The goal of repositories amitkr2410/MachineLearning and amitkr2410/MachineLearning-Deployment is to explore all stages from preparation to deployment of machine learning models and build end-to-end applications. In this repository, we present methods to deploy machine learning models on Google Cloud and AWS servers using flask, docker and html.
The goal of this project is to build CT scan tumor detection app using self-attention module and compare the performance with traditional VGG16 architecture. We deploy the application on Google Cloud Run. To access the web app, click here:
PyTorch based WebApp for BrainTumor detection on Google Cloud Run (Contact to view the interactive app.)
The goal of this project is to build CT scan tumor detection app using self-attention module and compare the performance with traditional VGG16 architecture. We deploy the application on AWS server using AWS ECR and AWS Lambda. To access the web files, click here:
PyTorch based WebApp for BrainTumor detection on AWS Cloud
The goal of this project is to build CT scan tumor detection app using self-attention module and compare the performance with traditional VGG16 architecture. We deploy the application on Google Kubernetes Engine . To access the web app, click here:
PyTorch based WebApp for BrainTumor detection on Google Kubernetes
[AWS Web APP Machine Learning](Contact to view the interactive app)
dvc_pipelines_svc/: Build DVC data pipelines and explore versioning
of ML experiments and input data.
NLP_twitter_aws_flask/: Build a sentiment analysis app
using NLTK library and host on AWS
server using flask, docker, AWS ECR,
and AWS lambda function.
**Personal Homepage: Amit's Personal HomePage
In below, we present a typical layout of data pipelines and ML experimentation for prototyping a model.
