https://github.com/ARM-software/CMSIS_5
공식 코드CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs
Rethinking Weight Decay For Efficient Neural Network Pruning
Small-Footprint Keyword Spotting with Multi-Scale Temporal Convolution
Image Generation for Efficient Neural Network Training in Autonomous Drone Racing
Efficient Neural Network Approximation of Robust PCA for Automated Analysis of Calcium Imaging Data
Ground-aware Monocular 3D Object Detection for Autonomous Driving
Differentiable Neural Architecture Learning for Efficient Neural Network Design
Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression
SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
LightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks
EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
FLIGHT Mode On: A Feather-Light Network for Low-Light Image Enhancement
LUTNet: Learning FPGA Configurations for Highly Efficient Neural Network Inference
Logic Shrinkage: Learned FPGA Netlist Sparsity for Efficient Neural Network Inference
EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network Acceleration
Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks
Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes
Orthogonal Transforms in Neural Networks Amount to Effective Regularization
The Effectiveness of a Simplified Model Structure for Crowd Counting
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics
Efficient Neural Network Robustness Certification with General Activation Functions
HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.