/gradcam-tf2

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

Primary LanguagePython

GRADCAM

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.

Requirement

  • Python 3.6.x
  • Matplotlib 3.4.x
  • Numpy 1.19.x
  • Tensorflow 2.4.x

Usage

Please take a look of examples folder for a complete example.

from gradcam import Gradcam

gc = Gradcam(model, 
             layer_name="top_conv",
             img_path=img_path,
             size=img_size,
             inner_model=model.get_layer("efficientnetb0"))

gc.generate_stack_img(save_name="../output/example_out")

output image

Reference

[1] Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization.