Rename SpotDetection application to Polaris

README.md

@@ -46,9 +46,9 @@ docker run --gpus '"device=0"' -it \
 ### How to Use
 
 ```python
-from deepcell_spots.applications.spot_detection import SpotDetection
+from deepcell_spots.applications import Polaris
 
-app = SpotDetection()
+app = Polaris()
 # image is an np array with dimensions (batch,x,y,channel)
 # threshold is the probability threshold that a pixel must exceed to be considered a spot
 coords = app.predict(image,threshold=0.9)

deepcell_spots/applications/__init__.py

@@ -24,4 +24,4 @@
 # limitations under the License.
 # ==============================================================================
 
-from deepcell_spots.applications.spot_detection import SpotDetection
+from deepcell_spots.applications.polaris import Polaris

deepcell_spots/applications/spot_detection.py → deepcell_spots/applications/polaris.py

@@ -33,7 +33,6 @@
 import tensorflow as tf
 from deepcell.applications import Application
 
-from deepcell_spots.dotnet import *
 from deepcell_spots.dotnet_losses import DotNetLosses
 from deepcell_spots.postprocessing_utils import y_annotations_to_point_list_max
 from deepcell_spots.preprocessing_utils import min_max_normalize
@@ -43,22 +42,22 @@
               'saved-models/SpotDetection-3.tar.gz')
 
 
-class SpotDetection(Application):
-    """Loads a :mod:`deepcell.model_zoo.panopticnet.PanopticNet` model
-    for nuclear segmentation with pretrained weights.
+class Polaris(Application):
+    """Loads a :mod:`deepcell.model_zoo.featurenet.FeatureNet` model
+    for fluorescent spot detection with pretrained weights.
     The ``predict`` method handles prep and post processing steps
     to return a labeled image.
     Example:
     .. code-block:: python
         from skimage.io import imread
-        from deepcell_spots.applications import SpotDetection
+        from deepcell_spots.applications import Polaris
         # Load the image
-        im = imread('HeLa_nuclear.png')
+        im = imread('spots_image.png')
         # Expand image dimensions to rank 4
         im = np.expand_dims(im, axis=-1)
         im = np.expand_dims(im, axis=0)
         # Create the application
-        app = SpotDetection()
+        app = Polaris()
         # create the lab
         labeled_image = app.predict(im)
     Args:
@@ -86,7 +85,6 @@ class SpotDetection(Application):
     def __init__(self, model=None):
 
         if model is None:
-            # model_path = '/data/20210331-training_data/models/em_model'
             archive_path = tf.keras.utils.get_file(
                 'SpotDetection.tgz', MODEL_PATH,
                 file_hash='2b9a46087b25e9aab20a2c9f67f4f559',
@@ -100,7 +98,7 @@ def __init__(self, model=None):
                 }
             )
 
-        super(SpotDetection, self).__init__(
+        super(Polaris, self).__init__(
             model,
             model_image_shape=model.input_shape[1:],
             model_mpp=0.65,
@@ -203,8 +201,9 @@ def predict(self,
                 preprocess_kwargs=None,
                 postprocess_kwargs=None,
                 threshold=0.9):
-        """Generates a labeled image of the input running prediction with
-        appropriate pre and post processing functions.
+        """Generates a list of coordinate spot locations of the input
+        running prediction with appropriate pre and post processing
+        functions.
         Input images are required to have 4 dimensions
         ``[batch, x, y, channel]``.
         Additional empty dimensions can be added using ``np.expand_dims``.

notebooks/Multiplex FISH Analysis.ipynb

@@ -21,7 +21,7 @@
     "from skimage import transform\n",
     "from skimage.feature import register_translation\n",
     "from sklearn.cluster import DBSCAN\n",
-    "from deepcell_spots.applications.spot_detection import SpotDetection\n",
+    "from deepcell_spots.applications import Polaris\n",
     "from deepcell_spots.spot_em import define_edges\n",
     "from deepcell_spots.point_metrics import *\n",
     "from deepcell_spots.singleplex import *\n",
@@ -700,7 +700,7 @@
    "outputs": [],
    "source": [
     "# Instantiate the spot detection application\n",
-    "spots_app = SpotDetection()"
+    "spots_app = Polaris()"
    ]
   },
   {
@@ -1090,13 +1090,6 @@
     "plt.tight_layout()\n",
     "plt.show()"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -1120,4 +1113,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 2
-}
+}

notebooks/Singleplex FISH Analysis.ipynb

@@ -14,7 +14,7 @@
     "from deepcell_toolbox.processing import histogram_normalization,normalize\n",
     "from deepcell_toolbox.deep_watershed import deep_watershed\n",
     "from deepcell.applications import CytoplasmSegmentation,NuclearSegmentation\n",
-    "from deepcell_spots.applications.spot_detection import SpotDetection\n",
+    "from deepcell_spots.applications import Polaris\n",
     "from deepcell_spots.singleplex import *\n",
     "\n",
     "class OverrideCytoplamSegmentation(CytoplasmSegmentation):\n",
@@ -297,7 +297,7 @@
    "outputs": [],
    "source": [
     "# Initialize spot detection application\n",
-    "spots_app = SpotDetection()"
+    "spots_app = Polaris()"
    ]
   },
   {
@@ -437,13 +437,6 @@
     "plt.tight_layout()\n",
     "plt.show()"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -467,4 +460,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 2
-}
+}