Create helpers.py

helpers.py

@@ -0,0 +1,85 @@
+from ultralyticsplus import YOLO
+from PIL import Image
+import numpy as np
+from tensorflow.keras.models import Model, Sequential
+from tensorflow.keras.layers import (
+    Convolution2D,
+    LocallyConnected2D,
+    MaxPooling2D,
+    Flatten,
+    Dense,
+    Dropout,
+)
+import os
+import zipfile
+import gdown
+import tensorflow as tf
+
+
+def load_detector():
+  # load model
+  model = YOLO('https://github.com/akanametov/yolov8-face/releases/download/v0.0.0/yolov8n-face.pt')
+
+  # set model parameters
+  model.overrides['conf'] = 0.25  # NMS confidence threshold
+  model.overrides['iou'] = 0.45  # NMS IoU threshold
+  model.overrides['agnostic_nms'] = False  # NMS class-agnostic
+  model.overrides['max_det'] = 50  # maximum number of detections per image
+  return model
+
+def extract_faces(model, image):
+  # perform inference
+  results = model.predict(image)
+  ids = np.array(results[0].boxes.xyxy).astype(np.int32)
+  img = Image.open(image)
+  crops = []
+  for id in ids:
+    crops.append(Image.fromarray(np.array(img)[id[1] : id[3], id[0]: id[2]]))
+  return crops
+
+def load_model(
+    url="https://github.com/swghosh/DeepFace/releases/download/weights-vggface2-2d-aligned/VGGFace2_DeepFace_weights_val-0.9034.h5.zip",
+):
+    base_model = Sequential()
+    base_model.add(
+        Convolution2D(32, (11, 11), activation="relu", name="C1", input_shape=(152, 152, 3))
+    )
+    base_model.add(MaxPooling2D(pool_size=3, strides=2, padding="same", name="M2"))
+    base_model.add(Convolution2D(16, (9, 9), activation="relu", name="C3"))
+    base_model.add(LocallyConnected2D(16, (9, 9), activation="relu", name="L4"))
+    base_model.add(LocallyConnected2D(16, (7, 7), strides=2, activation="relu", name="L5"))
+    base_model.add(LocallyConnected2D(16, (5, 5), activation="relu", name="L6"))
+    base_model.add(Flatten(name="F0"))
+    base_model.add(Dense(4096, activation="relu", name="F7"))
+    base_model.add(Dropout(rate=0.5, name="D0"))
+    base_model.add(Dense(8631, activation="softmax", name="F8"))
+
+    # ---------------------------------
+
+    home = os.getcwd()
+
+    if os.path.isfile(home + "/VGGFace2_DeepFace_weights_val-0.9034.h5") != True:
+        print("VGGFace2_DeepFace_weights_val-0.9034.h5 will be downloaded...")
+
+        output = home + "/VGGFace2_DeepFace_weights_val-0.9034.h5.zip"
+
+        gdown.download(url, output, quiet=False)
+
+        # unzip VGGFace2_DeepFace_weights_val-0.9034.h5.zip
+        with zipfile.ZipFile(output, "r") as zip_ref:
+            zip_ref.extractall(home)
+
+    base_model.load_weights(home + "/VGGFace2_DeepFace_weights_val-0.9034.h5")
+
+    # drop F8 and D0. F7 is the representation layer.
+    deepface_model = Model(inputs=base_model.layers[0].input, outputs=base_model.layers[-3].output)
+
+    return deepface_model
+
+def get_embeddings(model, imgs):
+  embeddings = []
+  for img in imgs:
+    img = np.expand_dims(np.array(img.resize((152,152))), axis = 0)
+    embedding = model.predict(img, verbose=0)[0]
+    embeddings.append(embedding)
+  return embeddings