patch: documentation upgrade

app.py

@@ -1,6 +1,6 @@
 """
-building-segmentation
-Proof of concept showing effectiveness of a fine tuned instance segmentation model for deteting buildings.
+tree-segmentation
+Proof of concept showing effectiveness of a fine tuned instance segmentation model for detecting trees.
 """
 import os
 import cv2
@@ -32,7 +32,7 @@ cfg.MODEL.WEIGHTS = "model_weights/tree_model.pth"
 cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
 predictor = DefaultPredictor(cfg)
 
-def segment_buildings(im):
+def segment_image(im):
 
     im = np.array(im)
     outputs = predictor(im)
@@ -40,7 +40,7 @@ def segment_buildings(im):
                    scale=0.5,
                    instance_mode=ColorMode.IMAGE_BW
     )
-    print(len(outputs["instances"])," buildings detected.")
+    print(len(outputs["instances"])," trees detected.")
     out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
     
     return Image.fromarray(out.get_image()[:, :, ::-1])
@@ -54,11 +54,11 @@ gr_slider_confidence = gr.inputs.Slider(0,1,.1,.7,
 inputs = gr.inputs.Image(type="pil", label="Input Image")
 outputs = gr.outputs.Image(type="pil", label="Output Image")
 
-title = "Building Segmentation"
-description = "An instance segmentation demo for identifying boundaries of buildings in aerial images using DETR (End-to-End Object Detection) model with MaskRCNN-101 backbone"
+title = "Tree Segmentation"
+description = "An instance segmentation demo for identifying trees in aerial images using DETR (End-to-End Object Detection) model with MaskRCNN-101 backbone"
 
 # Create user interface and launch
-gr.Interface(segment_buildings, 
+gr.Interface(segment_image, 
                 inputs = inputs,
                 outputs = outputs,
                  title = title,