Verified65% confidenceFactTime unknown
F1分数是Fβ分数在β=1时的特例
3
Sources
65%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
混淆矩阵详解：Precision、Recall与F1分数计算公式及实战应用
bilibili拓跋龙的私人领地
Related Entities
Related Claims
UnverifiedAccording to the MedViT paper, the model achieved a Macro F1 score of 0.7791 on ChestX-ray1462% similarUnverifiedOCR的F1分数为25.1%，通用Agent为11.57%，OCR高出约2.17倍57% similarUnverifiedMacro F1 computes F1 independently for each class then takes a simple arithmetic average across all classes56% similarUnverifiedFP4格式仅有4位（1位符号、2位指数、1位尾数），仅能精确表示约16个离散值56% similarUnverifiedBF16采用1位符号位、8位指数位和7位尾数位，牺牲精度但保留了与FP32相同的动态范围54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/20850API
curl https://kongchang.com/api/v1/knowledge/claims/20850MCP
get_claim(id=20850)