2 dépôts
Awesome GitHub RepositoriesFrequency Encodings
Transforms each input dimension into sine and cosine pairs at logarithmically spaced frequencies for neural network input.
Distinct from Input Encoding Combinations: Distinct from Input Encoding Combinations: focuses on the specific frequency-based encoding technique, not the combination of multiple encoding schemes.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Frequency Encodings. Refine with filters or upvote what's useful.
Awesome Frequency Encodings GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- fulldecent/system-bus-radio
fulldecent/system-bus-radio
6,680Voir sur GitHubSystem-bus-radio is a software-defined radio transmitter that generates AM radio signals by modulating the electromagnetic emissions from a computer's processor and memory bus, without requiring any dedicated radio hardware or physical antennas. It functions as a CPU electromagnetic emissions tool and processor-based signal generator, enabling radio transmission through precise control of CPU instructions and memory bus operations. The project encodes musical notes as sequences of frequency and duration pairs, then synthesizes the AM radio waveform in real-time by executing a tight loop of CP
Encodes musical notes as frequency-duration pairs for playback via the modulated carrier.
Cairgapcommunicationcommunication-protocol - nvlabs/tiny-cuda-nn
NVlabs/tiny-cuda-nn
4,418Voir sur GitHubThis project is a high-performance C++ and CUDA neural network library designed for fast training and inference of small networks on NVIDIA GPUs. It serves as a specialized backend for neural radiance fields and coordinate-based networks, providing a fused GPU kernel library and a hash grid encoder for transforming raw input dimensions into high-dimensional representations. The library distinguishes itself through the use of C++ template metaprogramming and fused-kernel execution, which merge neural network layers into single GPU device functions to eliminate memory bottlenecks. It leverages
Transforms each input dimension into sine and cosine pairs at logarithmically spaced frequencies.
C++cudadeep-learninggpu
