自动瑕疵定位
#569
Replies: 1 comment
-
# 测评计算图样本在两个后端上的表现
eval_backend_diff :=
[model_path]
-> LOG
# 过滤有瑕疵的计算图
get_fault_model_paths :=
LOG
-> [model_path]
# 计算ES向量
get_es_scores :=
LOG
-> ES
# 特定容忍值t是否有瑕疵
has_fault_at :=
ES
-> tTolerance int
-> bool
# 子图分解
subgraph_generator :=
model_path
-> [(tStart int, tEnd int)]
-> [model_path]
# 二分终止判断
bi_search_terminator :=
[(tSplitPoint int, bool)]
-> bool
# 二分查找算法
bi_search :=
model_path
-> tTruncator (model_path -> tSplitPoint int -> model_path)
-> tEvaluator (model_path -> ES)
-> tPredicator (ES -> tTolerance int -> bool)
-> tStoper ([(tSplitPoint int, bool)] -> bool)
-> [(tSplitPoint int, bool)]
# 单测样本生成
generate_unittest :=
model_path
-> unittest |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
torch框架上自动瑕疵定位需补齐或更新的功能组件:
Beta Was this translation helpful? Give feedback.
All reactions