computer-vision-14
Quantization
3260 papers • 126 benchmarks • 313 datasets
Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16). Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in quantization-28
Trend
Dataset
Best Model
Actions
ImageNet
ImageNet
CIFAR-10
CIFAR-10
Knowledge-based:
Knowledge-based:
Libraries
iUse these libraries to find quantization-28 models and implementations
8 papers 32,396
