Skip to content

Instantly share code, notes, and snippets.

Avatar
🎩
Being awesome as always

Tero Keski-Valkama keskival

🎩
Being awesome as always
View GitHub Profile
View wavenet.py
def mu_law(x, mu):
return np.sign(x) * np.log(1 + mu * np.abs(x)) / np.log(1 + mu)
# value shape is [batches, width, D]
# filters shape is [width, D, C]
def causal_atrous_conv1d(value, filters, rate, padding):
# Using height in 2-D as the 1-D.
value_2d = tf.expand_dims(value, 2)
filters_2d = tf.expand_dims(filters, 1)
# Note that for filters using 'SAME' padding, padding zeros are added to the end of the input.
@keskival
keskival / report.txt
Created Jan 29, 2016
My high performance computing platform for deep neural networks.
View report.txt
tero@Curie:~$ cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 60
model name : Intel(R) Core(TM) i5-4690 CPU @ 3.50GHz
stepping : 3
microcode : 0x19
cpu MHz : 898.515
cache size : 6144 KB