Merge pull request #134 from karolmajek/devel

Place Recognition support

docs/source/main/model_zoo/MODEL_ZOO.md

@@ -21,6 +21,13 @@ The [Model ZOO](https://chmura.put.poznan.pl/s/2pJk4izRurzQwu3) is a collection
 |         |  |  |  |  |
 |         |  |  |  |  |
 
+## Recognition models
+
+| Model   | Input size | CM/PX | Description | Example image |
+|---------|---|---|---|---|
+|  NAIP Place recognition | 224 | 100 | ConvNeXt nano trained using SimSiam onn NAIP imagery |  |
+|         |  |  |  |  |
+
 ## Object detection models
 
 | Model                                                                          | Input size | CM/PX | Description                                                                                                                                                                                   | Example image                                           |

src/deepness/common/processing_parameters/map_processing_parameters.py

@@ -20,6 +20,7 @@ class ModelOutputFormat(enum.Enum):
     ALL_CLASSES_AS_SEPARATE_LAYERS = 'All classes as separate layers'
     CLASSES_AS_SEPARATE_LAYERS_WITHOUT_ZERO_CLASS = 'Classes as separate layers (without 0 class)'
     ONLY_SINGLE_CLASS_AS_LAYER = 'Single class as a vector layer'
+    RECOGNITION_RESULT = 'Cosine distance between query image and map'
 
     @classmethod
     def get_all_names(cls):

src/deepness/common/processing_parameters/recognition_parameters.py

@@ -0,0 +1,17 @@
+import enum
+from dataclasses import dataclass
+from typing import Optional
+
+from deepness.common.processing_parameters.map_processing_parameters import \
+    MapProcessingParameters
+from deepness.processing.models.model_base import ModelBase
+
+
+@dataclass
+class RecognitionParameters(MapProcessingParameters):
+    """
+    Parameters for Inference of Recognition model (including pre/post-processing) obtained from UI.
+    """
+
+    query_image_path: str  # path to query image
+    model: ModelBase  # wrapper of the loaded model

src/deepness/deepness_dockwidget.py

@@ -18,6 +18,7 @@
 from deepness.common.processing_parameters.detection_parameters import DetectionParameters, DetectorType
 from deepness.common.processing_parameters.map_processing_parameters import (MapProcessingParameters, ModelOutputFormat,
                                                                              ProcessedAreaType)
+from deepness.common.processing_parameters.recognition_parameters import RecognitionParameters
 from deepness.common.processing_parameters.regression_parameters import RegressionParameters
 from deepness.common.processing_parameters.segmentation_parameters import SegmentationParameters
 from deepness.common.processing_parameters.superresolution_parameters import SuperresolutionParameters
@@ -196,6 +197,7 @@ def get_selected_processed_area_type(self) -> ProcessedAreaType:
     def _create_connections(self):
         self.pushButton_runInference.clicked.connect(self._run_inference)
         self.pushButton_runTrainingDataExport.clicked.connect(self._run_training_data_export)
+        self.pushButton_browseQueryImagePath.clicked.connect(self._browse_query_image_path)
         self.pushButton_browseModelPath.clicked.connect(self._browse_model_path)
         self.comboBox_processedAreaSelection.currentIndexChanged.connect(self._set_processed_area_mask_options)
         self.comboBox_modelType.currentIndexChanged.connect(self._model_type_changed)
@@ -216,6 +218,7 @@ def _model_type_changed(self):
         detection_enabled = False
         regression_enabled = False
         superresolution_enabled = False
+        recognition_enabled = False
 
         if model_type == ModelType.SEGMENTATION:
             segmentation_enabled = True
@@ -225,15 +228,19 @@ def _model_type_changed(self):
             regression_enabled = True
         elif model_type == ModelType.SUPERRESOLUTION:
             superresolution_enabled = True
+        elif model_type == ModelType.RECOGNITION:
+            recognition_enabled = True
         else:
             raise Exception(f"Unsupported model type ({model_type})!")
 
         self.mGroupBox_segmentationParameters.setVisible(segmentation_enabled)
         self.mGroupBox_detectionParameters.setVisible(detection_enabled)
         self.mGroupBox_regressionParameters.setVisible(regression_enabled)
         self.mGroupBox_superresolutionParameters.setVisible(superresolution_enabled)
-        # Disable output format options for super-resolution models.
-        self.mGroupBox_6.setEnabled(not superresolution_enabled)
+        self.mGroupBox_recognitionParameters.setVisible(recognition_enabled)
+        # Disable output format options for super-resolution or recognition models.
+        if recognition_enabled or superresolution_enabled:
+            self.mGroupBox_6.setEnabled(False)
 
     def _detector_type_changed(self):
         detector_type = DetectorType(self.comboBox_detectorType.currentText())
@@ -268,6 +275,16 @@ def _browse_model_path(self):
             self.lineEdit_modelPath.setText(file_path)
             self._load_model_and_display_info()
 
+    def _browse_query_image_path(self):
+        file_path, _ = QFileDialog.getOpenFileName(
+            self,
+            "Select image file...",
+            os.path.expanduser("~"),
+            "All files (*.*)",
+        )
+        if file_path:
+            self.lineEdit_recognitionPath.setText(file_path)
+
     def _load_default_model_parameters(self):
         """
         Load the default parameters from model metadata
@@ -478,6 +495,8 @@ def get_inference_parameters(self) -> MapProcessingParameters:
             params = self.get_regression_parameters(map_processing_parameters)
         elif model_type == ModelType.SUPERRESOLUTION:
             params = self.get_superresolution_parameters(map_processing_parameters)
+        elif model_type == ModelType.RECOGNITION:
+            params = self.get_recognition_parameters(map_processing_parameters)
         elif model_type == ModelType.DETECTION:
             params = self.get_detection_parameters(map_processing_parameters)
 
@@ -515,6 +534,14 @@ def get_superresolution_parameters(self, map_processing_parameters: MapProcessin
         )
         return params
 
+    def get_recognition_parameters(self, map_processing_parameters: MapProcessingParameters) -> RecognitionParameters:
+        params = RecognitionParameters(
+            **map_processing_parameters.__dict__,
+            model=self._model,
+            query_image_path=self.lineEdit_recognitionPath.text(),
+        )
+        return params
+
     def get_detection_parameters(self, map_processing_parameters: MapProcessingParameters) -> DetectionParameters:
 
         params = DetectionParameters(

src/deepness/deepness_dockwidget.ui

@@ -24,9 +24,9 @@
        <property name="geometry">
         <rect>
          <x>0</x>
-         <y>0</y>
+         <y>-325</y>
          <width>452</width>
-         <height>1621</height>
+         <height>1742</height>
         </rect>
        </property>
        <layout class="QVBoxLayout" name="verticalLayout_3">
@@ -626,6 +626,51 @@
           </layout>
          </widget>
         </item>
+        <item>
+         <widget class="QgsCollapsibleGroupBox" name="mGroupBox_recognitionParameters">
+          <property name="sizePolicy">
+           <sizepolicy hsizetype="Preferred" vsizetype="Maximum">
+            <horstretch>0</horstretch>
+            <verstretch>0</verstretch>
+           </sizepolicy>
+          </property>
+          <property name="title">
+           <string>Recognition parameters</string>
+          </property>
+          <layout class="QGridLayout" name="gridLayout_12">
+           <item row="1" column="1" colspan="2">
+            <widget class="QLabel" name="label_23">
+             <property name="font">
+              <font>
+               <weight>75</weight>
+               <bold>true</bold>
+              </font>
+             </property>
+             <property name="text">
+              <string>NOTE: Applicable only if a recognition model is used</string>
+             </property>
+            </widget>
+           </item>
+           <item row="3" column="1" colspan="2">
+            <widget class="QLabel" name="label_24">
+             <property name="text">
+              <string>Image to localize path:</string>
+             </property>
+            </widget>
+           </item>
+           <item row="4" column="1">
+            <widget class="QLineEdit" name="lineEdit_recognitionPath"/>
+           </item>
+           <item row="4" column="2">
+            <widget class="QPushButton" name="pushButton_browseQueryImagePath">
+             <property name="text">
+              <string>Browse</string>
+             </property>
+            </widget>
+           </item>
+          </layout>
+         </widget>
+        </item>
         <item>
          <widget class="QgsCollapsibleGroupBox" name="mGroupBox_detectionParameters">
           <property name="title">