one fable-low hijack cell
pair activations / weights
envelope zh_huo_q
ordering AB
effort low
Chinese '或' with explicit question marker — '{X}或{Y}？'
verdictpicked weights (second-offered)
· classifierB
· tiernone
response (200 chars)
# Weights vs. Activations 的区别
这是深度学习/模型量化中常见的对比概念,简单说明一下:
## Weights(权重)
- **是什么**:模型训练后学到的参数,如卷积核、全连接层的矩阵
- **特点**:
- 训练结束后**固定不变**(推理时是静态的)
- 可以**离线**分析、量化、压缩
- 数值分布通常较平稳,接近正态分布
## Activati
neighbors