app: major refactoring (add new possibility to provide both image link OR upload an image, add min score slider, fix various preprocessing issues)

app.py

@@ -4,6 +4,8 @@ except:
     import os 
     os.system('pip install git+https://github.com/facebookresearch/detectron2.git')
 
+import cv2
+
 from matplotlib.pyplot import axis
 import gradio as gr
 import requests
@@ -24,7 +26,6 @@ model_path = "https://huggingface.co/dbmdz/detectron2-model/resolve/main/model_f
 
 cfg = get_cfg()
 cfg.merge_from_file("./configs/detectron2/faster_rcnn_R_50_FPN_3x.yaml")
-cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.8
 cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
 cfg.MODEL.WEIGHTS = model_path
 
@@ -32,31 +33,41 @@ my_metadata = MetadataCatalog.get("dbmdz_coco_all")
 my_metadata.thing_classes = ["Illumination", "Illustration"]
 
 if not torch.cuda.is_available():
-    cfg.MODEL.DEVICE='cpu'
+    cfg.MODEL.DEVICE = "cpu"
 
-predictor = DefaultPredictor(cfg)
 
-def inference(image):
-    print(image.height)
+def inference(image_url, image, min_score):
+    if image_url:
+        r = requests.get(image_url)
+        if r:
+            im = np.frombuffer(r.content, dtype="uint8")
+            im = cv2.imdecode(im, cv2.IMREAD_COLOR)
+    else:
+        # Model expect BGR!
+        im = image[:,:,::-1]
 
-    height = image.height
+    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = min_score
+    predictor = DefaultPredictor(cfg)
 
-    img = np.array(image)
-    outputs = predictor(img)
+    outputs = predictor(im)
 
-    v = Visualizer(img, my_metadata, scale=1.2)
+    v = Visualizer(im, my_metadata, scale=1.2)
     out = v.draw_instance_predictions(outputs["instances"].to("cpu"))
-    
+
     return out.get_image()
 
+
 title = "DBMDZ Detectron2 Model Demo"
-description = "This demo introduces an interactive playground for our trained Detectron2 model. <br>The model was trained on manually annotated segments from digitized books to detect Illustration or Illumination segments on a given page. <br>Minimum score for classification is set to 80%."
+description = "This demo introduces an interactive playground for our trained Detectron2 model. <br>The model was trained on manually annotated segments from digitized books to detect Illustration or Illumination segments on a given page."
 article = '<p>Detectron model is available from our repository <a href="">here</a> on the Hugging Face Model Hub.</p>'
 
 gr.Interface(
-    inference, 
-    [gr.inputs.Image(type="pil", label="Input")], 
-    gr.outputs.Image(type="numpy", label="Output"),
+    inference,
+    [gr.inputs.Textbox(label="Image URL", placeholder="https://api.digitale-sammlungen.de/iiif/image/v2/bsb10483966_00008/full/500,/0/default.jpg"),
+     gr.inputs.Image(type="numpy", label="Input Image"),
+     gr.Slider(minimum=0.0, maximum=1.0, value=0.5, label="Minimum score:"),
+    ], 
+    gr.outputs.Image(type="pil", label="Output"),
     title=title,
     description=description,
     article=article,