multi pipeplines config support

analysis/full_visual_cmp.py

@@ -397,7 +397,7 @@ if __name__ == "__main__":
     f2 = "/Users/mariuslaska/PycharmProjects/boxprediction/evaluation/uji/cnn/output/CNNLoc_1"
 
     f2 = "/home/laskama/PycharmProjects/bboxPrediction/evaluation/uji/cnn/hpc/CNNLoc_1"
-    f1 = "/home/laskama/PycharmProjects/bboxPrediction/evaluation/uji/cnn/hpc/CNNLoc-DLB_1"
+    f1 = "/home/laskama/PycharmProjects/bboxPrediction/evaluation/uji/cnn/hpc/DNN-DLB_1"
     main(p_box_f=f1,
          p_reg_f=f2,
          vis_idx=(0,77))
\ No newline at end of file

base/ujiindoorloc_provider.py

@@ -24,12 +24,12 @@ class UJIndoorLocProvider(DataProviderBase):
         """
 
         train = pd.read_csv("UJIndoorLoc/trainingData.csv")
-        #train = train[train.BUILDINGID.eq(building_id)]
-        #train = train[train.FLOOR.eq(floor_id)]
+        train = train[train.BUILDINGID.eq(building_id)]
+        train = train[train.FLOOR.eq(floor_id)]
 
         test = pd.read_csv("UJIndoorLoc/validationData.csv")
-        #test = test[test.BUILDINGID.eq(building_id)]
-        #test = test[test.FLOOR.eq(floor_id)]
+        test = test[test.BUILDINGID.eq(building_id)]
+        test = test[test.FLOOR.eq(floor_id)]
 
         self.num_train = train.shape[0]
         self.num_test = test.shape[0]

config/cnn_config.yml → config/gpu_b0_f0.yml

@@ -15,7 +15,7 @@ data:
 global_params:
 
   # number of experiment repetitions
-  repetitions: 1
+  repetitions: 10
 
   preprocessing:
     # Whether to standardize the RSS values
@@ -41,49 +41,72 @@ global_params:
     #first_neuron: 512
     #hidden_layers: 1
     lr: 0.002
-    batch_size: 66
-    epochs: 5
+    batch_size: 32
+    epochs: 1
     #dropout: 0.7
     #regularization_penalty: 0.0
     augmentation: 0
     autoencoder: train
     #pretrain: yes
 
-    loss:
-      grid:
-        scale: 30.0
-      outside:
-        scale: 1.0
-        delta: 10.0
-
 pipelines:
 
   - name: CNNLoc
-    ns: 1
-    ts: 1
     model_params:
+      lr: 0.002
       type: CNNLoc_REG
       autoencoder: train
-      epochs: 5
-      batch_size: 64
 
   - name: CNNLoc-DLB
-    ns: 1
-    ts: 1
     model_params:
       lr: 0.002
-      batch_size: 64
-      epochs: 5
-      #dropout: 0.7
-      #regularization_penalty: 0.0
+      batch_size: 32
       augmentation: 0
       autoencoder: train
-      #pretrain: yes
+
+      loss:
+        grid:
+          scale: 100.0
+        outside:
+          scale: 1.0
+          delta: [10.0, 15.0, 20.0]
+
+  - name: DNN
+    model_params:
+      type: DNN # (DNN, CNN, kNN, SVM) supported (require different parameters)
+      pred: regression
+      first_neuron: 512
+      hidden_layers: [1,2,3]
+      lr: 0.7
+      batch_size: 32
+      #epochs: 200
+      dropout: 0.5
+      regularization_penalty: 0.0
+      augmentation: 0
+
+  - name: DNN-DLB
+    model_params:
+      type: GRID_OVERLAP-BBOX # (DNN, CNN, kNN, SVM) supported (require different parameters)
+      first_neuron: 512
+      hidden_layers: [1,2]
+      lr: 0.7
+      batch_size: 32
+      #epochs: 200
+      dropout: 0.5
+      regularization_penalty: 0.0
+      augmentation: 0
+
+      loss:
+        grid:
+          scale: 100.0
+        outside:
+          scale: 1.0
+          delta: [10.0, 15.0, 20.0]
 
 
 
 # base directories for file storage
 output:
-    model_dir: evaluation/uji/cnn/full_cmp/output/
-    summary_dir: evaluation/uji/cnn/full_cmp/summary/
+    model_dir: evaluation/uji/gpu/b0/f0/output/
+    summary_dir: evaluation/uji/gpu/b0/f0/summary/
     img_folder: evaluation/uji/ # folder where floorplan images is located (if not present, will be downloaded)

config/gpu_b0_f1.yml

+data:
+  # The data provider which should be used
+  provider: UJIndoorLocProvider
+  # File name of floor plan img
+  floor_plan_img: <test>.jpg
+  # (train, val, test) test=0.2 => 5 fold  # The number of temporal epochs into which the dataset is split
+  split_ratio: [0.7, 0.1, 0.2]
+  building: 0
+  floor: 1
+
+#
+# are used when not locally set for pipeline
+#
+
+global_params:
+
+  # number of experiment repetitions
+  repetitions: 10
+
+  preprocessing:
+    # Whether to standardize the RSS values
+    standardize: True
+    # Whether to assign labels with no matching area to closet area
+    assign_closest: False
+    # The floor number of the Lohan dataset, which should be used
+    #floor: 0
+    # The epoch number of the split dataset
+    #num_epochs: 10
+    #epoch: 5
+    # How to check for area matches of labels (to label positions with matching areas)
+    area_assignment: convex_hull
+    grid_size: 40
+
+  floor_plan:
+      # 'segmentation' => computes floor plan segmentation,
+      #  'regression' => uses DBSCAN to partitions labels into train, test split
+      type: floor_classification
+
+  model_params:
+    type: GRID_OVERLAP-BBOX_CNN # (DNN, CNN, kNN, SVM) supported (require different parameters)
+    #first_neuron: 512
+    #hidden_layers: 1
+    lr: 0.002
+    batch_size: 32
+    epochs: 1
+    #dropout: 0.7
+    #regularization_penalty: 0.0
+    augmentation: 0
+    autoencoder: train
+    #pretrain: yes
+
+pipelines:
+
+  - name: CNNLoc
+    model_params:
+      lr: 0.002
+      type: CNNLoc_REG
+      autoencoder: train
+
+  - name: CNNLoc-DLB
+    model_params:
+      lr: 0.002
+      batch_size: 32
+      augmentation: 0
+      autoencoder: train
+
+      loss:
+        grid:
+          scale: 100.0
+        outside:
+          scale: 1.0
+          delta: [10.0, 15.0, 20.0]
+
+  - name: DNN
+    model_params:
+      type: DNN # (DNN, CNN, kNN, SVM) supported (require different parameters)
+      pred: regression
+      first_neuron: 512
+      hidden_layers: [1,2,3]
+      lr: 0.7
+      batch_size: 32
+      #epochs: 200
+      dropout: 0.5
+      regularization_penalty: 0.0
+      augmentation: 0
+
+  - name: DNN-DLB
+    model_params:
+      type: GRID_OVERLAP-BBOX # (DNN, CNN, kNN, SVM) supported (require different parameters)
+      first_neuron: 512
+      hidden_layers: [1,2]
+      lr: 0.7
+      batch_size: 32
+      #epochs: 200
+      dropout: 0.5
+      regularization_penalty: 0.0
+      augmentation: 0
+
+      loss:
+        grid:
+          scale: 100.0
+        outside:
+          scale: 1.0
+          delta: [10.0, 15.0, 20.0]
+
+
+
+# base directories for file storage
+output:
+    model_dir: evaluation/uji/gpu/b0/f1/output/
+    summary_dir: evaluation/uji/gpu/b0/f1/summary/
+    img_folder: evaluation/uji/ # folder where floorplan images is located (if not present, will be downloaded)

config/gpu_b0_f2.yml

+data:
+  # The data provider which should be used
+  provider: UJIndoorLocProvider
+  # File name of floor plan img
+  floor_plan_img: <test>.jpg
+  # (train, val, test) test=0.2 => 5 fold  # The number of temporal epochs into which the dataset is split
+  split_ratio: [0.7, 0.1, 0.2]
+  building: 0
+  floor: 2
+
+#
+# are used when not locally set for pipeline
+#
+
+global_params:
+
+  # number of experiment repetitions
+  repetitions: 10
+
+  preprocessing:
+    # Whether to standardize the RSS values
+    standardize: True
+    # Whether to assign labels with no matching area to closet area
+    assign_closest: False
+    # The floor number of the Lohan dataset, which should be used
+    #floor: 0
+    # The epoch number of the split dataset
+    #num_epochs: 10
+    #epoch: 5
+    # How to check for area matches of labels (to label positions with matching areas)
+    area_assignment: convex_hull
+    grid_size: 40
+
+  floor_plan:
+      # 'segmentation' => computes floor plan segmentation,
+      #  'regression' => uses DBSCAN to partitions labels into train, test split
+      type: floor_classification
+
+  model_params:
+    type: GRID_OVERLAP-BBOX_CNN # (DNN, CNN, kNN, SVM) supported (require different parameters)
+    #first_neuron: 512
+    #hidden_layers: 1
+    lr: 0.002
+    batch_size: 32
+    epochs: 1
+    #dropout: 0.7
+    #regularization_penalty: 0.0
+    augmentation: 0
+    autoencoder: train
+    #pretrain: yes
+
+pipelines:
+
+  - name: CNNLoc
+    model_params:
+      lr: 0.002
+      type: CNNLoc_REG
+      autoencoder: train
+
+  - name: CNNLoc-DLB
+    model_params:
+      lr: 0.002
+      batch_size: 32
+      augmentation: 0
+      autoencoder: train
+
+      loss:
+        grid:
+          scale: 100.0
+        outside:
+          scale: 1.0
+          delta: [10.0, 15.0, 20.0]
+
+  - name: DNN
+    model_params:
+      type: DNN # (DNN, CNN, kNN, SVM) supported (require different parameters)
+      pred: regression
+      first_neuron: 512
+      hidden_layers: [1,2,3]
+      lr: 0.7
+      batch_size: 32
+      #epochs: 200
+      dropout: 0.5
+      regularization_penalty: 0.0
+      augmentation: 0
+
+  - name: DNN-DLB
+    model_params:
+      type: GRID_OVERLAP-BBOX # (DNN, CNN, kNN, SVM) supported (require different parameters)
+      first_neuron: 512
+      hidden_layers: [1,2]
+      lr: 0.7
+      batch_size: 32
+      #epochs: 200
+      dropout: 0.5
+      regularization_penalty: 0.0
+      augmentation: 0
+
+      loss:
+        grid:
+          scale: 100.0
+        outside:
+          scale: 1.0
+          delta: [10.0, 15.0, 20.0]
+
+
+
+# base directories for file storage
+output:
+    model_dir: evaluation/uji/gpu/b0/f2/output/
+    summary_dir: evaluation/uji/gpu/b0/f2/summary/
+    img_folder: evaluation/uji/ # folder where floorplan images is located (if not present, will be downloaded)

config/gpu_b0_f3.yml

+data:
+  # The data provider which should be used
+  provider: UJIndoorLocProvider
+  # File name of floor plan img
+  floor_plan_img: <test>.jpg
+  # (train, val, test) test=0.2 => 5 fold  # The number of temporal epochs into which the dataset is split
+  split_ratio: [0.7, 0.1, 0.2]
+  building: 0
+  floor: 3
+
+#
+# are used when not locally set for pipeline
+#
+
+global_params:
+
+  # number of experiment repetitions
+  repetitions: 10
+
+  preprocessing:
+    # Whether to standardize the RSS values
+    standardize: True
+    # Whether to assign labels with no matching area to closet area
+    assign_closest: False
+    # The floor number of the Lohan dataset, which should be used
+    #floor: 0
+    # The epoch number of the split dataset
+    #num_epochs: 10
+    #epoch: 5
+    # How to check for area matches of labels (to label positions with matching areas)
+    area_assignment: convex_hull
+    grid_size: 40
+
+  floor_plan:
+      # 'segmentation' => computes floor plan segmentation,
+      #  'regression' => uses DBSCAN to partitions labels into train, test split
+      type: floor_classification
+
+  model_params:
+    type: GRID_OVERLAP-BBOX_CNN # (DNN, CNN, kNN, SVM) supported (require different parameters)
+    #first_neuron: 512
+    #hidden_layers: 1
+    lr: 0.002
+    batch_size: 32
+    epochs: 1
+    #dropout: 0.7
+    #regularization_penalty: 0.0
+    augmentation: 0
+    autoencoder: train
+    #pretrain: yes
+
+pipelines:
+
+  - name: CNNLoc
+    model_params:
+      lr: 0.002
+      type: CNNLoc_REG
+      autoencoder: train
+
+  - name: CNNLoc-DLB
+    model_params:
+      lr: 0.002
+      batch_size: 32
+      augmentation: 0
+      autoencoder: train
+
+      loss:
+        grid:
+          scale: 100.0
+        outside:
+          scale: 1.0
+          delta: [10.0, 15.0, 20.0]
+
+  - name: DNN
+    model_params:
+      type: DNN # (DNN, CNN, kNN, SVM) supported (require different parameters)
+      pred: regression
+      first_neuron: 512
+      hidden_layers: [1,2,3]
+      lr: 0.7
+      batch_size: 32
+      #epochs: 200
+      dropout: 0.5
+      regularization_penalty: 0.0
+      augmentation: 0
+
+  - name: DNN-DLB
+    model_params:
+      type: GRID_OVERLAP-BBOX # (DNN, CNN, kNN, SVM) supported (require different parameters)
+      first_neuron: 512
+      hidden_layers: [1,2]
+      lr: 0.7
+      batch_size: 32
+      #epochs: 200
+      dropout: 0.5
+      regularization_penalty: 0.0
+      augmentation: 0
+
+      loss:
+        grid:
+          scale: 100.0
+        outside:
+          scale: 1.0
+          delta: [10.0, 15.0, 20.0]
+
+
+
+# base directories for file storage
+output:
+    model_dir: evaluation/uji/gpu/b0/f3/output/
+    summary_dir: evaluation/uji/gpu/b0/f3/summary/
+    img_folder: evaluation/uji/ # folder where floorplan images is located (if not present, will be downloaded)

main.py

@@ -44,8 +44,11 @@ def execute(conf_file):
     # only PD
     conf.download_floor_plan()
 
+    # obtain pipeline config variations
+    pipeline_configs = conf.get_pipeline_variation(conf.pipelines)
+
     # sequentially execute all training pipelines
-    for p_idx, pipeline_params in enumerate(conf.pipelines):
+    for p_idx, pipeline_params in enumerate(pipeline_configs):
 
         # set random seeds
         # if 'ns' in pipeline_params:
@@ -61,7 +64,7 @@ def execute(conf_file):
 
         num_iterations = conf.get_params('repetitions', pipeline_params)
         log.info('Train and evaluate il_pipeline "{}"... ({}/{}))'.format(
-            pipeline_params['name'], p_idx + 1, len(conf.pipelines)))
+            pipeline_params['name'], p_idx + 1, len(pipeline_configs)))
         log.info('Repeat {} time(s) and build average...'.format(num_iterations))
 
         # read pipeline parameters