how dialated convolution actually work ?
SlowMonk opened this issue · comments
archeion commented
can someone tell me how this result came out?
and if change to dialated to 2 ? what will happen??
conv = layers.Conv1D(1, 3, padding='causal',
dilation_rate=1,
bias_initializer=tf.keras.initializers.zeros)
np.squeeze(sequence.numpy())
->array([0. , 0.46517092, 0.82355802, 0.99289061, 0.93429699])
np.squeeze(conv.trainable_variables[0].numpy())
->array([-0.19279779, 0.55129746, -0.52658171])
output = conv(sequence)
np.squeeze(output.numpy())
->array([ 0. , -0.2449505 , -0.17722305, -0.15849652, -0.1033858 ])