Create app.py

app.py

@@ -0,0 +1,260 @@
+import gradio as gr
+import cv2
+import numpy as np
+from pathlib import Path
+from ultralytics import YOLO
+
+# ── Constants ─────────────────────────────────────────────────────────────────
+MODEL_PATH = "yolov8_cattle_keypoints.pt"
+
+KP_NAMES = [
+    "left_ear_tip", "right_ear_tip", "left_ear_base", "right_ear_base",
+    "left_eye", "right_eye", "nose_left", "nose_right", "nose_tip",
+    "mouth_left", "mouth_right", "chin_left", "chin_right",
+]
+
+KP_COLORS = [
+    (255,  69,   0),
+    ( 30, 144, 255),
+    (255, 165,   0),
+    (  0, 191, 255),
+    (154, 205,  50),
+    (238, 130, 238),
+    (  0, 255, 127),
+    (255, 215,   0),
+    (255, 255,   0),
+    (255,  20, 147),
+    (  0, 255, 255),
+    (255, 140,   0),
+    (147, 112, 219),
+]
+
+SKELETON = [
+    (0, 2), (1, 3),
+    (2, 4), (3, 5),
+    (4, 5),
+    (6, 8), (7, 8),
+    (6, 9), (7, 10),
+    (9, 10),
+    (9, 11), (10, 12),
+    (11, 12),
+    (4, 6), (5, 7),
+]
+
+# ── Model loading ─────────────────────────────────────────────────────────────
+_model = None
+
+def load_model():
+    global _model
+    if _model is None:
+        if not Path(MODEL_PATH).exists():
+            raise FileNotFoundError(
+                f"Model file '{MODEL_PATH}' not found. "
+                "Upload yolov8_cattle_keypoints.pt to the Space root."
+            )
+        _model = YOLO(MODEL_PATH)
+    return _model
+
+
+# ── Inference ─────────────────────────────────────────────────────────────────
+def run_inference(image: np.ndarray, conf_threshold: float, show_labels: bool):
+    if image is None:
+        return None, "Upload an image first."
+
+    m = load_model()
+    results = m.predict(source=image, conf=float(conf_threshold), verbose=False)
+
+    annotated  = image.copy()
+    table_rows = []
+
+    for result in results:
+        boxes          = result.boxes
+        keypoints_data = result.keypoints
+        if boxes is None or keypoints_data is None or len(boxes) == 0:
+            continue
+
+        for det_idx in range(len(boxes)):
+            conf = float(boxes.conf[det_idx])
+            kps  = keypoints_data.data[det_idx].cpu().numpy()  # (13, 3)
+
+            # Bounding box
+            x1, y1, x2, y2 = boxes.xyxy[det_idx].cpu().numpy().astype(int)
+            cv2.rectangle(annotated, (x1, y1), (x2, y2), (255, 255, 255), 2)
+            cv2.putText(
+                annotated, f"cattle {conf:.2f}",
+                (x1, max(y1 - 8, 0)),
+                cv2.FONT_HERSHEY_SIMPLEX, 0.55, (255, 255, 255), 1, cv2.LINE_AA,
+            )
+
+            # Skeleton
+            for (i, j) in SKELETON:
+                if i >= len(kps) or j >= len(kps):
+                    continue
+                xi, yi, vi = kps[i]
+                xj, yj, vj = kps[j]
+                if vi < 0.5 or vj < 0.5:
+                    continue
+                cv2.line(
+                    annotated,
+                    (int(xi), int(yi)), (int(xj), int(yj)),
+                    (180, 180, 180), 1, cv2.LINE_AA,
+                )
+
+            # Keypoints
+            row = {"detection": det_idx + 1, "confidence": f"{conf:.3f}"}
+            for kp_idx, (kx, ky, kv) in enumerate(kps):
+                name  = KP_NAMES[kp_idx]
+                color = KP_COLORS[kp_idx]
+                if kv > 0.5:
+                    cv2.circle(annotated, (int(kx), int(ky)), 6, color, -1)
+                    cv2.circle(annotated, (int(kx), int(ky)), 7, (0, 0, 0), 1)
+                    if show_labels:
+                        cv2.putText(
+                            annotated, name,
+                            (int(kx) + 8, int(ky) - 4),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.38,
+                            color, 1, cv2.LINE_AA,
+                        )
+                    row[name] = f"({int(kx)}, {int(ky)})  vis={kv:.2f}"
+                else:
+                    row[name] = "not visible"
+
+            table_rows.append(row)
+
+    if table_rows:
+        lines = [f"### {len(table_rows)} detection(s) found\n"]
+        for row in table_rows:
+            lines.append(f"**Detection {row['detection']}** — conf {row['confidence']}")
+            for name in KP_NAMES:
+                lines.append(f"  - `{name}`: {row.get(name, 'n/a')}")
+            lines.append("")
+        results_md = "\n".join(lines)
+    else:
+        results_md = "### No cattle detected\nTry lowering the confidence threshold."
+
+    return annotated, results_md
+
+
+# ── CSS ────────────────────────────────────────────────────────────────���──────
+CSS = """
+@import url('https://fonts.googleapis.com/css2?family=Bebas+Neue&family=DM+Mono:wght@400;500&family=DM+Sans:wght@300;400;500&display=swap');
+
+:root {
+    --bg:      #0d0f0e;
+    --surface: #161a18;
+    --border:  #2a332e;
+    --accent:  #4ffe9a;
+    --muted:   #7a8c80;
+    --text:    #e8ede9;
+    --radius:  4px;
+}
+body, .gradio-container {
+    background: var(--bg) !important;
+    font-family: 'DM Sans', sans-serif !important;
+    color: var(--text) !important;
+}
+.hdr {
+    padding: 2.5rem 0 1.5rem;
+    text-align: center;
+    border-bottom: 1px solid var(--border);
+    margin-bottom: 2rem;
+}
+.hdr h1 {
+    font-family: 'Bebas Neue', sans-serif;
+    font-size: clamp(2.8rem, 7vw, 5.5rem);
+    letter-spacing: 0.08em;
+    color: var(--accent);
+    margin: 0;
+    line-height: 1;
+    text-shadow: 0 0 40px rgba(79,254,154,0.25);
+}
+.hdr p {
+    font-family: 'DM Mono', monospace;
+    font-size: 0.78rem;
+    color: var(--muted);
+    letter-spacing: 0.15em;
+    text-transform: uppercase;
+    margin: 0.6rem 0 0;
+}
+.tags {
+    display: flex; gap: 0.5rem; flex-wrap: wrap;
+    justify-content: center; margin-top: 0.8rem;
+}
+.tag {
+    font-family: 'DM Mono', monospace;
+    font-size: 0.68rem; letter-spacing: 0.1em;
+    text-transform: uppercase; padding: 0.25rem 0.65rem;
+    border: 1px solid var(--border); border-radius: 2px; color: var(--muted);
+}
+.tag.hot { border-color: var(--accent); color: var(--accent); }
+button.primary {
+    background: var(--accent) !important;
+    color: #0d0f0e !important;
+    font-family: 'Bebas Neue', sans-serif !important;
+    font-size: 1.1rem !important;
+    letter-spacing: 0.12em !important;
+    border: none !important;
+    border-radius: var(--radius) !important;
+    padding: 0.7rem 2rem !important;
+    transition: opacity 0.15s, transform 0.1s !important;
+}
+button.primary:hover { opacity: 0.85 !important; transform: translateY(-1px) !important; }
+input[type=range]    { accent-color: var(--accent) !important; }
+input[type=checkbox] { accent-color: var(--accent) !important; }
+"""
+
+HEADER_HTML = """
+<div class="hdr">
+  <h1>CattleFace · Pose</h1>
+  <p>YOLOv8 · 13-point facial landmark detection for bovines</p>
+  <div class="tags">
+    <span class="tag hot">13 keypoints</span>
+    <span class="tag">ears · eyes · nose · mouth · chin</span>
+    <span class="tag hot">real-time inference</span>
+    <span class="tag">UARK-AICV benchmark</span>
+  </div>
+</div>
+"""
+
+FOOTER_HTML = """
+<div style="text-align:center;padding:1.5rem 0 0.5rem;
+            font-family:'DM Mono',monospace;font-size:0.7rem;
+            color:#7a8c80;letter-spacing:0.08em;">
+  MODEL · YOLOv8s-pose &nbsp;|&nbsp;
+  DATASET · UARK-AICV/CattleFace-RGBT-benchmark &nbsp;|&nbsp;
+  13 FACIAL LANDMARKS
+</div>
+"""
+
+# ── Layout ────────────────────────────────────────────────────────────────────
+with gr.Blocks(title="CattleFace Pose") as demo:
+    gr.HTML(HEADER_HTML)
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            inp_image = gr.Image(
+                label="Input Image",
+                type="numpy",
+                sources=["upload", "webcam", "clipboard"],
+            )
+            conf_slider = gr.Slider(
+                minimum=0.05, maximum=0.95, value=0.25, step=0.05,
+                label="Confidence Threshold",
+            )
+            show_labels = gr.Checkbox(value=True, label="Show keypoint labels")
+            run_btn = gr.Button("Detect Landmarks", variant="primary")
+
+        with gr.Column(scale=1):
+            out_image = gr.Image(label="Annotated Output", type="numpy")
+            out_text  = gr.Markdown(label="Keypoint Details")
+
+    run_btn.click(
+        fn=run_inference,
+        inputs=[inp_image, conf_slider, show_labels],
+        outputs=[out_image, out_text],
+    )
+
+    gr.HTML(FOOTER_HTML)
+
+if __name__ == "__main__":
+    demo.launch(css=CSS)