update desc

Author: dnth

examples/analyzing-image-classification-dataset.ipynb

@@ -58,7 +58,9 @@
     "tags": []
    },
    "source": [
-    "## Download Imagenette Dataset"
+    "## Download Dataset\n",
+    "\n",
+    "We will analyze the [Imagenette](https://github.com/fastai/imagenette) dataset - a subset of 10 easily classified classes from Imagenet (tench, English springer, cassette player, chain saw, church, French horn, garbage truck, gas pump, golf ball, parachute)."
    ]
   },
   {
@@ -97,7 +99,13 @@
     "id": "f01586fe-db75-4154-aa15-9ea2709c9461"
    },
    "source": [
-    "## Load and Format Annotations"
+    "## Load and Format Annotations\n",
+    "\n",
+    "fastdup expects an annotation `DataFrame` that contains the following column:\n",
+    "\n",
+    "+ filename - contains the path to the image file.\n",
+    "+ label - contains a label of the image.\n",
+    "+ split - whether the image is subset of the training, validation or test dataset.\n"
    ]
   },
   {
@@ -494,7 +502,7 @@
    "source": [
     "## Import & Run fastdup\n",
     "\n",
-    "In this example we run fastdup by providing the annotations."
+    "With the images and annotations, we are now ready to run an analysis."
    ]
   },
   {
@@ -519,6 +527,16 @@
     "fastdup.__version__"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "52f2d878",
+   "metadata": {},
+   "source": [
+    "`work_dir` is the path to store the artifacts from the analysis.\n",
+    "\n",
+    "`input_dir` is the path to the downloaded images."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 9,
@@ -1926,6 +1944,7 @@
    "execution_count": 12,
    "id": "4d7cf1b9-c6c0-4b90-b7bb-59ca7bdbdcd7",
    "metadata": {
+    "scrolled": false,
     "tags": []
    },
    "outputs": [