Closed kirarenctaon closed 5 years ago
In section 2.3, you described the backprop_dense like this :
def backprop_dense(activation, kernel, bias, relevance): W_p = tf.maximum(0., kernel) b_p = tf.maximum(0., bias) z_p = tf.matmul(activation, W_p) + b_p s_p = relevance / z_p c_p = tf.matmul(s_p, tf.transpose(W_p)) W_n = tf.maximum(0., kernel) b_n = tf.maximum(0., bias) z_n = tf.matmul(activation, W_n) + b_n s_n = relevance / z_n c_n = tf.matmul(s_n, tf.transpose(W_n)) return activation * (self.alpha * c_p + (1 - self.alpha) * c_n)
For negative case, it would be betterr to change "tf.maximun" to "tf.minimun". The LRP class in models_2_3 also uses "tf.minimun".
Btw, your tutorials are really helpful for me. Thanks :)
Thank you for pointing that out! I fixed the typo.
I'm glad you found the tutorials helpful!
In section 2.3, you described the backprop_dense like this :
For negative case, it would be betterr to change "tf.maximun" to "tf.minimun". The LRP class in models_2_3 also uses "tf.minimun".
Btw, your tutorials are really helpful for me. Thanks :)