modified cyclegan intro

Author: mayank2

guide/14-deep-learning/How CycleGAN Works.ipynb

@@ -12,7 +12,7 @@
    "metadata": {},
    "source": [
     "## Introduction\n",
-    "There are situations when we have two different domains of images, which are randomly organized or unpaired and we want to convert images from one domain to another just like [Pix2Pix](https://developers.arcgis.com/python/guide/how-pix2pix-works/).\n",
+    "CycleGAN is and Image to Image translation model, just like [Pix2Pix](https://developers.arcgis.com/python/guide/how-pix2pix-works/). There are some challenges in Pix2Pix is that the images should be paired which are randomly organized or unpaired and we want to convert images from one domain to another just like \n",
     "\n",
     "The Cycle Generative Adversarial Network, or CycleGAN, is an approach to training a deep convolutional neural network for image-to-image translation tasks. The Network learns mapping between input and output images using unpaired dataset. For Example: Generating RGB imagery from SAR, multispectral imagery from RGB, map routes from satellite imagery, etc.\n",
     "\n",