Pinned Repositories
amitav710
amitav710.github.io
Repository hosting my Personal Website.
AnirudhM1
Calorie-Estimation-YOLOv5
Food Calorie Estimation using YOLOv5
Customer-Segmentation-using-K-Means-Clustering
Clustering helps marketers improve their customer base, work on target areas, and segment customers based on purchase history, interests, or activity monitoring. Here the K-Means Clustering Algorithm has been used to group customers with the help of their Annual Incomes and their spending scores as metrics.
goadest-frontend
SAiDL-Spring-Assignment-2022
My Implementations of Bayesian Neural Network to solve Noisy XORs and Image Super-resolution using SRCNNs and SRResNet
Soundemic
stl-10-supervised
This model/project aims to achieve improved test set accuracy by implementation of Residual Networks (ResNets) on datasets where training data is limited. An accuracy of 74% was achieved when Residual Layers were introduced to the model as compared to 68% when the same model was used on the training data without any Residual Layers. Training was done on a total of 5000 examples and 8000 examples were tested. All the training and testing examples were a part of the stl-10 dataset, which comntains 10 different classes.
CS-F213-Chess
amitav710's Repositories
amitav710/Calorie-Estimation-YOLOv5
Food Calorie Estimation using YOLOv5
amitav710/goadest-frontend
amitav710/amitav710
amitav710/amitav710.github.io
Repository hosting my Personal Website.
amitav710/AnirudhM1
amitav710/Customer-Segmentation-using-K-Means-Clustering
Clustering helps marketers improve their customer base, work on target areas, and segment customers based on purchase history, interests, or activity monitoring. Here the K-Means Clustering Algorithm has been used to group customers with the help of their Annual Incomes and their spending scores as metrics.
amitav710/SAiDL-Spring-Assignment-2022
My Implementations of Bayesian Neural Network to solve Noisy XORs and Image Super-resolution using SRCNNs and SRResNet
amitav710/Soundemic
amitav710/stl-10-supervised
This model/project aims to achieve improved test set accuracy by implementation of Residual Networks (ResNets) on datasets where training data is limited. An accuracy of 74% was achieved when Residual Layers were introduced to the model as compared to 68% when the same model was used on the training data without any Residual Layers. Training was done on a total of 5000 examples and 8000 examples were tested. All the training and testing examples were a part of the stl-10 dataset, which comntains 10 different classes.
amitav710/ashmitkx.github.io
Repo hosting my personal website
amitav710/Coursera-DL-Specialization
Repository for Programming Assignments of Coursera's DL Specialization
amitav710/CS-F213-Chess
amitav710/cs231n
My attempt at the assignments of cs231n
amitav710/Everything-GANs
Reviewing Existing Literature on GANs and their implementations
amitav710/ML4SCI-HiggsClassification
amitav710/Object-Detection-and-YOLO-Implementations
My implementation of some YOLO versions
amitav710/RTChatApp
Real Time Chat Application built using React, NodeJS and socket.io
amitav710/ViT-Implementation
An Implementation of Visual Transformers in PyTorch for the CIFAR10 dataset