Merge branch 'main' into atqy/preprocess-image-data

Author: atqy

introduction_to_amazon_algorithms/object_detection_birds/object_detection_birds.ipynb

@@ -28,7 +28,7 @@
     "\n",
     "Object detection is the process of identifying and localizing objects in an image. A typical object detection solution takes an image as input and provides a bounding box on the image where an object of interest is found.  It also identifies what type of object the box encapsulates.  To create such a solution, we need to acquire and process a traning dataset, create and setup a training job for the alorithm so that it can learn about the dataset. Finally, we can then host the trained model in an endpoint, to which we can supply images.\n",
     "\n",
-    "This notebook is an end-to-end example showing how the Amazon SageMaker Object Detection algorithm can be used with a publicly available dataset of bird images. We demonstrate how to train and to host an object detection model based on the [Caltech Birds (CUB 200 2011)](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html) dataset.  Amazon SageMaker's object detection algorithm uses the Single Shot multibox Detector ([SSD](https://arxiv.org/abs/1512.02325)) algorithm, and this notebook uses a [ResNet](https://arxiv.org/pdf/1603.05027.pdf) base network with that algorithm.\n",
+    "This notebook is an end-to-end example showing how the Amazon SageMaker Object Detection algorithm can be used with a publicly available dataset of bird images. We demonstrate how to train and to host an object detection model based on the [Caltech Birds (CUB 200 2011)](https://paperswithcode.com/dataset/cub-200-2011) dataset.  Amazon SageMaker's object detection algorithm uses the Single Shot multibox Detector ([SSD](https://arxiv.org/abs/1512.02325)) algorithm, and this notebook uses a [ResNet](https://arxiv.org/pdf/1603.05027.pdf) base network with that algorithm.\n",
     "\n",
     "![Sample results detecting a pair of goldfinch on a feeder](./goldfinch_detections.png)\n",
     "\n",
@@ -136,11 +136,7 @@
    "source": [
     "## Data Preparation\n",
     "\n",
-    "The [Caltech Birds (CUB 200 2011)](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html) dataset contains 11,788 images across 200 bird species (the original technical report can be found [here](http://www.vision.caltech.edu/visipedia/papers/CUB_200_2011.pdf)).  Each species comes with around 60 images, with a typical size of about 350 pixels by 500 pixels.  Bounding boxes are provided, as are annotations of bird parts.  A recommended train/test split is given, but image size data is not.\n",
-    "\n",
-    "![](./cub_200_2011_snapshot.png)\n",
-    "\n",
-    "The dataset can be downloaded [here](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html).\n",
+    "The Caltech Birds (CUB 200 2011) dataset contains 11,788 images across 200 bird species (the original technical report can be found [here](https://authors.library.caltech.edu/27452/1/CUB_200_2011.pdf)).  Each species comes with around 60 images, with a typical size of about 350 pixels by 500 pixels.  Bounding boxes are provided, as are annotations of bird parts.  A recommended train/test split is given, but image size data is not.\n",
     "\n",
     "## Download and unpack the dataset\n",
     "\n",