Update app.py

app.py

@@ -1,51 +1,49 @@
 import gradio as gr
 import torch
-import yolov5
+from PIL import Image
+import json
+
 
 # Images
-torch.hub.download_url_to_file('https://i.imgur.com/4GmZXID.jpg', '1.jpg')
-torch.hub.download_url_to_file('https://i.imgur.com/ktIGRvs.jpg', '2.jpg')
-torch.hub.download_url_to_file('https://i.imgur.com/fSEsXoE.jpg', '3.jpg')
-torch.hub.download_url_to_file('https://i.imgur.com/lsVJRzd.jpg', '4.jpg')
-torch.hub.download_url_to_file('https://i.imgur.com/1OFmJd1.jpg', '5.jpg')
-torch.hub.download_url_to_file('https://i.imgur.com/GhfAWMJ.jpg', '6.jpg')
-
-def yolov5_inference(
-    image: gr.inputs.Image = None,
-    model_path: gr.inputs.Dropdown = None,
-    image_size: gr.inputs.Slider = 1280,
-    conf_threshold: gr.inputs.Slider = 0.7,
-    iou_threshold: gr.inputs.Slider = 0.45,
-):
-
-    model = torch.hub.load('yolov5', 'custom', path='plate.pt', source="local") 
-    model.conf = conf_threshold
-    model.iou = iou_threshold
-    results = model([image], size=image_size)
-    return results.render()[0]
-        
-
-inputs = [
-    gr.inputs.Image(type="pil", label="Input Image"),
-    # gr.inputs.Dropdown(["plate.pt"], label="Model"),
-    gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size"),
-    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.7, step=0.05, label="Confidence Threshold"),
-    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.7, step=0.05, label="IOU Threshold"),
-]
-
-outputs = gr.outputs.Image(type="filepath", label="Output Image")
-title = "YOLOv5"
-description = "YOLOv5 is a family of object detection models pretrained on COCO dataset. This model is a pip implementation of the original YOLOv5 model."
-
-examples = [['1.jpg', 'plate.pt', 1280, 0.7, 0.45], ['2.jpg', 'plate.pt', 1280, 0.7, 0.45], ['3.jpg', 'plate.pt', 1280, 0.7, 0.45], ['4.jpg', 'plate.pt', 1280, 0.7, 0.45], ['5.jpg', 'plate.pt', 1280, 0.7, 0.45], ['6.jpg', 'plate.pt', 1280, 0.7, 0.45]]
-demo_app = gr.Interface(
-    fn=yolov5_inference,
-    inputs=inputs,
-    outputs=outputs,
-    title=title,
-    examples=examples,
-    cache_examples=True,
-    live=True,
-    theme='huggingface',
-)
-demo_app.launch(debug=True, enable_queue=True)
+torch.hub.download_url_to_file(
+    'https://i.imgur.com/4GmZXID.jpg', '1.jpg')
+torch.hub.download_url_to_file(
+    'https://i.imgur.com/ktIGRvs.jpg', '2.jpg')
+torch.hub.download_url_to_file(
+    'https://i.imgur.com/fSEsXoE.jpg', '3.jpg')
+torch.hub.download_url_to_file(
+    'https://i.imgur.com/lsVJRzd.jpg', '4.jpg')
+torch.hub.download_url_to_file(
+    'https://i.imgur.com/1OFmJd1.jpg', '5.jpg')
+torch.hub.download_url_to_file(
+    'https://i.imgur.com/GhfAWMJ.jpg', '6.jpg')
+
+# Model
+# model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # force_reload=True to update
+model = torch.hub.load('ultralytics/yolov5', 'custom', path='plate.pt', source="local") 
+
+def yolo(im, size=1024):
+    g = (size / max(im.size))  # gain
+    im = im.resize((int(x * g) for x in im.size), Image.ANTIALIAS)  # resize
+
+    results = model(im)  # inference
+    results.render()  # updates results.imgs with boxes and labels
+
+    df = results.pandas().xyxy[0].to_json(orient="records")
+    res = json.loads(df)
+
+    return [Image.fromarray(results.imgs[0]), res]
+
+
+inputs = gr.inputs.Image(type='pil', label="Original Image")
+outputs = [gr.outputs.Image(type="pil", label="Output Image"),
+    gr.outputs.JSON(label="Output JSON")]
+
+title = "TW_plate_number"
+description = "TW_plate_number"
+# article = "<p style='text-align: center'>TW_plate_number <a href=\"http://codh.rois.ac.jp/char-shape/\">日本古典籍くずし字データセット</a>.</p>"
+
+examples = [['1.jpg'], ['2.jpg'], ['3.jpg'], ['4.jpg'], ['5.jpg'], ['6.jpg']]
+gr.Interface(yolo, inputs, outputs, title=title, description=description, examples=examples, theme="huggingface").launch(enable_queue=True) # cache_examples=True,
+
+