def wst_net_v1(x_dict, dropout, reuse, is_training, n_classes):
"""Network to follow ST preprocessing.
x should be (...)
"""
psi = win.fst2d_psi_factory([7, 7], include_avg=False)
layer_params = layerO((1, 1), 'valid')
nfeat = 32
with tf.variable_scope('wst_net_v1', reuse=reuse):
x = x_dict['spectrograms']
x = tf.expand_dims(x, -1)
# ..., ...
U1 = scat2d(x, psi, layer_params)
conv = tf.layers.conv2d(U1, nfeat, (7, 1), 1, activation=tf.nn.relu)
conv = tf.layers.conv2d(conv, nfeat, (1, 7), 1, activation=tf.nn.relu)
conv = tf.layers.conv2d(conv, nfeat, 5, 1, activation=tf.nn.relu)
conv = tf.layers.conv2d(conv, nfeat, 5, 2, activation=tf.nn.relu)
conv = tf.layers.conv2d(conv, nfeat, 5, 4, activation=tf.nn.relu)
conv = tf.layers.conv2d(conv, nfeat, 5, 8, activation=tf.nn.relu)
fc = tf.contrib.layers.flatten(conv)
fc = tf.layers.dense(fc, 300)
out = tf.layers.dense(fc, n_classes)
return tf.squeeze(out, axis=1)
def scat2d_to_2d_2layer(x, reuse=tf.AUTO_REUSE, bs=batch_size):
"""
Args:
x: in (batch, h, w, 1) shape
Returns
(batch, h, w, channels)
"""
psis = [None, None]
layer_params = [None, None, None]
with tf.variable_scope('scat2d_to_2d_2layer', reuse=reuse):
# TF Estimator input is a dict, in case of multiple inputs
psis[0] = win.fst2d_psi_factory([7, 7], include_avg=False)
layer_params[0] = layerO((1, 1), 'valid')
# 107, 107
U1 = scat2d(x, psis[0], layer_params[0])
psis[1] = win.fst2d_psi_factory([7, 7], include_avg=False)
layer_params[1] = layerO((1, 1), 'valid')
U2s = []
# only procede with increasing frequency paths
for res_i, used_params in enumerate(psis[0].filter_params):
increasing_psi = win.fst2d_psi_factory(psis[1].kernel_size,
used_params)
if increasing_psi.nfilt > 0:
U2s.append(
scat2d(U1[:, :, :, res_i:(res_i + 1)], increasing_psi,
layer_params[1]))
# 101, 101
U2 = tf.concat(U2s, 3)
# swap to (batch, chanU2, h, w)
U2 = tf.transpose(U2, [0, 3, 1, 2])
# reshape to (batch, h,w, 1)
U2os = U2.get_shape()
U2 = tf.reshape(
U2,
(bs * U2.get_shape()[1], U2.get_shape()[2], U2.get_shape()[3], 1))
# swap to (batch, chanU1, h, w)
U1 = tf.transpose(U1, [0, 3, 1, 2])
# reshape to (batch, h,w, 1)
U1os = U1.get_shape()
U1 = tf.reshape(
U1,
(bs * U1.get_shape()[1], U1.get_shape()[2], U1.get_shape()[3], 1))
# now lo-pass
# each layer lo-passed differently so that (h,w) align bc we
# want to be able to do 2d convolutions afterwards again
layer_params[2] = layerO((1, 1), 'valid')
phi = win.fst2d_phi_factory([5, 5])
# filter and separate by original batch via old shape
S0 = scat2d(x[:, 6:-6, 6:-6, :], phi, layer_params[2])
S0 = tf.reshape(S0, (bs, 1, S0.get_shape()[1], S0.get_shape()[2]))
S1 = scat2d(U1[:, 3:-3, 3:-3, :], phi, layer_params[2])
S1 = tf.reshape(S1,
(bs, U1os[1], S1.get_shape()[1], S1.get_shape()[2]))
S2 = scat2d(U2, phi, layer_params[2])
S2 = tf.reshape(S2,
(bs, U2os[1], S2.get_shape()[1], S2.get_shape()[2]))
# (batch, chan, h,w)
feat2d = tf.concat([S0, S1, S2], 1)
return tf.transpose(feat2d, [0, 2, 3, 1])