Inspiration

What it does

BarugahTime is a CUDA-optimized neural network inference engine that accelerates image recognition, providing rapid and precise results for real-time applications.

How we built it

We built BarugahTime using Python, optimizing neural network layers with custom CUDA kernels and leveraging cuDNN for enhanced performance. The architecture and weights were integrated for efficient inference.

Challenges we ran into

Since this was the first time we tinkered with anything regarding Neural Networks, our main challenge was understanding the concepts behind network and implementation of the matter.

Accomplishments that we're proud of

We mainly took the opportunity to learn a new field that has been a gap in our knowledge pool.

What we learned

How to build a Neural network from scratch.

What's next for BarugahTime

Built With

Share this project:

Updates