Spaces:
Running
Running
| 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 findCosineDistance(source_representation, test_representation): | |
| a = np.matmul(np.transpose(source_representation), test_representation) | |
| b = np.sum(np.multiply(source_representation, source_representation)) | |
| c = np.sum(np.multiply(test_representation, test_representation)) | |
| return 1 - (a / (np.sqrt(b) * np.sqrt(c))) | |
| 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 |