Skip to content

take2rohit/flower-classifier

Repository files navigation

Binary classification using Logistic Regression model

Aim

It classifies whether a given image is of Sunflower or of rose using different Deep Learning algorithms

Code Requirements

You can install Conda for python which resolves all the dependencies for machine learning.

Technical Details

  1. Model Used: Logistic Regression
  2. Training Dataset Size: 1300
  3. Test Dataset Size: 90
  4. Library used: Pytorch, MatPlotLib, TorchVision,Random
  5. Initial learning rate: 0.01
  6. No. of epochs: 100
  7. Mini batch size: 64

Description

Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised or unsupervised.

Deep learning models are loosely related to information processing and communication patterns in a biological nervous system, such as neural coding that attempts to define a relationship between various stimuli and associated neuronal responses in the brain.

The code is written from scratch using pytorch for dataloading, matrix calculations and GPU acceleration.

Algorithms used;

  1. Gradient Descent (Batch, Mini-batch, Stochastic)
  2. Gradient Descent with Momentum
  3. Learning rate decay

PS: For Code, accuracy v/s iteration & Cost v/s iteration graphs of different algorithms, check different release of this repo

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Packages

No packages published