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.
Log in or sign up for Devpost to join the conversation.