Cat vs NonCat Project Clarification

[sushovan_chaudhury]

Hi,
This question is meant for Sandip Sir! If you guys can forward it will be great.
Sandip Sir has done a perfect job to teach the complex concepts in an easy manner.
Sir, though I have completed this project, using logistic regression(with the help of internet resources), I still have some doubts on this project -

1. It will be highly appreciated if you can clarify a bit more on the data loading and preprocessing part. Coz the data loading and preprocessing parts are mostly different for different projects and data sets.
   2.It will be better if you can throw some light on how to compare the validation result with the expected result. The coding part in those portions is not very clear to me.

We have spent a lot of time, in the algorithms, initialization, activation function, pooling, steps of creating the network, optimization, regularization but please explain a bit on the above two points.
Thanks in advance.
Sushovan

[sgiri]

Hi Sushovan,

As part of the course, the chapters on Numpy and Pandas and Python would help you understand the mechanics of cleaning and processing the data.

The end-to-end project (Chapter 2 of Machine Learning) helps you understand the preprocessing of data from the perspective of Machine learning. In this chapter, we have done a detailed analysis of validation and testing of the model. Please go thru it.

[sushovan_chaudhury]

Thank you sir…I am going through it.