Update app.py

app.py

@@ -70,7 +70,8 @@ model_path = "./model_final.pth"
 # cfg.MODEL.WEIGHTS = model_path
 
 # my_metadata = MetadataCatalog.get("dbmdz_coco_all")
-# my_metadata.thing_classes = ["Fiber", "Fiber"]
+Fiber_metadata.thing_classes = ["Fiber", "Fiber","Fiber"]
+# my_metadata.thing_classes = ["Fiber", "Fiber";]
 cfg = get_cfg()
 cfg.merge_from_file("./configs/detectron2/mask_rcnn_R_50_FPN_3x.yaml")
 cfg.MODEL.WEIGHTS = model_path #os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
@@ -96,7 +97,7 @@ def inference(image_url, image, min_score):
 
     outputs = predictor(im)
 
-    # v = Visualizer(im, my_metadata, scale=1.2)
+    # v = Visualizer(im, my_metadata, scale=1)
     # out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
 
 
@@ -117,14 +118,14 @@ def inference(image_url, image, min_score):
     
     
     
-    # # im = cv2.imread(d["file_name"])
+    # im = cv2.imread(d["file_name"])
     # outputs = predictor(im)
-    # v = Visualizer(im[:, :, ::-1],
-    #                 metadata=Fiber_metadata, 
-    #                 scale=1, 
-    #                 instance_mode=ColorMode.IMAGE_BW   # remove the colors of unsegmented pixels
-    # )
-    # v = v.draw_instance_predictions(outputs["instances"].to("cpu"))
+    v = Visualizer(im[:, :, ::-1],
+                    metadata=Fiber_metadata, 
+                    scale=1, 
+                    instance_mode=ColorMode.IMAGE_BW   # remove the colors of unsegmented pixels
+    )
+    v = v.draw_instance_predictions(outputs["instances"].to("cpu"))
     # cv2_imshow(v.get_image()[:, :, ::-1])
     # print(outputs["instances"])
     masks = np.asarray(outputs["instances"].pred_masks.to("cpu"))
@@ -190,7 +191,7 @@ def inference(image_url, image, min_score):
     )
     # return file
 
-    return upload_result["url"]
+    return upload_result["url"], v.get_image()
 
 
 title = " fi ber detec tion Model "
@@ -204,7 +205,11 @@ gr.Interface(
      gr.Slider(minimum=0.0, maximum=1.0, value=0.01, label="Minimum score"),
     ], 
     gr.Text(label="Data"),
+
     title=title,
     description=description,
     article=article,
-    examples=[]).launch()
+
+    examples=[]
+      outputs=["image", "text"],
+).launch()