CONVOLUTIONAL NETWORK from Scratch - Binary Classification

 I used the world renowned dogs-vs-cats dataset from kaggle, to train a convolutional neural network. My procedure was as follows:

-   I downloaded the dataset from kaggle 

-   Created directories and transferred the relevant data. 

  • I created an 'original_dataset_dir' and transferred all of the data (data of all classes) to this directory.
  • I then created a base directory: 'base_dir'.
  • I created the folders 'train', 'validation' and 'test' inside base directory.
  • Then I created the folders 'cats', 'dogs', inside the folders created in last step.
  • Then I transferred the data according to the following ratio: (Train, Validation, Test) = (50, 25, 25)

-  Initiated a small convolutional network

  • In the conv base, I created 4 successive 'conv2D' layers, each followed by a 'Maxpooling2D' layer, without any padding.
  • In the classifier base, I added a 'Flatten' layer, followed by two Dense Layers

-  Compiled the model

-  Did Data Processing

  • Different images had d/f dimensions. I created two data generator object. One for 'training dataset' & one for 'test & validation datasets'.
  • I resized all of the images to the size 150*150 in both of the data generator objects.
  • Class Mode in both objects was set to 'binary'
  • All of the pixels were rescaled as (1./255) in both generator objects, to standardize the data.
  • For this particular case, only one data generator object was enough to create data generators for all of the data sets. But I still defined  two d/f data gen objects, as in the upcoming notebooks, they'll be helpful for me, when I'll perform data augmentation on training dataset. But won't do the same with test and validation datsets.

-  Trained the model

-  Plotted the Data

-  The max validation accuracy achieved was 73.4%

Here is the github link to the said Jupyter Notebook. It is the first half of this Notebook.

I also made some video explanations for myself in URDU language, You can see them here.

Summary

Cell Details 













Comments

Post a Comment

Popular posts from this blog

Ai SDK ui - 1 - Learning AI SDK UI with Next.js

I recently started learning AI SDK UI . I’ve been working with Next.js already, but this library adds something special. It's  framework agnostic !  It works with Angular, Vue, Svelte, and React. Of course, I’m doing it with Next.js (React) because that’s what I know best. One of the first things I tried was the useChat hook. This makes building a chatbot UI feel way simpler. Normally, handling messages, updating state, and keeping track of what the AI is saying can be messy. With useChat , a lot of that heavy lifting is done for you. Here are some cool things I noticed about it: Message streaming out-of-the-box. You don't need to implement manual streaming! The hook manages states like input, messages, status, and errors. You don’t need to write all that boilerplate yourself. I also liked that it handles more than just happy paths. For example: You can stop a response midway if you want. It provides it out of the box! There are even helpers for modifying message...
Read more

NMLS - 1. Clustering - Kmeans - Unsupervised Learning - Introductory Machine Learning

In 2022 I started the new  Machine Learning Specialization by Andrew NG. I completed it's first two courses in 2022. I'll sgare the jupyter notebooks from this specialization soon. Now, in 2023 when I am finally free from my M1, I am going to complete the specialization. Here is the first Assignment of course 3 (last course) on Clustering. Procedure : Distances between each data-point and all of the cluster centroids were computed The cluster centroid closest to the each data-point was assigned to that data-point The average positions of all of the data-points in a cluster were computed Corresponding centroids were moved to these new average positions The procedure was repeated for a specific number of iterations. Relevant  github link Relevant  video explanation (in Urdu)
Read more

NMLS - 3. Recommender Systems - Collaborative Filtering - Introductory Machine Learning

  In 2022 I started the new  Machine Learning Specialization by Andrew NG. I completed it's first two courses in 2022. I'll share the jupyter notebooks from this specialization soon. Now, in 2023 when I am finally free from my M1, I am going to complete the specialization. Here is the third Assignment of course 3 (last course) on Recommender Systems.   We were given a dataset which contained 'nu' users and 'nm' movies. The ratings that each user gave to various movies were present in the dataset. The task was: We have a new user who has not yet rated a lot of movies. We have have to recommended him movies based on his previous ratings.   Procedure : The cost function was implemented using For Loop & then without any loop (Vectorized Implementation) A list of movie ratings for a new user was created and was added to the training data The rows(movies) were normalized by taking average of each row for non-zero values and then subtracting each value from the...
Read more