本篇文章发表于ICLR 2023。
论文链接:https://arxiv.org/abs/2304.06129
代码链接:
GitHub - Trustworthy-ML-Lab/Label-free-CBM: A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without…
先给出一键三连模块 包含卷积-BN-激活函数
def autopad(k, pNone, d1): # kernel, padding, dilation"""Pad to same shape outputs."""if d > 1:k d * (k - 1) 1 if isinstance(k, int) else [d * (x - 1) 1 for x in k] # actual ke…