Class Activation Map (CAM) Visualizations in PyTorch.
-
Updated
May 20, 2020 - Python
Class Activation Map (CAM) Visualizations in PyTorch.
Code for "Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability" (https://arxiv.org/abs/2010.09750)
pytorch实现Grad-CAM和Grad-CAM++,可以可视化任意分类网络的Class Activation Map (CAM)图,包括自定义的网络;同时也实现了目标检测faster r-cnn和retinanet两个网络的CAM图;欢迎试用、关注并反馈问题...
Implementation of the Grad-CAM algorithm in an easy-to-use class, optimized for transfer learning projects and written using Keras and Tensorflow 2.x
Official repository for the paper "Instance-wise Causal Feature Selection for Model Interpretation" (CVPRW 2021)
Exercise on interpretability with integrated gradients.
Investigating a neural network response to input parameters using sensitivity analysis techniques.
squid repository for manuscript analysis
Sentiment Analysis using Machine Learning
surrogate quantitative interpretability for deepnets
Standardized Serverless ML Inference Platform on Kubernetes
Add a description, image, and links to the model-interpretability topic page so that developers can more easily learn about it.
To associate your repository with the model-interpretability topic, visit your repo's landing page and select "manage topics."