Git Product home page Git Product logo

🙋‍♂️ The Training notebook(s) used to train/FineTune ResNet50 on Mendley Medicinal leaf dataset

2nd One is latest btw

The Code for the model serving can be found at the following repo links, There are two repos for Front-End and Back-End Components

What is this? :

  • The Project aims to solve the problem of identification of medicinal herbs.
  • The Machine Learning Model uses ResNet, with a validation accuracy of 98% and testing accuracy of 96%.
  • The training and testing dataset contains over 1500 images across 50 medicinal herb species.
  • The model is capable of classifying the user-given image into 30 species.

Tech Stack Used :

Training, Validation and Test Accuracies for 54 Epochs (Early Stoping):

  • Training Accuracy : 97.55%
  • Validation Accuracy : 98.64%
  • Top 1 Testing Accuracy : 96.43%
  • Top 5 Testing Accuracy : 99.07%

Training Vs Validation Accuracy :

download

Sample Predictions :

download

Mohammad Ausaf's Projects

aushadhhub-backend icon aushadhhub-backend

Repo 1 of End-to-End Machine Learning Project aiming to solve the problem of identification of medicinal herbs.The Application uses ResNet trained on custom dataset, a validation accuracy of 96%. The training and testing dataset contains over 1500 images across 30 medicinal herb species.

aushadhubfrontend icon aushadhubfrontend

Repo 2 of AushadHub, a FlaskApp with HTML, CSS and Javascript as FrontEnd. This is client side FrontEnd which posts the Image input to endpoint of FlaskApp hosted on google cloud for preprocessing and Inferencing.

cs-2024-a icon cs-2024-a

Project Repository for the major project in 2024 Batch. PCS24-26

dontlookup icon dontlookup

In browser Wikipedia style quick loookup, LLM and Wiki based quick search extension. Open-Source, Contributions, Forkes and Suggestions welcomed. Temp API below

exercise-countercumtimer icon exercise-countercumtimer

A pose detection cum timer implementation, however focused on preprocessing of the feed beforehand to filter feed fluctuations.

generative-ai icon generative-ai

Sample code and notebooks for Generative AI on Google Cloud

hugging-face-nlp icon hugging-face-nlp

A custom NLP template implementing Text classification and Sentiment Analysis using Hugging Face Transformer.

llm-finetuning-template icon llm-finetuning-template

Template Code for working and finetuning a LLM for custom dataset, here a artificially generated dataset ( couldn't find a real one).

mirnetforlol icon mirnetforlol

Tensorflow implementation of MIRNet for Low-light image enhancement

notebook-medicinal-herb-model-resnet icon notebook-medicinal-herb-model-resnet

A possible tool for assistance in Alternative Medicine using DeepLearning models of Resnet-50, looking to try more algorithms especially VGG16. If someone has any suggestions please feel obliged to guide me .

playstoreeda icon playstoreeda

Did EDA on Play Store Data. Used some references from kaggle notebooks .

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.