --shm-size=2gb (at least) to enable sufficient shared memory when predicting on large data
-    # predict.subtile_overlap specifies overlap between adjacent samples (in meters).
-    - name: Example inference run via Docker with inference-time subtiles overlap to smooth-out results.
+    # IMPORTANT: Always run images with --ipc=host and --shm-size=2gb (at least) to enable 
+    # sufficient shared memory when predicting on large files.
+    - name: Example inference run via Docker with default config and checkpoint
       run: >
         docker run
-        -v /var/data/cicd/CICD_github_assets/myria3d_V3.2.0/inputs/:/inputs/
-        -v /var/data/cicd/CICD_github_assets/myria3d_V3.2.0/outputs/:/outputs/
+        -v /var/data/cicd/CICD_github_assets/myria3d_V3.3.0/inputs/:/inputs/
+        -v /var/data/cicd/CICD_github_assets/myria3d_V3.3.0/outputs/:/outputs/
         --ipc=host
         --shm-size=2gb
         myria3d
         python run.py
-        --config-path /inputs/
-        --config-name proto151_V2.0_epoch_100_Myria3DV3.1.0_predict_config_V3.2.0
-        predict.ckpt_path=/inputs/proto151_V2.0_epoch_100_Myria3DV3.1.0.ckpt
         predict.src_las=/inputs/792000_6272000_subset_buildings.las
         predict.output_dir=/outputs/
-        predict.subtile_overlap=25
-        datamodule.batch_size=10
-        predict.interpolator.probas_to_save=[building,unclassified]
         task.task_name=predict
 
-    - name: Example inference run via Docker with default config and checkpoint
+    # predict.subtile_overlap specifies overlap between adjacent samples (in meters).
+    - name: Example inference run via Docker with inference-time subtiles overlap to smooth-out results.
       run: >
         docker run
-        -v /var/data/cicd/CICD_github_assets/myria3d_V3.2.0/inputs/:/inputs/
-        -v /var/data/cicd/CICD_github_assets/myria3d_V3.2.0/outputs/:/outputs/
+        -v /var/data/cicd/CICD_github_assets/myria3d_V3.3.0/inputs/:/inputs/
+        -v /var/data/cicd/CICD_github_assets/myria3d_V3.3.0/outputs/:/outputs/
         --ipc=host
         --shm-size=2gb
         myria3d
         python run.py
+        --config-path /inputs/
+        --config-name proto151_V2.0_epoch_100_Myria3DV3.1.0_predict_config_V3.3.0
+        predict.ckpt_path=/inputs/proto151_V2.0_epoch_100_Myria3DV3.1.0.ckpt
         predict.src_las=/inputs/792000_6272000_subset_buildings.las
         predict.output_dir=/outputs/
         predict.subtile_overlap=25
         datamodule.batch_size=10
-        predict.interpolator.probas_to_save=[building,unclassified]
+        predict.interpolator.probas_to_save=[building,ground]
         task.task_name=predict
 
     - name: Check code neatness (linter)

configs/config.yaml

@@ -29,7 +29,7 @@ defaults:
   - datamodule: hdf5_datamodule.yaml
   - dataset_description: 20220607_151_dalles_proto.yaml  # describes input features and classes
   - callbacks: default.yaml # set this to null if you don't want to use callbacks
-  - model: pyg_randla_net_model.yaml  # other option is pyg_randla_net_model
+  - model: pyg_randla_net_model.yaml
 
   - logger: comet # set logger here or use command line (e.g. `python run.py logger=wandb`)
   - task: default.yaml

configs/datamodule/transforms/default.yaml

@@ -1,5 +1,5 @@
 defaults:
-  - preparations: default.yaml
+  - preparations: points_budget.yaml
   - augmentations: none.yaml
   - normalizations: default.yaml
 

configs/datamodule/transforms/preparations/default.yaml → configs/datamodule/transforms/preparations/fixed_num_points.yaml

@@ -1,12 +1,16 @@
 # default preparations with grid sampling and random sampling.
 
 train:
+
   TargetTransform:
     _target_: myria3d.pctl.transforms.transforms.TargetTransform
     _args_:
       - ${dataset_description.classification_preprocessing_dict}
       - ${dataset_description.classification_dict}
 
+  DropPointsByClass:
+    _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
+
   GridSampling:
     _target_: torch_geometric.transforms.GridSampling
     _args_:
@@ -23,6 +27,10 @@ train:
     _target_: torch_geometric.transforms.Center
 
 eval:
+
+  CopyFullPos:
+    _target_: myria3d.pctl.transforms.transforms.CopyFullPos
+
   TargetTransform:
     _target_: myria3d.pctl.transforms.transforms.TargetTransform
     _args_:
@@ -32,8 +40,8 @@ eval:
   CopyFullPreparedTargets:
     _target_: myria3d.pctl.transforms.transforms.CopyFullPreparedTargets
 
-  CopyFullPos:
-    _target_: myria3d.pctl.transforms.transforms.CopyFullPos
+  DropPointsByClass:
+    _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
 
   GridSampling:
     _target_: torch_geometric.transforms.GridSampling
@@ -55,9 +63,13 @@ eval:
     _target_: torch_geometric.transforms.Center
 
 predict:
+
   CopyFullPos:
     _target_: myria3d.pctl.transforms.transforms.CopyFullPos
 
+  DropPointsByClass:
+    _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
+
   GridSampling:
     _target_: torch_geometric.transforms.GridSampling
     _args_:

configs/datamodule/transforms/preparations/no_random_subsampling.yaml → configs/datamodule/transforms/preparations/points_budget.yaml

@@ -1,12 +1,16 @@
 # default preparations with grid sampling and random sampling.
 
 train:
+
   TargetTransform:
     _target_: myria3d.pctl.transforms.transforms.TargetTransform
     _args_:
       - ${dataset_description.classification_preprocessing_dict}
       - ${dataset_description.classification_dict}
 
+  DropPointsByClass:
+    _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
+
   GridSampling:
     _target_: torch_geometric.transforms.GridSampling
     _args_:
@@ -26,18 +30,22 @@ train:
     _target_: torch_geometric.transforms.Center
 
 eval:
+
   TargetTransform:
     _target_: myria3d.pctl.transforms.transforms.TargetTransform
     _args_:
       - ${dataset_description.classification_preprocessing_dict}
       - ${dataset_description.classification_dict}
 
-  CopyFullPreparedTargets:
-    _target_: myria3d.pctl.transforms.transforms.CopyFullPreparedTargets
+  DropPointsByClass:
+    _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
 
   CopyFullPos:
     _target_: myria3d.pctl.transforms.transforms.CopyFullPos
 
+  CopyFullPreparedTargets:
+    _target_: myria3d.pctl.transforms.transforms.CopyFullPreparedTargets
+
   GridSampling:
     _target_: torch_geometric.transforms.GridSampling
     _args_:
@@ -53,14 +61,17 @@ eval:
     _args_:
       - 40000
 
-  # For interpolation
   CopySampledPos:
     _target_: myria3d.pctl.transforms.transforms.CopySampledPos
 
   Center:
     _target_: torch_geometric.transforms.Center
 
 predict:
+
+  DropPointsByClass:
+    _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
+
   CopyFullPos:
     _target_: myria3d.pctl.transforms.transforms.CopyFullPos
 

configs/dataset_description/20220607_151_dalles_proto.yaml

@@ -5,12 +5,9 @@ _convert_: all  # For omegaconf struct to be converted to python dictionnaries
 # 160: antenna -> lasting_above
 # 161: wind_turbines -> lasting_above
 # 162: pylon -> lasting_above
-
-# Expectded classification dict:
-# classification_preprocessing_dict: {3: 5, 4: 5, 64:1, 65:1, 160: 64, 161: 64, 162: 64}
-
-# Additionnaly, artefacts as well as synthetic points (65, 66) are set to "unclassified"
-classification_preprocessing_dict: {3: 5, 4: 5, 160: 64, 161: 64, 162: 64, 0: 1, 7: 1, 46: 1, 47: 1, 48: 1, 49: 1, 50: 1, 51: 1, 52: 1, 53: 1, 54: 1, 55: 1, 56: 1, 57: 1, 58: 1, 64: 1, 65: 1, 66: 1, 67: 1, 77: 1, 155: 1, 204: 1}
+# 65: noise --> -1 (to ignore them in inference process, but tey will still be included in the final output cloud).
+# Some trash classes were left in this dataset We do not drop them (i.e. map them to -1) to avoid unintended conflict in production.
+classification_preprocessing_dict: {3: 5, 4: 5, 160: 64, 161: 64, 162: 64, 0: 1, 7: 1, 46: 1, 47: 1, 48: 1, 49: 1, 50: 1, 51: 1, 52: 1, 53: 1, 54: 1, 55: 1, 56: 1, 57: 1, 58: 1, 64: 1, 66: 1, 67: 1, 77: 1, 155: 1, 204: 1}
 
 # classification_dict = {code_int: name_str, ...} and MUST be sorted (increasing order).
 classification_dict: {1: "unclassified", 2: "ground", 5: vegetation, 6: "building", 9: water, 17: bridge, 64: lasting_above}

configs/experiment/RandLaNet-PyG-Overfit.yaml → configs/experiment/RandLaNet-Overfit.yaml

@@ -8,7 +8,7 @@ defaults:
 
 logger:
   comet:
-    experiment_name: "RandLaNetOverfit"
+    experiment_name: "RandLaNet-Overfit"
 
 trainer:
   min_epochs: 100

configs/experiment/RandLaNet_base_run_FR_pyg_randla_net-MultiGPU.yaml → configs/experiment/RandLaNet_base_run_FR-MultiGPU.yaml

@@ -1,6 +1,6 @@
 # @package _global_
 defaults:
-  - RandLaNet_base_run_FR_pyg_randla_net.yaml
+  - RandLaNet_base_run_FR.yaml
 
 logger:
   comet:

configs/experiment/RandLaNet_base_run_FR_pyg_randla_net-SQRT-ICFW.yaml → configs/experiment/RandLaNet_base_run_FR-SQRTOfInverseFreqencyClassWeighting.yaml

@@ -1,11 +1,12 @@
 # @package _global_
 defaults:
-  - RandLaNet_base_run_FR_pyg_randla_net.yaml
+  - RandLaNet_base_run_FR.yaml
   - override /model/criterion: WeightedCrossEntropyLoss.yaml
 
 logger:
   comet:
-    experiment_name: "RandLaNet_base_run_FR_pyg_randla_net-SQRT-ICFW"
+    experiment_name: "RandLaNet_base_run_FR-SQRT-ICFW"
 
 dataset_description:
+  # Sqrt(Inverse Frequency) of classes in defaut dataset (a.k.a. `151proto`).
   class_weights: [0.19,0.08,0.08,0.36,1.13,3.11,2.05]

configs/experiment/RandLaNet_base_run_FR_pyg_randla_net_NoRS.yaml → configs/experiment/RandLaNet_base_run_FR.yaml

@@ -1,11 +1,11 @@
 # @package _global_
 defaults:
-  - RandLaNet_base_run_FR_pyg_randla_net.yaml
-  - override /datamodule/transforms/preparations: no_random_subsampling.yaml
+  - RandLaNet_base_run_FR.yaml
+  - override /datamodule/transforms/augmentations: light.yaml
 
 logger:
   comet:
-    experiment_name: "RandLaNet_base_run_FR_pyg_randla_net_NoRS-(BS10xMAX40000pts)"
+    experiment_name: "RandLaNet_base_run_FR-(BatchSize10xBudget(300pts-40000pts))"
 
 
 # Smaller BS : 10 x 40 000 (max) == 400 000 pts i.e. previous budget of 32 x 12 500pts.
@@ -16,5 +16,5 @@ trainer:
   num_sanity_val_steps: 2
   min_epochs: 100
   max_epochs: 150
-  accumulate_grad_batches: 3  # b/c larger clouds will not fit in memory with original BS.
+  accumulate_grad_batches: 3  # b/c larger clouds will not fit in memory with original Batch Size
   # gpus: [1]

configs/model/criterion/CrossEntropyLoss.yaml

@@ -1,2 +1,3 @@
 _target_: torch.nn.CrossEntropyLoss
-label_smoothing: 0.0
+label_smoothing: 0.0
+ignore_index: 65  # artefacts are mapped to 65 by convention

configs/model/criterion/WeightedCrossEntropyLoss.yaml

@@ -1,5 +1,6 @@
 _target_: torch.nn.CrossEntropyLoss
 label_smoothing: 0.0
+ignore_index: 65  # artefacts are mapped to 65 by convention
 weight:
   _target_: torch.FloatTensor
   _args_: 

docs/source/apidoc/default_config.yml

@@ -25,16 +25,20 @@ datamodule:
           _args_:
           - ${dataset_description.classification_preprocessing_dict}
           - ${dataset_description.classification_dict}
+        DropPointsByClass:
+          _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
         GridSampling:
           _target_: torch_geometric.transforms.GridSampling
           _args_:
           - 0.25
-        FixedPoints:
-          _target_: torch_geometric.transforms.FixedPoints
+        MinimumNumNodes:
+          _target_: myria3d.pctl.transforms.transforms.MinimumNumNodes
           _args_:
-          - 12500
-          replace: false
-          allow_duplicates: true
+          - 300
+        MaximumNumNodes:
+          _target_: myria3d.pctl.transforms.transforms.MaximumNumNodes
+          _args_:
+          - 40000
         Center:
           _target_: torch_geometric.transforms.Center
       eval:
@@ -43,37 +47,45 @@ datamodule:
           _args_:
           - ${dataset_description.classification_preprocessing_dict}
           - ${dataset_description.classification_dict}
-        CopyFullPreparedTargets:
-          _target_: myria3d.pctl.transforms.transforms.CopyFullPreparedTargets
+        DropPointsByClass:
+          _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
         CopyFullPos:
           _target_: myria3d.pctl.transforms.transforms.CopyFullPos
+        CopyFullPreparedTargets:
+          _target_: myria3d.pctl.transforms.transforms.CopyFullPreparedTargets
         GridSampling:
           _target_: torch_geometric.transforms.GridSampling
           _args_:
           - 0.25
-        FixedPoints:
-          _target_: torch_geometric.transforms.FixedPoints
+        MinimumNumNodes:
+          _target_: myria3d.pctl.transforms.transforms.MinimumNumNodes
+          _args_:
+          - 300
+        MaximumNumNodes:
+          _target_: myria3d.pctl.transforms.transforms.MaximumNumNodes
           _args_:
-          - 12500
-          replace: false
-          allow_duplicates: true
+          - 40000
         CopySampledPos:
           _target_: myria3d.pctl.transforms.transforms.CopySampledPos
         Center:
           _target_: torch_geometric.transforms.Center
       predict:
+        DropPointsByClass:
+          _target_: myria3d.pctl.transforms.transforms.DropPointsByClass
         CopyFullPos:
           _target_: myria3d.pctl.transforms.transforms.CopyFullPos
         GridSampling:
           _target_: torch_geometric.transforms.GridSampling
           _args_:
           - 0.25
-        FixedPoints:
-          _target_: torch_geometric.transforms.FixedPoints
+        MinimumNumNodes:
+          _target_: myria3d.pctl.transforms.transforms.MinimumNumNodes
+          _args_:
+          - 300
+        MaximumNumNodes:
+          _target_: myria3d.pctl.transforms.transforms.MaximumNumNodes
           _args_:
-          - 12500
-          replace: false
-          allow_duplicates: true
+          - 40000
         CopySampledPos:
           _target_: myria3d.pctl.transforms.transforms.CopySampledPos
         Center:
@@ -137,7 +149,6 @@ dataset_description:
     57: 1
     58: 1
     64: 1
-    65: 1
     66: 1
     67: 1
     77: 1
@@ -208,6 +219,7 @@ model:
   criterion:
     _target_: torch.nn.CrossEntropyLoss
     label_smoothing: 0.0
+    ignore_index: 65
   _target_: myria3d.models.model.Model
   d_in: ${dataset_description.d_in}
   num_classes: ${dataset_description.num_classes}