Initial commit.

Former-commit-id: f32e2c9

.gitignore

@@ -0,0 +1,216 @@
+# Created by .ignore support plugin (hsz.mobi)
+### macOS template
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+### Example user template template
+### Example user template
+
+# IntelliJ project files
+.idea
+*.iml
+out
+gen### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+### VirtualEnv template
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+.Python
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+.venv
+pip-selfcheck.json
+
+# Ignore Data
+data

arsfutura-face-similarity/collect_face_images.py

@@ -0,0 +1,39 @@
+import os
+import cv2
+import argparse
+
+
+def main(directory, name, test):
+    cap = cv2.VideoCapture(0)
+
+    i = 0
+    while True:
+        # Capture frame-by-frame
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+
+        # Display the resulting frame
+        cv2.imshow(name, frame)
+        if not test and i != 0 and i % 10 == 0:
+            cv2.imwrite("{}/{}{}.png".format(directory, name, i / 10), frame)
+        i += 1
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    # When everything done, release the captureq
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--person', required=True)
+    parser.add_argument('--test', action='store_true')
+    args = parser.parse_args()
+    directory = 'images/{}'.format(args.person)
+    if not args.test and not os.path.exists(directory):
+        os.mkdir(directory)
+    try:
+        main(directory, args.person, args.test)
+    except KeyboardInterrupt:
+        print "Photo session done for {} :)".format(args.person)

arsfutura-face-similarity/constants.py

@@ -0,0 +1,2 @@
+DATA_PATH = 'data/features/'
+MODEL_PATH = 'models/model.pkl'

arsfutura-face-similarity/dataset.py

@@ -0,0 +1,15 @@
+import pandas as pd
+from constants import DATA_PATH
+
+EMBEDDINGS_PATH = DATA_PATH + 'reps.csv'
+LABELS_PATH = DATA_PATH + 'labels.csv'
+
+
+def load_data():
+    embeddings = pd.read_csv(EMBEDDINGS_PATH, header=None).values
+    labels = map(lambda label: label.split('/')[-2].upper(), pd.read_csv(LABELS_PATH, header=None).values[:, 1].tolist())
+    return embeddings, labels
+
+
+if __name__ == '__main__':
+    print load_data()

arsfutura-face-similarity/predict.py

@@ -0,0 +1,45 @@
+import openface
+import cv2
+import pickle
+import numpy as np
+from collections import namedtuple
+from constants import MODEL_PATH
+
+Face = namedtuple('Face', 'bb identity probability')
+
+align = openface.AlignDlib('models/shape_predictor_68_face_landmarks.dat')
+net = openface.TorchNeuralNet('models/nn4.small2.v1.t7', imgDim=96, cuda=False)
+le, model = pickle.load(open(MODEL_PATH, 'rb'))
+
+
+def faces_embeddings_and_bbs(img):
+    rgb_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    bb = align.getAllFaceBoundingBoxes(rgb_img)
+
+    aligned_faces = []
+    for box in bb:
+        aligned_faces.append(
+            align.align(
+                96,
+                rgb_img,
+                box,
+                landmarkIndices=openface.AlignDlib.OUTER_EYES_AND_NOSE))
+
+    embeddings = np.array([net.forward(alignedFace) for alignedFace in aligned_faces])
+
+    return embeddings, bb
+
+
+def predict(img):
+    embeddings, bb = faces_embeddings_and_bbs(img)
+    if embeddings.size == 0 or not bb:
+        return None
+    probs = model.predict_proba(embeddings)
+    predicted = probs.argmax(axis=1)
+    identities = le.inverse_transform(predicted)
+    probs = probs[np.arange(len(predicted)), predicted]
+    return [Face(box, identity, prob * 100) for identity, box, prob in zip(identities, bb, probs)]
+
+
+if __name__ == '__main__':
+    predict('')

arsfutura-face-similarity/real_time_face_detection.py

@@ -0,0 +1,33 @@
+from __future__ import print_function, division
+
+import cv2
+from predict import predict
+
+
+def main():
+    cap = cv2.VideoCapture(0)
+
+    while True:
+        # Capture frame-by-frame
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+
+        faces = predict(frame)
+        if faces is not None:
+            for face in faces:
+                cv2.rectangle(frame, (face.bb.left(), face.bb.top()), (face.bb.right(), face.bb.bottom()), (0, 255, 0), 2)
+                cv2.putText(frame, "%s %.2f%%" % (face.identity, face.probability),
+                            (face.bb.left(), face.bb.bottom() + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, (255, 255, 255), 1)
+
+        # Display the resulting frame
+        cv2.imshow('frame', frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    # When everything done, release the captureq
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+if __name__ == '__main__':
+    main()

arsfutura-face-similarity/train.py

@@ -0,0 +1,42 @@
+import pickle
+from sklearn.model_selection import GridSearchCV
+from sklearn.svm import SVC
+from sklearn.linear_model import LogisticRegression
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import classification_report
+from dataset import load_data
+from constants import MODEL_PATH
+from sklearn.ensemble import RandomForestClassifier
+
+CLASSIFIERS = {
+    'svm': (
+        SVC(decision_function_shape='ovr'),
+        [
+            {'C': [0.001, 0.1, 1, 10, 100, 1000], 'kernel': ['linear']},
+            {'C': [0.001, 0.1, 1, 10, 100, 1000], 'gamma': [100, 50, 10, 1, 0.01, 0.001, 0.0001], 'kernel': ['rbf']}
+        ]
+    ),
+    'logreg': (
+        LogisticRegression(max_iter=100000),
+        {'C': [0.001, 0.1, 1, 10, 100, 1000]}
+    )
+}
+
+
+def main():
+    X, y = load_data()
+    le = LabelEncoder()
+    le.fit(y)
+
+    classifier = CLASSIFIERS['logreg']
+
+    clf = GridSearchCV(classifier[0], classifier[1], cv=5, verbose=1)
+    clf.fit(X, le.transform(y))
+
+    print clf.best_params_
+    print classification_report(le.transform(y), clf.predict(X), target_names=le.classes_)
+    pickle.dump((le, clf), open(MODEL_PATH, 'wb'))
+
+
+if __name__ == '__main__':
+    main()