LSFQ: A Low Precision Full Integer Quantization for High-Performance FPGA-Based CNN Acceleration.
Zhenshan BaoKang ZhanWenbo ZhangJunnan GuoPublished in: COOL CHIPS (2021)
Keyphrases
- cellular neural networks
- convolutional neural network
- hardware implementation
- application specific
- quantization step
- cost effective
- video processing
- quantization error
- hardware architecture
- quantization noise
- uniform quantization
- floating point
- high reliability
- rate distortion
- transform coefficients
- entropy coding
- scientific computing
- quantization scheme
- hardware architectures
- signal processing
- multiscale