Add image of espargos-0002 setup, add download code

README.md

@@ -17,7 +17,7 @@ All WiFi CSI data is for 40 MHz wide WiFi channels at 2.4GHz.
 * Four distributed 4 × 2 ESPARGOS antenna arrays, dominant LoS path
 * ["AoA-Augmented Channel Charting"](https://github.com/Jeija/ToA-AoA-Augmented-ChannelCharting/): Siamese Neural Network-based Channel Charting (with fused CSI-based / timestamp-based dissimilarity metric) is augmented by classical triangulation
 
-<img alt="Setp of espargos-0001" src="img/espargos-0001-setup.jpg" width=320>
+<img alt="Measurement setup for dataset espargos-0001" src="img/espargos-0001-setup.jpg" width=400>
 
 <table>
     <tr>
@@ -59,10 +59,12 @@ CT = Continuity, TW = Trustworthiness, KS = Kruskal Stress, MAE = Mean Absolute
 
 ### Triplet Neural Network-based Channel Charting applied to [`espargos-0002`](https://espargos.net/datasets/data/espargos-0002/): `TripletNeuralNetwork.ipynb`
 * One large 8 &times; 4 ESPARGOS antenna array
-* Metal wall to ensure NLoS propagation in large parts of measurement area
+* Metal wall to ensure NLoS propagation in large parts of measurement area (whenever robot is behind wall from point of view of antenna array)
 * Triplet Neural Network learns channel chart based on CSI data and timestamps
 * No augmentation with model-based approach: The channel chart coordinates can be arbitrarily translated / rotated / scaled / flipped (affine transformation) compared to the true physical coordinates.
 
+<img alt="Measurement setup for dataset espargos-0002" src="img/espargos-0002-setup.jpg" width=400>
+
 <table>
     <tr>
         <th style="text-align: center;">Training Animation</th>

TripletNeuralNetwork.ipynb

@@ -18,6 +18,27 @@
     "However, instead of a [DICHASUS](https://dichasus.inue.uni-stuttgart.de/) dataset, we use an [ESPARGOS](https://espargos.net/) dataset called [espargos-0002](https://espargos.net/datasets/data/espargos-0002/)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "d7316de0",
+   "metadata": {},
+   "source": [
+    "## Download Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2a7de1e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!mkdir espargos-0002\n",
+    "!wget -nc --content-disposition https://darus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-4456/12 -P espargos-0002 # espargos-0002-all-randomwalk-3.tfrecords\n",
+    "!wget -nc --content-disposition https://darus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-4456/13 -P espargos-0002 # espargos-0002-all-radial-meanders-1.tfrecords \n",
+    "!wget -nc --content-disposition https://darus.uni-stuttgart.de/api/access/datafile/:persistentId?persistentId=doi:10.18419/darus-4456/8 -P espargos-0002 # espargos-0002-all-spiral-1.tfrecords"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,