Added YOLO models

M-Raw.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15f95658f7423ece0c2da12a9c4378348cf5e42deb081c24839c71d4e6dd1ca
+size 52099424

N-Raw.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35531393fe68c6f8d65bfc4d7ce909f2033f106a1ea3fd37c13db9d2086fa62
+size 22557880

S-Raw.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:650137978f3688b85c43964630250da9ff479df21d52e91ba26e43334164ac3b
+size 22557944

app.py

@@ -0,0 +1,47 @@
+import numpy as np
+from PIL import Image
+import gradio as gr
+from ultralytics import YOLO
+
+# Load the YOLO model
+m_raw_model = YOLO("M-Raw.pt")
+n_raw_model = YOLO("N-Raw.pt")
+s_raw_model = YOLO("S-Raw.pt")
+
+def snap(image, model, conf):
+    # Convert the image to a numpy array
+    image = np.array(image)
+
+    # Run the selected model
+    results = None
+    if model == "M-Raw":
+        results = m_raw_model(image, conf=conf)
+    elif model == "N-Raw":
+        results = n_raw_model(image, conf=conf)
+    elif model == "S-Raw":
+        results = s_raw_model(image, conf=conf)
+
+    # Draw the bounding boxes
+    resulting_image = results.render()
+
+    # Convert the resulting image to a PIL image
+    resulting_image = Image.fromarray(resulting_image)
+
+    # Get the labels
+    labels = results.pandas().xyxy[0]["name"].values
+
+    # Sort the labels by their x-value
+    labels = labels[np.argsort(results.pandas().xyxy[0]["x"].values)]
+
+    return [resulting_image, labels]
+
+
+demo = gr.Interface(
+    snap,
+    [gr.Image(source="webcam", tool=None, streaming=True), gr.inputs.Radio(["M-Raw", "N-Raw", "S-Raw"]), gr.inputs.Slider(0.0, 1.0, 0.5, 0.1, "Confidence")],
+    ["image", "labels"],
+    title="Baybayin Instance Detection"
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+numpy
+Pillow
+ultralytics
+gradio