The vizgradcam's discuss from gkeechin

View Code? Open in Web Editor NEW

vizgradcam is the fastest way to visualize GradCAM with your Keras models.

License: MIT License

Python 100.00%

vizgradcam's Issues

last_conv_layer fails for Transfer Learning Models

Creating a transfer learning model using Keras.Applications yields a model.summary() such as:

Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_2 (InputLayer)         [(None, 160, 160, 3)]     0         
_________________________________________________________________
sequential (Sequential)      (None, 160, 160, 3)       0         
_________________________________________________________________
tf.math.truediv (TFOpLambda) (None, 160, 160, 3)       0         
_________________________________________________________________
tf.math.subtract (TFOpLambda (None, 160, 160, 3)       0         
_________________________________________________________________
mobilenetv2_1.00_160 (Functi (None, 5, 5, 1280)        2257984   
_________________________________________________________________
global_average_pooling2d (Gl (None, 1280)              0         
_________________________________________________________________
dropout (Dropout)            (None, 1280)              0         
_________________________________________________________________
dense (Dense)                (None, 1)                 1281      
=================================================================
Total params: 2,259,265
Trainable params: 1,281
Non-trainable params: 2,257,984
_________________________________________________________________

Note the Functional layer mobilenetv2_1.00_160 which hides the underlying base_model.

VizGradCAM fails to find the last convolutional layer as it doesn't "dive into" the Functional base_model.

Recommend Projects