Create app.py

app.py

@@ -0,0 +1,144 @@
+import gradio as gr
+import torch
+import numpy as np
+import cv2
+import json
+from VisionGauge.models import VisionGauge
+
+model = VisionGauge()
+
+def VisionGauge_Inference(imagem):
+    if imagem is None:
+        return None, "No image received."
+
+    frame_rgb = imagem.copy()
+
+    # Resize
+    target_width = 640 
+    h, w = frame_rgb.shape[:2]
+    scale = target_width / w
+    new_h = int(h * scale)
+    frame_rgb = cv2.resize(frame_rgb, (target_width, new_h))
+
+    # Convert to tensor
+    img_tensor = (
+        torch.from_numpy(frame_rgb)
+        .permute(2, 0, 1)
+        .float()
+        .unsqueeze(0)
+    )
+
+    # Model inference
+    boxes, preds = model.predict(img_tensor)
+    boxes = boxes[0]
+    preds = preds[0]
+
+    # Annotate frame
+    frame_bgr = cv2.cvtColor(frame_rgb, cv2.COLOR_RGB2BGR)
+    annotated_bgr = model.annotate_frame(
+        frame_bgr,
+        boxes,
+        preds.squeeze(-1),
+        frame_color="#551bb3",
+        font_color="#ffffff",
+        fontsize=10,
+        frame_thickness=4,
+    )
+    annotated_rgb = cv2.cvtColor(annotated_bgr, cv2.COLOR_BGR2RGB)
+
+    # Prepare JSON results
+    resultados = {}  # dictionary to store boxes indexed by ID
+
+    for i in range(boxes.shape[0]):
+        x1, y1, x2, y2 = boxes[i].int().tolist()
+
+        # Skip invalid boxes
+        if x1 == y1 == x2 == y2 == 0:
+            continue
+
+        pred = preds[i].item()
+
+        resultados[str(i)] = {
+            "coords": {
+                "x1": x1,
+                "y1": y1,
+                "x2": x2,
+                "y2": y2
+            },
+            "h_p": round(pred, 2)
+        }
+
+    # If no objects detected, return empty image dictionary
+    if not resultados:
+        resultado_json = json.dumps({"values": {}}, indent=2)
+    else:
+        resultado_json = json.dumps({"values": resultados}, indent=2)
+
+    return annotated_rgb, resultado_json
+
+
+def update_mode(mode):
+    if mode == "Image":
+        return (
+            gr.update(visible=True),
+            gr.update(visible=False),
+            gr.update(visible=True),
+        )
+    else:
+        return (
+            gr.update(visible=False),
+            gr.update(visible=True),
+            gr.update(visible=False),
+        )
+
+
+with gr.Blocks() as demo:
+
+    gr.Markdown("# VisionGauge Demo")
+
+    mode_selector = gr.Radio(
+        ["Image", "Live Capture"],
+        value="Image",
+        label="Select Input Mode"
+    )
+
+    input_img = gr.Image(
+        sources=["upload"],
+        type="numpy",
+        visible=True, webcam_options=gr.WebcamOptions(mirror=False)
+    )
+
+    webcam_img = gr.Image(
+        sources=["webcam"],
+        type="numpy",
+        streaming=True,
+        visible=False, webcam_options=gr.WebcamOptions(mirror=False),
+    )
+
+    output_img = gr.Image(label="Result")
+    output_txt = gr.Textbox(label="Predictions", show_label=True, buttons=["copy"])
+
+    btn = gr.Button("Run model", visible=True)
+
+    # Update interface when changing mode
+    mode_selector.change(
+        update_mode,
+        inputs=mode_selector,
+        outputs=[input_img, webcam_img, btn]
+    )
+    
+    # IMAGE mode (button)
+    btn.click(
+        VisionGauge_Inference,
+        inputs=input_img,
+        outputs=[output_img, output_txt]
+    )
+    
+    # LIVE mode (automatic stream)
+    webcam_img.stream(
+        VisionGauge_Inference,
+        inputs=webcam_img,
+        outputs=[output_img, output_txt],
+    )
+
+demo.launch(share=True)