akashpalrecha/deblurring-pipeline

Stars
1
Language
Python
License
MIT License
Created over 4 years ago
Updated over 3 years ago

akashpalrecha/deblurring-pipeline

akashpalrecha

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Contains code to run experiments on image deblurring using deep learning.

hyperspectral-reconstruction

Reconstructing 31 band hyperspectral imagery from 3 band RGB input

Jupyter Notebook

Resnet-multichannel

Helper class to create Pretrained Resnet models that can take in an arbitary number of channels as input.

custom-fastai-callbacks

Custom Callbacks to extend the Fastai library's functionality

Jupyter Notebook

distill-superres

fork of EDSR based repo to do knowledge distillation experiments for super resolution

classification_oversampling

Utility package to help in oversampling images in Image Classification tasks

drought-watch

A deep learning classification model to predict drought using satellite imagery.

Jupyter Notebook

siamese-transfer

A personal research attempt at making transfer learning work for Siamese Networks

Jupyter Notebook

ImageReader_w_data_augmentation

A simplified approach to Data Augmentation for Computer Vision applications using python.

Java-ML

Neural network implementation in pure Java (no third-party libraries used)

Jupyter Notebook

Deep-Into-PyTorch-Modules

Explores the internals of `torch.nn.Module`

Jupyter Notebook

HumanProteinAtlasClassification

My attempt at this Kaggle competition - https://www.kaggle.com/c/human-protein-atlas-image-classification

Jupyter Notebook

computational-linear-algebra

Contains my work on Fast.ai's Computational Linear Algebra Course (https://github.com/fastai/numerical-linear-algebra/blob/master/README.md) along with my own explorations of the subject.

Jupyter Notebook

Lookahead

This project compares Geoffrey Hinton's new Lookahead optimizer with other conventional optimizers like AdamW, SGD, RMSProp, etc. This is a work in progress

Jupyter Notebook