GitHub - Stiti-create/CNN-Implementation-Numpy: Implementation of CNN (consisting of maxpool, relu, fully-connected and convolutional layers) using Numpy Vectorisation (from scratch without any third-party library), followed by analysis using hyperparameter tuning and different regularisation techniques

CNN Implementation Numpy

Includes:

Implementation of CNN (consisting of maxpool, relu, fully-connected and convolutional layers) using Numpy Vectorisation (from scratch without any third-party library)
Studying the effects of different hyperparameters using hyperparameter tuning in pytorch implementation of CNN:
- learning rate (static or scheduled)
- loss functions
- Number of epochs
- Batch-sizes
- Adam and SGD optimisers
Achieving best accuracy on CIFAR-10 datasets using different techniques like Batch, Group Normalisations, Weight decays and Dropout layers

Use CIFAR-10 dataset from this link and refer to unpickling details for python given in the website.

Refer to Report.pdf for more implementation details and analysis part.

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
Report.pdf		Report.pdf
batches.ipynb		batches.ipynb
bonus.ipynb		bonus.ipynb
cnn.ipynb		cnn.ipynb
kdivloss.ipynb		kdivloss.ipynb
learnrate.ipynb		learnrate.ipynb
lrsched.ipynb		lrsched.ipynb
readme.md		readme.md
sgdeffect.ipynb		sgdeffect.ipynb
withoutaugment.ipynb		withoutaugment.ipynb