Adapted Hatef example

notebooks/Extract_ArcFace_from_MOBIO.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "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": 5,
+   "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\n",
+    "memory_demanding = True\n",
+    "dask_client = None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from bob.bio.face.embeddings.mxnet import arcface_insightFace_lresnet100\n",
+    "pipeline = arcface_insightFace_lresnet100(annotation_type=annotation_type,\n",
+    "                                          fixed_positions=fixed_positions,\n",
+    "                                          memory_demanding=memory_demanding)\n",
+    "transformer = pipeline.transformer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Pipeline(steps=[('ToDaskBag', ToDaskBag()),\n",
+      "                ('samplewrapper-1',\n",
+      "                 DaskWrapper(estimator=CheckpointWrapper(estimator=SampleWrapper(estimator=FaceCrop(annotator=BobIpMTCNN(),\n",
+      "                                                                                                    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",
+      "                                                         features_dir='featur...\n",
+      "                                                         save_func=<function save at 0x7f345a1224d0>))),\n",
+      "                ('samplewrapper-2',\n",
+      "                 DaskWrapper(estimator=CheckpointWrapper(estimator=SampleWrapper(estimator=ArcFaceInsightFace_LResNet100(memory_demanding=True),\n",
+      "                                                                                 fit_extra_arguments=(),\n",
+      "                                                                                 transform_extra_arguments=()),\n",
+      "                                                         features_dir='features/samplewrapper-2',\n",
+      "                                                         load_func=<function load at 0x7f345a122320>,\n",
+      "                                                         save_func=<function save at 0x7f345a1224d0>)))])\n"
+     ]
+    }
+   ],
+   "source": [
+    "from bob.pipelines import wrap\n",
+    "\n",
+    "\n",
+    "features_dir = \"features\" #Path to store extracted features\n",
+    "# Wrapping with CHECKPOINT and DASK\n",
+    "transformer = wrap([\"checkpoint\",\"dask\"],\n",
+    "                   transformer,\n",
+    "                   features_dir=features_dir)\n",
+    "\n",
+    "# Printing the setup of the transformer\n",
+    "print(transformer)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "As an example, we consider 10 samples from this database and extract features for these samples:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get 10 samples from database\n",
+    "samples = database.all_samples()[:10]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Setting the DASK client\n",
+    "# HERE MAKE ABSOLUTELLY SURE THAT YOU DO `SETSHELL grid` \n",
+    "# BEFORE STARTING THE NOTEBOOK\n",
+    "\n",
+    "from dask.distributed import Client\n",
+    "from bob.pipelines.distributed.sge import SGEMultipleQueuesCluster\n",
+    "\n",
+    "cluster = SGEMultipleQueuesCluster(min_jobs=1)\n",
+    "dask_client = Client(cluster)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "features = transformer.transform(samples)\n",
+    "if dask_client is not None:\n",
+    "    features = features.compute(scheduler=dask_client)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "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": 17,
+   "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": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[[ 0.5345935 , -1.0668839 , -0.62798595, ..., -0.78859204,\n",
+       "         -0.5147211 ,  2.1415784 ]],\n",
+       "\n",
+       "       [[ 0.24587776, -1.1436105 , -0.21513344, ..., -0.4950465 ,\n",
+       "         -0.7586405 ,  1.9262394 ]],\n",
+       "\n",
+       "       [[-0.01235329, -1.0903177 , -0.7307515 , ..., -1.5341333 ,\n",
+       "         -0.9396954 ,  1.8103021 ]],\n",
+       "\n",
+       "       ...,\n",
+       "\n",
+       "       [[ 0.46007535, -0.9715014 , -0.52703196, ..., -0.29170716,\n",
+       "         -0.74297565,  1.8094344 ]],\n",
+       "\n",
+       "       [[ 0.6113469 , -1.1828535 , -0.19491309, ..., -0.22889124,\n",
+       "         -0.58382076,  2.185493  ]],\n",
+       "\n",
+       "       [[ 0.71980965, -0.4669612 , -0.49327967, ...,  0.0910981 ,\n",
+       "         -0.65268064,  0.93472594]]], dtype=float32)"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "np_features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "tornado.application - ERROR - Exception in callback functools.partial(<function TCPServer._handle_connection.<locals>.<lambda> at 0x7f3470e7c8c0>, <Task finished coro=<BaseTCPListener._handle_stream() done, defined at /idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py:445> exception=ValueError('invalid operation on non-started TCPListener')>)\n",
+      "Traceback (most recent call last):\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/tornado/ioloop.py\", line 743, in _run_callback\n",
+      "    ret = callback()\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/tornado/tcpserver.py\", line 327, in <lambda>\n",
+      "    gen.convert_yielded(future), lambda f: f.result()\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py\", line 451, in _handle_stream\n",
+      "    logger.debug(\"Incoming connection from %r to %r\", address, self.contact_address)\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py\", line 486, in contact_address\n",
+      "    host, port = self.get_host_port()\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py\", line 467, in get_host_port\n",
+      "    self._check_started()\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py\", line 443, in _check_started\n",
+      "    raise ValueError(\"invalid operation on non-started TCPListener\")\n",
+      "ValueError: invalid operation on non-started TCPListener\n",
+      "tornado.application - ERROR - Exception in callback functools.partial(<function TCPServer._handle_connection.<locals>.<lambda> at 0x7f3470e7ce60>, <Task finished coro=<BaseTCPListener._handle_stream() done, defined at /idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py:445> exception=ValueError('invalid operation on non-started TCPListener')>)\n",
+      "Traceback (most recent call last):\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/tornado/ioloop.py\", line 743, in _run_callback\n",
+      "    ret = callback()\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/tornado/tcpserver.py\", line 327, in <lambda>\n",
+      "    gen.convert_yielded(future), lambda f: f.result()\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py\", line 451, in _handle_stream\n",
+      "    logger.debug(\"Incoming connection from %r to %r\", address, self.contact_address)\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py\", line 486, in contact_address\n",
+      "    host, port = self.get_host_port()\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py\", line 467, in get_host_port\n",
+      "    self._check_started()\n",
+      "  File \"/idiap/user/tpereira/conda/envs/bob.nightlies/lib/python3.7/site-packages/distributed/comm/tcp.py\", line 443, in _check_started\n",
+      "    raise ValueError(\"invalid operation on non-started TCPListener\")\n",
+      "ValueError: invalid operation on non-started TCPListener\n"
+     ]
+    }
+   ],
+   "source": [
+    "# KILL THE SGE WORKERS\n",
+    "dask_client.shutdown()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}