initial commit

.deepface/weights/facenet512_weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f76b5117a9ca574d536af8199e6720089eb4ad3dc7e93534496d88265de864f
+size 94955648

.deepface/weights/retinaface.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb2393a89da3dd3d6796ad86660e298f62a0c8ae7578d92eb6af14e0bb93adf
+size 118667368

.gitattributes

@@ -31,3 +31,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+venv
+flagged

app.py

@@ -0,0 +1,79 @@
+import os
+import json
+
+print(os.path.dirname(__file__))
+os.environ["DEEPFACE_HOME"] = os.path.dirname(__file__)
+
+import pyzipper
+import numpy as np
+import gradio as gr
+from annoy import AnnoyIndex
+from deepface.commons import functions
+from deepface.basemodels import Facenet512
+
+
+# load the face model
+model = Facenet512.loadModel()
+
+input_shape_x, input_shape_y = functions.find_input_shape(model)
+
+index = AnnoyIndex(512, "euclidean")
+index.load(f"face.db")
+
+ANNOY_INDEX = json.load(open(f"face.json"))
+
+with pyzipper.AESZipFile('persons.zip') as zf:
+    zf.setpassword(b"4321ecafhsats"[::-1])
+    PERFORMER_DB = json.loads(zf.read('performers.json'))
+
+
+def predict(image, threshold=20.0, results=3):
+    image_array = np.array(image)
+
+    img = functions.preprocess_face(
+        img=image_array,
+        target_size=(input_shape_x, input_shape_y),
+        enforce_detection=True,
+        detector_backend="retinaface",
+        align=True,
+    )
+
+    img = functions.normalize_input(img, normalization="Facenet2018")
+    face = model.predict(img)[0].tolist()
+    ids, distances = index.get_nns_by_vector(
+        face, 50, search_k=10000, include_distances=True
+    )
+
+    persons = {}
+    for p, distance in zip(ids, distances):
+        id = ANNOY_INDEX[p]
+        if id in persons:
+            persons[id]["hits"] += 1
+            persons[id]["distance"] -= 0.5
+            continue
+
+        persons[id] = {
+            "id": id,
+            "distance": round(distance, 2),
+            "hits": 1,
+        }
+
+        if id in PERFORMER_DB:
+            persons[id].update(PERFORMER_DB.get(id))
+
+    persons = sorted(persons.values(), key=lambda x: x["distance"])
+    persons = [p for p in persons if p["distance"] < threshold]
+    return persons[:results]
+
+
+gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.components.Image(),
+        gr.components.Slider(label="threshold",minimum=0.0, maximum=30.0, value=20.0),
+        gr.components.Slider(label="results", minimum=0, maximum=10, value=3),
+    ],
+    outputs=gr.outputs.JSON(label=""),
+    title="Who is in the photo?",
+    description="Upload an image of a person and we'll tell you who it is.",
+).launch(enable_queue=True)

face.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e73f162347245f8d4267ac2a4f2788b77d0910185b505152fceca0320a840b84
+size 399631680

persons.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af1307a506a612e7d61bdaad3e40c6cb348c1420166628044309bc55d4376fa
+size 2530170

requirements.txt

@@ -0,0 +1,4 @@
+annoy==1.17.1
+deepface==0.0.75
+pyzipper
+gradio