Ayush Thakur

Deep Learning for Computer Vision

Top projects

Simple Transformers: Transformers Made Easy
Simple Transformers removes complexity and lets you get down to what matters – model training and experimenting with the Transformer model architectures.
transformers huggingface simple-transformers text-classification
Image Segmentation Using Keras and W&B
This report explores semantic segmentation with a UNET like architecture in Keras and interactively visualizes the model's prediction in Weights & Biases.
semantic-segmentation kera wandb visualization
Modern Data Augmentation Techniques for Computer Vision
A bunch of modern data augmentation techniques for computer vision covering cutout, mixup, cutmix and augmix.
data-augmentation cutout mixup cutmix
Understanding the Effectivity of Ensembles in Deep Learning
The report explores the ideas presented in Deep Ensembles: A Loss Landscape Perspective by Stanislav Fort, Huiyi Hu, and Balaji Lakshminarayanan.
computer-vision deep-learning neural-networks ensembles
Simple Ways to Tackle Class Imbalance
Various methods used to counter class imbalance in image classification problems – class weighting, oversampling, under sampling, and two-phase learning.
tensorflow class-imbalance keras wandb

Top collections