initial commit

BboxModel.py

+import math
+
+from data.data_provider_base import DataProviderBase
+from il_pipeline.models.dnn_model import DnnModel
+from il_pipeline.summary.summary import KFoldClassSummary
+from il_pipeline.models.tf_model_definition import classification_model_for_generator, cnn_model_for_generator
+from tensorflow.keras import Sequential
+from tensorflow.keras.activations import softmax, linear
+from tensorflow.keras.losses import mean_squared_error
+from tensorflow.keras.backend import categorical_crossentropy, relu, softmax
+from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping
+from tensorflow.keras.optimizers import Adam
+
+from bbox_model_definition import bbox_model_for_generator
+from custom_loss import custom_loss_tf, bbox_loss, center_loss
+
+
+class BboxModel(DnnModel):
+
+    def __init__(self, type="classification", summary: KFoldClassSummary=None,
+                 data_provider: DataProviderBase=None,
+                 params=None, output_dir=None, filename=None):
+        super().__init__(type, summary, data_provider, params, output_dir, filename)
+
+    def load_weights(self):
+        self.classifier.load_weights(self.output_dir + self.filename + ".hdf5")
+
+    def setup_params(self):
+        params = self.params
+
+        # update parameters with standard values for classification model
+        params.update({
+            'shape': 'brick',
+            'weight_regulizer': None,
+            'kernel_initializer': 'he_normal',
+            'optimizer': Adam,
+            'activation': relu})
+
+        if self.type == "classification" or "CNN" in self.type:
+            params.update({'last_activation': softmax,
+                           'losses': categorical_crossentropy})
+        elif self.type == "regression":
+            params.update({'last_activation': linear,
+                           'losses': mean_squared_error})
+        elif self.type == "BBOX":
+            params.update({'last_activation': linear,
+                           'losses': bbox_loss})
+
+    def pre_train_model(self):
+        self.params.update({'losses': center_loss})
+        self.setup_model()
+        self._train_model(save_weights_only=True, evaluate=False)
+
+    def setup_model(self, setup_params=False):
+        # use instance variables if no optional variables are supplied
+        output_dir = self.output_dir
+        data_provider = self.data_provider
+        params = self.params
+
+        if setup_params:
+            self.setup_params()
+
+        # obtain Keras classifier (Sequential) for specified parameters
+        x_cols, y_cols = data_provider.get_data_dims("regression")
+        if self.type == "regression":
+            y_cols = 2
+        if self.type == "BBOX":
+            y_cols = 4
+
+        # obtain the model definition
+        if "BBOX" in self.type:
+            classifier_template = bbox_model_for_generator(metrics=[])
+            self.classifier = classifier_template(X_cols=x_cols, Y_cols=y_cols, params=params)
+        elif "CNN" in self.type:
+            classifier_template = cnn_model_for_generator(metrics=[])
+            self.classifier = classifier_template(input_shape=x_cols,
+                                                  Y_cols=y_cols, params=params)
+        else:
+            classifier_template = classification_model_for_generator(
+                metrics=[])
+
+            self.classifier = classifier_template(
+                X_cols=x_cols, Y_cols=y_cols, params=params)
+
+        self.type = "regression"
+
+    def _train_model(self, save_weights_only=False, evaluate=True):
+        """
+        Trains a DNN model with the specified parameters using Keras
+        fit_generator function. Model is evaluated on separate test data
+        """
+        output_dir = self.output_dir
+        data_provider = self.data_provider
+        params = self.params
+
+        # self.setup_model()
+
+        # calculate batch sizes (might be smaller than specified batch size if
+        # not enough data supplied)
+        num_train, num_val, num_test = data_provider.get_train_val_test_num(area_labels=self.type != "regression")
+
+        train_bs = min(num_train, params['batch_size'])
+        val_bs = min(num_val, train_bs)
+        test_bs = min(num_test, train_bs)
+
+        # calculate the steps per epoch (used by generator) to determine
+        # after how many steps a new epoch starts (model has seen all data)
+        val_steps_per_epoch = math.ceil(num_val / val_bs)
+        num_augs = 0
+        if 'augmentation' in params and params['augmentation'] is not None:
+            num_augs = params['augmentation']
+
+        train_steps_per_epoch = math.ceil(num_train * (num_augs + 1) / train_bs)
+
+        # setup callbacks
+        checkpoint_file_name = output_dir + "{}.hdf5".format(self.filename)
+
+        # save best performing model parameters
+        checkpoint = ModelCheckpoint(checkpoint_file_name, verbose=0,
+                                     monitor='val_loss',
+                                     save_best_only=True, mode='auto',
+                                     save_weights_only=save_weights_only)
+
+        earlyStopping = EarlyStopping(monitor='val_loss',
+                                      patience=60,
+                                      verbose=0,
+                                      mode='auto')
+
+        # obtain generator function from data provider
+        generator = data_provider.in_mem_data_generator
+        area_labels = self.type == "classification" or "CNN" in self.type
+
+        noise_percentage = None
+        if 'noise_percentage' in self.params:
+            noise_percentage = self.params['noise_percentage']
+
+        train_on_noisy_labels = False
+        if 'noisy_labels' in self.params:
+            train_on_noisy_labels = True
+
+        self.classifier.fit_generator(
+            generator(mode='train',
+                      model_type=self.type,
+                      area_labels=area_labels,
+                      augmentation=num_augs,
+                      noise_percentage=noise_percentage,
+                      noisy_labels=train_on_noisy_labels),
+            validation_data=generator(mode='val', model_type=self.type,
+                                      area_labels=area_labels,
+                                      noisy_labels=train_on_noisy_labels,
+                                      batch_size=val_bs),
+            validation_steps=val_steps_per_epoch,
+            steps_per_epoch=train_steps_per_epoch,
+            epochs=params['epochs'],
+            callbacks=[earlyStopping, checkpoint],
+            verbose=0)
+
+        # evaluate model and store results in summary file
+        if evaluate:
+            self.evaluate_model(test_bs)
\ No newline at end of file

bbox_model_definition.py

+from tensorflow.keras import regularizers
+from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping
+from tensorflow.keras.layers import Dense, Dropout, Conv2D, MaxPooling2D, Flatten
+from tensorflow.keras.models import Sequential
+from il_pipeline.models.layer_generator import hidden_layers
+from il_pipeline.models.lr_normalizer import lr_normalizer
+
+
+def bbox_model_for_generator(metrics):
+
+    def define_classification_model_for_generator(X_cols, Y_cols, params) -> Sequential:
+        model = Sequential()
+
+        model.add(Dense(params['first_neuron'], input_dim=X_cols,
+                        activation=params['activation'],
+                        kernel_regularizer=regularizers.l2(
+                            params['regularization_penalty'])))
+
+        model.add(Dropout(params['dropout']))
+
+        hidden_layers(model, params, X_cols)
+
+        model.add(Dense(Y_cols, activation=params['last_activation'],
+                        kernel_initializer=params['kernel_initializer'],
+                        kernel_regularizer=regularizers.l2(
+                            params['regularization_penalty'])))
+
+        # compile the model
+        model.compile(loss=params['losses'],
+                      metrics=[*metrics],
+                      optimizer=params['optimizer'](
+                          lr=lr_normalizer(params['lr'], params['optimizer'])))
+
+        return model
+
+
+    return define_classification_model_for_generator
\ No newline at end of file

bbox_pipeline.py

+from data.data_provider_base import DataProviderBase
+from il_pipeline.models.dnn_model import DnnModel
+from il_pipeline.models.svm_model import SvmModel
+from il_pipeline.models.transfer_model import TransferModel
+from il_pipeline.pipeline import Pipeline
+from il_pipeline.utility.config_reader import ConfigReader
+from ldce.base import ClusterBase
+from BboxModel import BboxModel
+
+
+class BboxPipeline(Pipeline):
+    def __init__(self, data_provider: DataProviderBase=None,
+                 clusterer: ClusterBase=None, config: ConfigReader=None,
+                 params=None, filename=None):
+        super().__init__(data_provider, clusterer, config, params, filename)
+
+    def train_model(self):
+        super().train_model()
+
+        params = self.model_params
+
+        if params['type'] == "BBOX":
+            model = BboxModel(params['type'], self.summary, self.data_provider, params,
+                     self.config.output_dir, self.filename)
+            model.setup_params()
+            model.pre_train_model()
+
+            model.type = "BBOX"
+            model.setup_model(setup_params=True)
+            model.load_weights()
+            model.train_model()

config.yml

+data:
+  # The data provider which should be used
+  provider: PDdataProvider
+  # File name of floor plan img
+  floor_plan_img: gia_floor_4.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]
+  connection: postgres://ogvxncajvywtut:98d3541b0d276eeb9fb9a892a308afdb6f99d9f0c705676ccb6dd8ad57346ee9@ec2-54-217-208-105.eu-west-1.compute.amazonaws.com:5432/d4g66sh4pgrte0
+  REST_connection:
+    base_url: https://indoor-localization.herokuapp.com/
+    token: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySUQiOjEsImlhdCI6MTU4MzIyOTQ2MCwiZXhwIjoxNTgzMzE1ODYwLCJhdWQiOiJsb2NhbGhvc3QiLCJpc3MiOiJsb2NhbGhvc3QifQ.aF8-wgZYjANzRb5e0bSlwI0bnV7ru8Wwlb8N5W12KYg
+  map_id: 1
+
+#
+# are used when not locally set for pipeline
+#
+
+global_params:
+
+  # number of experiment repetitions
+  repetitions: 1
+
+  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
+
+  model_params:
+    type: BBOX # (DNN, CNN, kNN, SVM) supported (require different parameters)
+    first_neuron: 512
+    hidden_layers: 3
+    lr: 0.7
+    batch_size: 32
+    epochs: 200
+    dropout: 0.5
+    regularization_penalty: 0
+    augmentation: 0
+
+#
+# List of pipelines that are executed
+#
+
+pipelines:
+
+  - name: gia_upload_class
+    floor_plan:
+      # 'segmentation' => computes floor plan segmentation,
+      #  'regression' => uses DBSCAN to partitions labels into train, test split
+      type: regression
+      # file where segmentation is stored or loaded from
+      seg_file: evaluation/gia_class_particle
+      # whether to 'load' or compute and 'store' the segmentation
+      mode: store # (load/store)
+      # file location that holds numpy array with walls (rows of form [s_x, s_y, e_x, e_y]
+      walls_file: /home/laskama/PycharmProjects/automaticPartitioning/my_new_walls.npy
+      # parameters of floor plan segmentation algorithm
+      segmentation:
+        # algorithm identifier (currently only LDCE supported)
+        type: LDCE
+        # file location of precomputed distance file (will be recomputed if it does not exist yet)
+        precomp_dist_file: evaluation/precomp_dist_gia(0,0).npy
+        # Parameters of LDCE algorithm
+        stop_size: 1
+        eps: 0.8
+        max_eps: 50
+        min_pts: 2
+        min_members: 1
+        rss_penalty: 0
+        wall_penalty: 0
+        cluster_penalty: 20
+        area_mode: convex_hull
+
+# base directories for file storage
+output:
+    model_dir: evaluation/gia/upload/particle/test/output/
+    summary_dir: evaluation/gia/upload/particle/test/summary/
+    img_folder: evaluation/gia/ # folder where floorplan images is located (if not present, will be downloaded)
\ No newline at end of file

config_gia_pretrain.yml

+data:
+  # The data provider which should be used
+  provider: PDdataProvider
+  # File name of floor plan img
+  floor_plan_img: gia_floor_4.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]
+  connection: postgres://ogvxncajvywtut:98d3541b0d276eeb9fb9a892a308afdb6f99d9f0c705676ccb6dd8ad57346ee9@ec2-54-217-208-105.eu-west-1.compute.amazonaws.com:5432/d4g66sh4pgrte0
+  REST_connection:
+    base_url: https://indoor-localization.herokuapp.com/
+    token: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySUQiOjEsImlhdCI6MTU4MzIyOTQ2MCwiZXhwIjoxNTgzMzE1ODYwLCJhdWQiOiJsb2NhbGhvc3QiLCJpc3MiOiJsb2NhbGhvc3QifQ.aF8-wgZYjANzRb5e0bSlwI0bnV7ru8Wwlb8N5W12KYg
+  map_id: 1
+
+#
+# are used when not locally set for pipeline
+#
+
+global_params:
+
+  # number of experiment repetitions
+  repetitions: 1
+
+  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
+
+  model_params:
+    type: BBOX # (DNN, CNN, kNN, SVM) supported (require different parameters)
+    first_neuron: 512
+    hidden_layers: 3
+    lr: 0.7
+    batch_size: 32
+    epochs: 200
+    dropout: 0.5
+    regularization_penalty: 0
+    augmentation: 0
+
+#
+# List of pipelines that are executed
+#
+
+pipelines:
+
+  - name: BBOX
+    floor_plan:
+      # 'segmentation' => computes floor plan segmentation,
+      #  'regression' => uses DBSCAN to partitions labels into train, test split
+      type: regression
+      # file where segmentation is stored or loaded from
+      seg_file: evaluation/gia_reg_bbox
+      # whether to 'load' or compute and 'store' the segmentation
+      mode: load # (load/store)
+      # file location that holds numpy array with walls (rows of form [s_x, s_y, e_x, e_y]
+      walls_file: /home/laskama/PycharmProjects/automaticPartitioning/my_new_walls.npy
+      # parameters of floor plan segmentation algorithm
+      segmentation:
+        # algorithm identifier (currently only LDCE supported)
+        type: LDCE
+        # file location of precomputed distance file (will be recomputed if it does not exist yet)
+        precomp_dist_file: evaluation/precomp_dist_gia_new(0,0).npy
+        # Parameters of LDCE algorithm
+        stop_size: 1
+        eps: 0.7
+        max_eps: 50
+        min_pts: 3
+        min_members: 1
+        rss_penalty: 0
+        wall_penalty: 0
+        cluster_penalty: 20
+        area_mode: convex_hull
+
+# base directories for file storage
+output:
+    model_dir: evaluation/gia/pretrain/box/output/
+    summary_dir: evaluation/gia/pretrain/box/summary/
+    img_folder: evaluation/gia/ # folder where floorplan images is located (if not present, will be downloaded)
\ No newline at end of file

config_lohan.yml

+data:
+  # The data provider which should be used
+  provider: LohanDSprovider
+  # File name of floor plan img
+  floor_plan_img: <image_name>
+  # (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]
+
+#
+# are used when not locally set for pipeline
+#
+
+global_params:
+
+  # number of experiment repetitions
+  repetitions: 1
+
+  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
+
+  floor_plan:
+    # 'segmentation' => computes floor plan segmentation,
+    #  'regression' => uses DBSCAN to partitions labels into train, test split
+    type: regression
+    # file where segmentation is stored or loaded from
+    seg_file: evaluation/lohan_class_particle
+    # whether to 'load' or compute and 'store' the segmentation
+    mode: load # (load/store)
+    # file location that holds numpy array with walls (rows of form [s_x, s_y, e_x, e_y]
+    walls_file: lohan/LohanWalls1stfloor.npy
+    # parameters of floor plan segmentation algorithm
+    segmentation:
+      # algorithm identifier (currently only LDCE supported)
+      type: LDCE
+      # file location of precomputed distance file (will be recomputed if it does not exist yet)
+      precomp_dist_file: evaluation/precomp_dist_lohan(0,0).npy
+      # Parameters of LDCE algorithm
+      stop_size: 1
+      eps: 0.8
+      max_eps: 50
+      min_pts: 2
+      min_members: 1
+      rss_penalty: 0
+      wall_penalty: 0
+      cluster_penalty: 20
+      area_mode: convex_hull
+
+  model_params:
+    type: BBOX # (DNN, CNN, kNN, SVM) supported (require different parameters)
+    first_neuron: 512
+    hidden_layers: 3
+    lr: 0.7
+    batch_size: 32
+    epochs: 200
+    dropout: 0.5
+    regularization_penalty: 0
+    augmentation: 0
+
+#
+# List of pipelines that are executed
+#
+
+pipelines:
+
+  - name: DNN
+    model_params:
+      pred: regression
+      type: DNN
+  - name: BBOX
+    model_params:
+      type: BBOX
+
+# base directories for file storage
+output:
+    model_dir: evaluation/lohan_cmp/output/
+    summary_dir: evaluation/lohan_cmp/summary/
+    img_folder: evaluation/lohan/ # folder where floorplan images is located (if not present, will be downloaded)
\ No newline at end of file

config_lohan_progress.yml

+data:
+  # The data provider which should be used
+  provider: LohanDSprovider
+  # File name of floor plan img
+  floor_plan_img: <image_name>
+  # (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]
+
+#
+# are used when not locally set for pipeline
+#
+
+global_params:
+
+  # number of experiment repetitions
+  repetitions: 1
+
+  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
+
+  floor_plan:
+    # 'segmentation' => computes floor plan segmentation,
+    #  'regression' => uses DBSCAN to partitions labels into train, test split
+    type: regression
+    # file where segmentation is stored or loaded from
+    seg_file: evaluation/lohan_class_particle
+    # whether to 'load' or compute and 'store' the segmentation
+    mode: load # (load/store)
+    # file location that holds numpy array with walls (rows of form [s_x, s_y, e_x, e_y]
+    walls_file: lohan/LohanWalls1stfloor.npy
+    # parameters of floor plan segmentation algorithm
+    segmentation:
+      # algorithm identifier (currently only LDCE supported)
+      type: LDCE
+      # file location of precomputed distance file (will be recomputed if it does not exist yet)
+      precomp_dist_file: evaluation/precomp_dist_lohan(0,0).npy
+      # Parameters of LDCE algorithm
+      stop_size: 1
+      eps: 0.8
+      max_eps: 50
+      min_pts: 2
+      min_members: 1
+      rss_penalty: 0
+      wall_penalty: 0
+      cluster_penalty: 20
+      area_mode: convex_hull
+
+  model_params:
+    type: BBOX # (DNN, CNN, kNN, SVM) supported (require different parameters)
+    first_neuron: 512
+    hidden_layers: 3
+    lr: 0.7
+    batch_size: 32
+    epochs: 200
+    dropout: 0.5
+    regularization_penalty: 0
+    augmentation: 0
+
+#
+# List of pipelines that are executed
+#
+
+pipelines:
+
+  - name: BBOX
+    model_params:
+      type: BBOX
+      pretraining: center_loss
+      epochs: 100
+#  - name: BBOX_1
+#    model_params:
+#      type: BBOX
+#      epochs: 1
+#  - name: BBOX_2
+#    model_params:
+#      type: BBOX
+#      epochs: 2
+#  - name: BBOX_3
+#    model_params:
+#      type: BBOX
+#      epochs: 3
+#  - name: BBOX_4
+#    model_params:
+#      type: BBOX
+#      epochs: 4
+#  - name: BBOX_5
+#    model_params:
+#      type: BBOX
+#      epochs: 5
+
+# base directories for file storage
+output:
+    model_dir: evaluation/lohan_pretrain/output/
+    summary_dir: evaluation/lohan_pretrain/summary/
+    img_folder: evaluation/lohan/ # folder where floorplan images is located (if not present, will be downloaded)
\ No newline at end of file

custom_loss.py

+import numpy as np
+import tensorflow as tf
+
+def test_center_loss():
+
+    init = tf.global_variables_initializer()
+
+    y_true = np.array([[4, 3], [9, 2], [3, 1], [2, 2], [7, 2]])
+
+    y_pred = np.array(
+        [[4, 3, 2, 3], [8, 0, 6, 3], [10, 2, 8, 4], [3, 1, 7, 3],
+         [8, 1, 12, 4]])
+
+    y_true = tf.constant(y_true, dtype=tf.float32)
+    y_pred = tf.constant(y_pred, dtype=tf.float32)
+
+    with tf.Session() as sess:
+        # Run the initializer on `w`.
+        sess.run(init)
+        print(sess.run(bbox_loss(y_true, y_pred)))
+        writer = tf.summary.FileWriter("output", sess.graph)
+
+        writer.close()
+
+
+def center_loss(y_true, y_pred):