New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

how dialated convolution actually work ? #382

Open

SlowMonk opened this issue Jun 7, 2019 · 0 comments

SlowMonk commented Jun 7, 2019

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 ])

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment