Add chapter

Author: curiousily

02.face-detection-with-detectron2.ipynb

@@ -30,7 +30,7 @@
         "\n",
         "Historically, this was a really tough problem to solve. Tons of manual feature engineering, novel algorithms and methods were developed to improve the state-of-the-art.\n",
         "\n",
-        "These days, face detection models are included in almost every computer vision package/framework. OpenCV, for example, provides a variety of tools like the [Cascade Classifier](https://docs.opencv.org/4.2.0/db/d28/tutorial_cascade_classifier.html).\n",
+        "These days, face detection models are included in almost every computer vision package/framework. Some of the best-performing ones use Deep Learning methods. OpenCV, for example, provides a variety of tools like the [Cascade Classifier](https://docs.opencv.org/4.2.0/db/d28/tutorial_cascade_classifier.html).\n",
         "\n",
         "- [Run the complete notebook in your browser (Google Colab)](https://colab.research.google.com/drive/1Jk4-qX9zdYGsBrTnh2vF52CV9ucuqpjk)\n",
         "- [Read the **Getting Things Done with Pytorch** book](https://github.com/curiousily/Getting-Things-Done-with-Pytorch)\n",
@@ -62,7 +62,7 @@
       "source": [
         "## Detectron 2\n",
         "\n",
-        "<img src=\"https://dl.fbaipublicfiles.com/detectron2/Detectron2-Logo-Horz.png\" width=\"55%\">\n",
+        "<img src=\"https://www.curiousily.com/media/pytorch-02/detectron2-logo.png\" width=\"55%\">\n",
         "\n",
         "[Detectron2](https://github.com/facebookresearch/detectron2) is a framework for building state-of-the-art object detection and image segmentation models. It is developed by the Facebook Research team. Detectron2 is a complete rewrite of the [first version](https://github.com/facebookresearch/Detectron).\n",
         "\n",