Why trainable parameters are not considered right?

Question

Why trainable parameters are not considered right?

Olfa2

2021年6月14日 17:05

I have tested the ResNet block and it works fine, but when I call it in the model class, it somehow it does not work properly? Is it related to the model definition?

Topic inceptionresnetv2 cnn convolutional-neural-network tensorflow deep-learning

Category Data Science

spb · Accepted Answer · 2021年5月29日 14:06

In your code by default training=False, set training=True it will work right.

Also, since you are already subclassing keras.Model you don't need to again call keras.Model. Remove the model() method, pass the input directly to call() method by setting training=True.

Why trainable parameters are not considered right?

About