图像索引>> Visualizations-of-the-interpretations-of-CNNs>> 返回
项目作者： 123dddd

项目描述 ：
Using Sensitivity Heatmap, Deconvolution, Guided Backpropagation, Class Activation Mapping, Grad-CAM and Guided Grad-CAM methods to interpret the predictions of different CNN models
高级语言： Jupyter Notebook
项目地址: git://github.com/123dddd/Visualizations-of-the-interpretations-of-CNNs.git


Visualizations-of-the-interpretations-of-CNNs

Using Sensitivity Heatmap, Deconvolution, Guided Backpropagation, Class Activation Mapping, Grad-CAM and Guided Grad-CAM methods to interpret the predictions of different CNN models

python 3.6.12;
torchvision 0.8.1;
opencv 4.5.0;
numpy 0.19.2;
matplotlib 3.3.2

PLUS: If you are interested in exploring more advanced things about Model Interpretability (for PyTorch), have a look https://captum.ai/. It provides easy-to-use APIs for visulization as well as interpretation of the DL models.

Credits:

  1. https://github.com/utkuozbulak/pytorch-cnn-visualizations
  2. https://github.com/FrancescoSaverioZuppichini/A-journey-into-Convolutional-Neural-Network-visualization-
  3. https://github.com/kazuto1011/grad-cam-pytorch