It classifies whether a given image is of Sunflower or of rose using different Deep Learning algorithms
You can install Conda for python which resolves all the dependencies for machine learning.
- Model Used: Logistic Regression
- Training Dataset Size: 1300
- Test Dataset Size: 90
- Library used: Pytorch, MatPlotLib, TorchVision,Random
- Initial learning rate: 0.01
- No. of epochs: 100
- Mini batch size: 64
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.
- Gradient Descent (Batch, Mini-batch, Stochastic)
- Gradient Descent with Momentum
- Learning rate decay
PS: For Code, accuracy v/s iteration & Cost v/s iteration graphs of different algorithms, check different release of this repo