Dynamic AutoML
Dynamic AutoML: Automate Data Tasks for Smarter Results.
Listed in categories:
Artificial IntelligenceData & AnalyticsGitHub
Description
Dynamic AutoML is a versatile platform designed to streamline various data tasks including CSV analysis, LSTM modeling, and image classification and detection. It offers advanced features and capabilities to empower developers in handling diverse datasets efficiently.
How to use Dynamic AutoML?
To use Dynamic AutoML, upload your CSV files or image datasets, explore the dataset properties, choose appropriate models for training, evaluate model performance, and download the trained models for deployment.
Core features of Dynamic AutoML:
1️⃣
Dynamic dataset architecture for CSV analysis
2️⃣
LazyPredict model implementation for model selection
3️⃣
Automated model training for image classification
4️⃣
Dynamic image segmentation using YOLO
5️⃣
Streamlined LSTM model training and hyperparameter tuning
Why could be used Dynamic AutoML?
| # | Use case | Status | |
|---|---|---|---|
| # 1 | Automating the analysis of time series datasets | ✅ | |
| # 2 | Efficiently training image classification models | ✅ | |
| # 3 | Optimizing LSTM models for specific datasets | ✅ | |
Who developed Dynamic AutoML?
Dynamic AutoML is developed by a passionate team of computer science students specializing in machine learning, including Siddhanth Sridhar, Swaraj Khan, and Shreya Chaurasia, who are dedicated to leveraging technology to solve real-world challenges.