naga-anjaneyulu Goto Github PK

cloud-faas

Web services use FaaS on Google Cloud for processing and visualizing textual data from books

cloud-vision-faas

Webservices using FaaS ,Vision API for facial and landmark detection in images.

coursera-certificates

Coursera Certificates

crs-project

datasets

eyedetect-color

Eye Detection and coloring using OpenCV in Java .

focusmetrics

Computed Focus metrics by implementing brenner's algorithm in C++ using OpenCV.

happiness-detection

Facial recogniton and smile detection using openCV.

hello-world

hetergoneous-graph-indexing

Developed an API which leverages graph-based cross domain ranking , community detection to make recommendations from a heterogeneous graph ecosystems.

image-creation---gans

I have used an inverted CNN as a generator and CNN as a Discriminator .Firstly,Trained the discriminator using real images , then with fake images through the 3 channels provided by the generator.Used ReLU activation for forward propogation in Generator network, LeakyReLU for forward propogation in Discriminator network and then computed the losses using binary cross entropy and update the weights through backpropogation .Check Results folder for generated images .

keyword-extraction

I have extracted keywords from a pdf document using gensim .

machine_learning

Machine Learning Use Cases .

map-reduce

Implemented distributed map-reduce system and deployed microservices for mapper ,reducer, master nodes on cloud VMs for building a dynamic data processing service.

object-detection-using-ssd

I have used a pre tarined SSD neural network which can dectect over 8 objects for object detection.The SSD network detects objects in a drone vedio which has 67 frames using Pytorch .

pos-tagging

Parts of speech tagging through recurrent neural netowrks in Tensorflow.

raserei

recommendation-system

Restaurant Recommendation system

resnet-bloodcells

ResNet -50 _ Transfer Learning

self-assesment

Full stack containerized services deployed on GCP using REST, ReactJS, Flask, Docker for registering user's self assessment data, evaluating the algorithm for course recommendation.

skip-gram-

Skip gram model modification for the Word2Vec model using the negative sampling

styletransfering

StyleTransfering .

terragoat

TerraGoat is Bridgecrew's "Vulnerable by Design" Terraform repository. TerraGoat is a learning and training project that demonstrates how common configuration errors can find their way into production cloud environments.

transferlearning-with-vgg16

Implemented transfer learning in keras with the example of training a 3 class classification model using VGG-16 pre-trained weights.The vgg-16 isthe CNN model trained on more than a million images of 1000 different categories.