+ notebook: Extract_ArcFace_from_MOBIO

notebooks/Extract_ArcFace_from_MOBIO.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "54da1cf9",
+   "metadata": {},
+   "source": [
+    "# Extracting embedding features from face data\n",
+    "In this notebook, we aim to extract embedding features from images using face recogntion extractors.\n",
+    "As an example, we use MOBIO dataset, and extract Arcface features from the face images:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3e7ff891",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##### CHANGE YOUR DATABASE HERE\n",
+    "from bob.bio.face.config.database.mobio_male import database\n",
+    "annotation_type = database.annotation_type\n",
+    "fixed_positions = database.fixed_positions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a5fba83d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from bob.bio.face.config.baseline.arcface_insightface import load\n",
+    "pipeline = load(annotation_type, fixed_positions) #pre-process and feature extraction pipeline\n",
+    "transformer = pipeline.transformer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4d610eb0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CheckpointWrapper(estimator=Pipeline(steps=[('samplewrapper-1',\n",
+      "                                             SampleWrapper(estimator=FaceCrop(cropped_image_size=(112,\n",
+      "                                                                                                  112),\n",
+      "                                                                              cropped_positions={'leye': (55,\n",
+      "                                                                                                          81),\n",
+      "                                                                                                 'reye': (55,\n",
+      "                                                                                                          42)}),\n",
+      "                                                           fit_extra_arguments=(),\n",
+      "                                                           transform_extra_arguments=(('annotations',\n",
+      "                                                                                       'annotations'),))),\n",
+      "                                            ('samplewrapper-2',\n",
+      "                                             SampleWrapper(estimator=ArcFaceInsightFace(),\n",
+      "                                                           fit_extra_arguments=(),\n",
+      "                                                           transform_extra_arguments=()))]),\n",
+      "                  features_dir='features',\n",
+      "                  load_func=<function load at 0x7f5c5424d4c0>,\n",
+      "                  save_func=<function save at 0x7f5c5424d670>)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import bob.pipelines\n",
+    "\n",
+    "features_dir = \"features\" #Path to store extracted features\n",
+    "transformer = bob.pipelines.CheckpointWrapper(transformer, features_dir=features_dir)\n",
+    "\n",
+    "# Printing the setup of the transformer\n",
+    "print(transformer)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7ea60d56",
+   "metadata": {},
+   "source": [
+    "As an example, we consider 10 samples from this database and extract features for these samples:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "bb65175a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get 10 samples from database\n",
+    "samples = database.all_samples()[:10]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "aee7754f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "features = transformer.transform(samples)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bb27ce2a",
+   "metadata": {},
+   "source": [
+    "In the following cells, we convert the extracted features to `numpy.array` and check the size of features."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "a0a9efe1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from bob.pipelines import SampleBatch\n",
+    "\n",
+    "np_features = np.array(SampleBatch(features))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "92971828",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(10, 512)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "np_features.shape"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}