Updated APP to see if I can get it to work on the website.

app.py

@@ -5,8 +5,10 @@ import requests, validators
 import torch
 import pathlib
 from PIL import Image
+import cv2 as cv
+import numpy as np
 
-from transformers import DetrFeatureExtractor, DetrForSegmentation, MaskFormerImageProcessor, MaskFormerForInstanceSegmentation
+from transformers import DetrImageProcessor, DetrForSegmentation, MaskFormerImageProcessor, MaskFormerForInstanceSegmentation
 from transformers.models.detr.feature_extraction_detr import rgb_to_id
 
 
@@ -60,6 +62,12 @@ def visualize_prediction(pil_img, output_dict, threshold=0.7, id2label=None):
     plt.axis("off")
     return fig2img(plt.gcf())
 
+def contour_map(map_to_use, label_id):
+    mask = (map_to_use.cpu().numpy() == label_id)
+    visual_mask = (mask * 255).astype(np.uint8)
+    contours, hierarchy = cv.findContours(visual_mask, cv.RETR_TREE, cv.CHAIN_APPROX_SIMPLE)
+    return contours, hierarchy
+
 def segment_images(model_name,url_input,image_input,threshold):
     ####
     # Get Image Object
@@ -81,6 +89,15 @@ def segment_images(model_name,url_input,image_input,threshold):
 
         outputs = model(**inputs)
         results = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
+
+        return_string = ""
+
+        for r in results["segments_info"]:
+            contour_list, hierarchy = contour_map(results["segmentation"], r["current_id"])
+            label_name = model.config.id2label[r["label_id"]]
+            return_string += f"ID: {r['id']}, Contour Length: {len(contour_list)}, Label Name: {label_name}, Score: {r['score']}\n"
+
+        return image, return_string
         
         pass
     else:

understand.py

@@ -6,7 +6,7 @@ import numpy as np
 from PIL import Image
 import cv2 as cv
 
-from transformers import DetrFeatureExtractor, DetrForSegmentation, MaskFormerImageProcessor, MaskFormerForInstanceSegmentation
+from transformers import DetrImageProcessor, DetrForSegmentation, MaskFormerImageProcessor, MaskFormerForInstanceSegmentation
 # from transformers.models.detr.feature_extraction_detr import rgb_to_id
 from transformers.image_transforms import rgb_to_id