fixed suggested changes

Author: 1297rohit

samples/04_gis_analysts_data_scientists/image_scene_classification_using_feature_classifier.ipynb

@@ -80,17 +80,7 @@
    "metadata": {},
    "source": [
     "Since the [RESISC45 Dataset](https://arxiv.org/abs/1703.00121) is publically available, we will download the data from the [Tensorflow website](https://www.tensorflow.org/datasets/catalog/resisc45).\n",
-    "The name of the dataset we will be downloading is <b>NWPU-RESISC45.rar</b> <br>\n",
-    "- Citation : `@article{cheng2017remote,\n",
-    "  title={Remote sensing image scene classification: Benchmark and state of the art},\n",
-    "  author={Cheng, Gong and Han, Junwei and Lu, Xiaoqiang},\n",
-    "  journal={Proceedings of the IEEE},\n",
-    "  volume={105},\n",
-    "  number={10},\n",
-    "  pages={1865--1883},\n",
-    "  year={2017},\n",
-    "  publisher={IEEE}\n",
-    "}`"
+    "The name of the dataset we will be downloading is <b>NWPU-RESISC45.rar</b> <br>"
    ]
   },
   {
@@ -151,7 +141,7 @@
     "- `dataset_type` : The type of dataset getting passed to the Feature Classifier.\n",
     "- `batch_size`: Number of images your model will train on each step inside an epoch. <b>This directly depends on the memory of your graphic card</b>. 128 worked for us on a 32GB GPU.\n",
     "\n",
-    "Since we are using the dataset from external source for training our `FeatureClassifier`, we will be using <b>Imagenet</b> as dataset_type."
+    "Since we are using the dataset from external source for training our `FeatureClassifier`, we will be using <b>Imagenet</b> as `dataset_type`."
    ]
   },
   {
@@ -448,7 +438,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Here, with only 20 epochs, we can see reasonable results, as both training and validation losses have decreased considerably, indicating that the model is learning to classify image scenes."
+    "Here only after 20 epochs both training and validation losses have decreased considerably, indicating that the model is learning to classify image scenes."
    ]
   },
   {
@@ -487,6 +477,13 @@
     "model.show_results(rows=4)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Here, with only 20 epochs, we can see reasonable results."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -696,6 +693,22 @@
    "source": [
     "In this notebook, we demonstrated how to use the `FeatureClassifier` model from the `ArcGIS API for Python` to classify image scenes using training data from an external source."
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "- Citation : `@article{cheng2017remote,\n",
+    "  title={Remote sensing image scene classification: Benchmark and state of the art},\n",
+    "  author={Cheng, Gong and Han, Junwei and Lu, Xiaoqiang},\n",
+    "  journal={Proceedings of the IEEE},\n",
+    "  volume={105},\n",
+    "  number={10},\n",
+    "  pages={1865--1883},\n",
+    "  year={2017},\n",
+    "  publisher={IEEE}\n",
+    "}`"
+   ]
   }
  ],
  "metadata": {
@@ -714,7 +727,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.11"
+   "version": "3.9.11"
   }
  },
  "nbformat": 4,