Deduce size of output logits in handler
未关闭
bug
enhancement
- 主要语言
- Python
- 星标
- 23
- 派生
- 28
- 平均合并
- 4 天 12 小时
- 30 天内合并 PR
- 5
描述
# Feature
## Desired Behavior / Functionality
Right now, each attack is responsible for finding out the size of the logits.
## What Needs to Be Done
This should be done once only in the handler.
## How Can It Be Tested
Attacks work for both single neuron output and multiple.
贡献指南
评估
这个 Issue 还没有评估数据。