def eval_on_biwi(store_file, results_fol, store_each=20, overwrite=False):
config.load_config()
config.CONFIG["STORAGE"]["database_file"] = store_file
aux_info = load_identities()
face_rec = recognition.Recognition()
dataset = BiwiDataset()
cached_results = len(os.listdir(results_fol))
start = int(store_each*cached_results)
results = {
"is_same": [],
"score": [],
"label": [],
"roll": [],
"yaw": [],
"pitch": [],
}
# Eval
for ctr, (iden, frame) in itertools.islice(enumerate(dataset), start, None):
image_path, (center3D, angle) = dataset[iden, frame]
image = cv2.imread(image_path)
faces = face_rec.recognize(image) # type: typing.List[datum.Datum]
match = match_detection(faces, (center3D, angle))
if match is None:
results["score"].append(1.0)
results["is_same"].append(False)
else:
results["score"].append(faces[match].match_score)
results["is_same"].append(
faces[match].identity == aux_info.iden[iden - 1]
)
results["label"].append(iden)
results["roll"].append(angle[0])
results["pitch"].append(angle[1])
results["yaw"].append(angle[2])
if ctr % 10 == 9:
print(
"\rImages processed: {}/~14000. Current folder: {}.".format(ctr, iden),
end="",
)
if ctr % store_each == store_each - 1:
df = pd.DataFrame(results)
df.to_pickle(path.join(results_fol, "results_{}.pkl".format(ctr)))
results = {
"is_same": [],
"score": [],
"label": [],
"roll": [],
"yaw": [],
"pitch": [],
}
df = pd.DataFrame(results)
df.to_pickle(path.join(results_fol, "results_END.pkl"))
def main(
flw_dir=LFW_ROOT + "flw_mtcnnpy_160",
pairs_filename=LFW_ROOT + "pairs.txt",
store_file="/home/sam/Desktop/face.pkl",
store=1,
):
if store == 2:
with open(store_file) as f:
embedding_list, y_true = pickle.load(f)
y_true = y_true.flatten()
else:
config.load_config()
encoder = encoding.FacialEncoder()
# encoder = encoding_arc.EncodingArc()
embedding_list = []
y_true = []
for (path0,
path1), issame in lfw_utils.get_paths(flw_dir, pairs_filename):
im0 = cv2.imread(path0)
im1 = cv2.imread(path1)
embs = encoder.predict([im0, im1])
embedding_list.append(embs)
y_true.append(issame)
embedding_list = np.vstack(embedding_list)
y_true = np.array(y_true)
if store == 1:
with open(store_file, "wb") as f:
pickle.dump((embedding_list, y_true), f)
tpr, fpr, accuracy, val, val_std, far = lfw_utils.evaluate(
embedding_list, y_true)
print("Accuracy: %2.5f+-%2.5f" % (np.mean(accuracy), np.std(accuracy)))
print("Validation rate: %2.5f+-%2.5f @ FAR=%2.5f" % (val, val_std, far))
auc = metrics.auc(fpr, tpr)
print("Area Under Curve (AUC): %1.3f" % auc)
eer = optimize.brentq(
lambda x: 1.0 - x - interpolate.interp1d(fpr, tpr)(x), 0.0, 1.0)
print("Equal Error Rate (EER): %1.3f" % eer)
def create_faces_dataset(in_dir, out_dir=None, out_file="database.pkl"):
# Path fixing
if out_dir is None:
out_dir = in_dir
if not os.path.exists(out_dir):
os.mkdir(out_dir)
# Processing pipeline
config.load_config()
config.logger_config()
det = detection.FacialDetector()
enc = encoding_arc.EncodingArc()
labels = []
embeddigs = []
for label, file_list in files.image_folder_traversal(in_dir):
logging.info("Adding {} to database".format(label))
for file_name in file_list:
image = cv2.imread(file_name)
if image is None:
continue
try:
# image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
faces = det.extract_images(image)
embedding = enc.predict(faces)
if embedding.shape[0] > 1:
logging.warn(
"Multiple faces in image image {}".format(file_name))
continue
except Exception as e:
logging.warn("Error in image {}".format(file_name))
logging.warn(e.message)
# os.remove(file_name)
# logging.warn("File {} deleted.".format(file_name))
else:
logging.debug("Image added: {}".format(file_name))
labels.append(label)
embeddigs.append(embedding[0])
df = pd.DataFrame({"identities": labels, "embeddings": embeddigs})
out_path = os.path.join(out_dir, out_file)
df.to_pickle(out_path)
logging.info("Face embeddings saved to {}".format(out_path))
def create_biwi_db(out_path):
dataset = BiwiDataset()
# Processing pipeline
config.load_config()
# config.logger_config()
detector = detection.FacialDetector()
encoder = encoding_arc.EncodingArc()
labels = []
embeddings = []
aux_info = load_identities()
# Create faces database (MIN_ANGLES)
for idx in range(len(aux_info)):
label = aux_info.iden[idx]
if label in labels:
continue
iden = aux_info.folder[idx]
frame = aux_info.center_frame[idx]
im_path, (center3D, angle) = dataset[int(iden), frame]
image = cv2.imread(im_path)
data = detector.predict(image, extract_image=True)
face_match = match_detection(data, (center3D, angle))
embedding = encoder.predict([data[face_match].image])
labels.append(label)
embeddings.append(embedding[0])
if idx % 5 == 4:
print("\rProgress: {}/{}".format(idx + 1, len(aux_info)), end="")
df = pd.DataFrame({"identities": labels, "embeddings": embeddings})
df.to_pickle(out_path)
print("\rProgress: {}/{}".format(idx + 1, len(aux_info)), end="")
# logging.info("Face embeddings saved to {}".format(out_path))
return df
# IMAGE_PATH = "/home/sam/Pictures/IMG-20190419-WA0001.jpg" IMAGE_PATH = "/home/sam/UMA/4/4_2/3-TFG/3-Workspace/face_recognition_ros/face_recognition_ros/data/database/family_dataset/sam/IMG_20190730_182021.jpg" image = cv2.cvtColor(cv2.imread(IMAGE_PATH, 1), cv2.COLOR_BGR2RGB) # RESOLUTION = (1280, 720) # 0.433 RESOLUTION = (640, 480) # 0.213 METHOD = "mtcnn" LOOPS = 50 image = cv2.resize(image, RESOLUTION) # plt.imshow(image) # In[3]: conf = config.load_config() detector = detection.FacialDetector(method=METHOD, conf=conf["DETECTION"]) # encoder = encoding.FacialEncoder(conf) encoder = encoding_arc.EncodingArc(conf) # matcher = default.FaceMatcher(conf) # matcher = svm.SVMMatcher(conf) # matcher = knn.KNNMatcher(conf) # In[6]: # for _ in range(LOOPS): faces = detector.extract_datum(image)
from __future__ import print_function
from scipy import misc
import sys
import os
import argparse
import numpy as np
import random
from time import sleep
import facenet
from face_recognition_ros import detection
from face_recognition_ros.utils import config
config.load_config()
def create_dataset_mtcnn(args):
sleep(random.random())
output_dir = os.path.expanduser(args.output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the log directory
# src_path, _ = os.path.split(os.path.realpath(__file__))
# facenet.store_revision_info(src_path, output_dir, " ".join(sys.argv))
dataset = facenet.get_dataset(args.input_dir)
print("Loading detector")
# Create and choose detector