Update README.md

README.md

@@ -191,8 +191,11 @@ This hack will help you to combine multiple PDF documents into a single document
 
 - ### [Data Science Hack #44 Create a Custom Image DataGenerator in Keras](./Code/CustomDataGen_Keras.ipynb)
 Sometimes you would need a functionality which is not directly provided by Keras's ImageDataGenerator. You can easily create a wrapper around it to suit your needs. 
-  - For example, your usecase is that you have multi-input Deep Learning model like this
 
-![temp](../Data/muti_input_nn.png)
+1. For example, your usecase is that you have multi-input Deep Learning model like this
 
-(i.e. a neural network which takes input from multiple data sources, and does a combined training on this data), and you want that the data generator should be able to handle the data preparation on the fly, you can create a wrapper around ImageDataGenerator class to give the required output.[This notebook](./Code/CustomDataGen_Keras.ipynb) explains a simple solution to this usecase. Another use case could be that you want to resize the images from a shape say 150x150 to a shape 224x224, which is generally utilized by the pretrained models, you can customize the ImageDataGenerator without coding your own data generator from ground up[(Example Notebook)](https://github.com/faizankshaikh/AV_Article_Codes/blob/master/Inception_From_Scratch/improvements/Inception_v1_from_Scratch.ipynb).
+![](./Data/muti_input_nn.png)
+
+(i.e. a neural network which takes input from multiple data sources, and does a combined training on this data), and you want that the data generator should be able to handle the data preparation on the fly, you can create a wrapper around ImageDataGenerator class to give the required output.[This notebook](./Code/CustomDataGen_Keras.ipynb) explains a simple solution to this usecase. 
+
+2. Another use case could be that you want to resize the images from a shape say 150x150 to a shape 224x224, which is generally utilized by the pretrained models, you can customize the ImageDataGenerator without coding your own data generator from ground up [(Example Notebook)](https://github.com/faizankshaikh/AV_Article_Codes/blob/master/Inception_From_Scratch/improvements/Inception_v1_from_Scratch.ipynb).