def build_layer(line,
layer_in,
seq_length=None,
keep_in_prob=None,
keep_out_prob=None):
layer_type, info = line.split(' ', 1)
if layer_type == '<AffineTransform>':
layer_out = layer.affine_transform(info, layer_in)
if layer_type == '<LinearTransform>':
layer_out = layer.linear_transform(info, layer_in)
elif layer_type == '<BatchNormalization>':
layer_out = layer.batch_normalization(info, layer_in)
elif layer_type == '<Sigmoid>':
layer_out = tf.sigmoid(layer_in)
elif layer_type == '<Relu>':
layer_out = tf.nn.relu(layer_in)
elif layer_type == '<Tanh>':
layer_out = tf.tanh(layer_in)
elif layer_type == '<Softmax>':
layer_out = tf.nn.softmax(layer_in)
elif layer_type == '<Dropout>':
layer_out = tf.nn.dropout(layer_in, float(info))
elif layer_type == '<LSTM>':
layer_out = layer.lstm(info, layer_in, seq_length, keep_in_prob,
keep_out_prob)
elif layer_type == '<BLSTM>':
layer_out = layer.blstm(info, layer_in, seq_length, keep_in_prob,
keep_out_prob)
return layer_out
def convolve(self, image, training, keep_prob):
result = layer.batch_normalization(image, training)
result = layer.conv_relu(result, 1, 18, width=5, padding="VALID")
result = layer.max_pool(result) # 12
result = layer.conv_relu(result, 18, 24, width=5, padding="VALID")
result = layer.max_pool(result) # 4
result = tf.nn.dropout(result, keep_prob)
return layer.conv(result, 24, 10, width=4, padding="VALID")
def convolve(self, image, training, keep_prob):
result = layer.batch_normalization(image, training)
result = layer.conv_relu(result,
1,
18,
width=5,
stride=2,
padding="VALID")
return layer.conv(result, 18, 10, width=12, padding="VALID")
def convolve(self, image, training, keep_prob):
result = layer.batch_normalization(image, training)
result = layer.conv_relu(result, 1, 18, width=5)
result = layer.max_pool(result) # 14
result = tf.nn.relu(drop_conv(keep_prob, result, 18, 24, width=5))
result = layer.max_pool(result) # 7
result = tf.nn.relu(
drop_conv(keep_prob, result, 24, 32, width=5, padding="VALID"))
return layer.conv(result, 32, 10, width=3, padding="VALID")
def build_layer(line,
layer_in,
seq_length=None,
mask_holder=None,
keep_in_prob=None,
keep_out_prob=None,
keep_prob=None,
reuse=False):
layer_type, info = line.split(' ', 1)
if layer_type == '<AffineTransform>':
layer_out = layer.affine_transform(info, layer_in)
elif layer_type == '<LinearTransform>':
layer_out = layer.linear_transform(info, layer_in)
elif layer_type == '<BatchNormalization>':
layer_out = layer.batch_normalization(info, layer_in)
elif layer_type == '<AffineBatchNormalization>':
layer_out = layer.affine_batch_normalization(info, layer_in)
elif layer_type == '<TDNNAffineTransform>':
layer_out = layer.tdnn_affine_transform(info, layer_in)
elif layer_type == '<Sigmoid>':
layer_out = tf.sigmoid(layer_in)
elif layer_type == '<Relu>':
layer_out = tf.nn.relu(layer_in)
elif layer_type == '<Relu6>':
layer_out = tf.nn.relu6(layer_in)
elif layer_type == '<Tanh>':
layer_out = tf.tanh(layer_in)
elif layer_type == '<Softmax>':
layer_out = tf.nn.softmax(layer_in)
elif layer_type == '<Dropout>':
layer_out = tf.nn.dropout(layer_in, keep_prob)
elif layer_type == '<LSTM>':
layer_out = layer.lstm(info,
layer_in,
seq_length,
keep_in_prob,
keep_out_prob,
reuse=reuse)
elif layer_type == '<BLSTM>':
layer_out = layer.blstm(info,
layer_in,
seq_length,
keep_in_prob,
keep_out_prob,
reuse=reuse)
elif layer_type == '<Pooling>':
layer_out = layer.pooling(info, layer_in, mask_holder, reuse=reuse)
else:
raise RuntimeError("layer_type %s not supported" % layer_type)
return layer_out
def convolve(self, image, training, keep_prob):
result = image
result = layer.batch_normalization(result, training)
result = layer.conv(result, 1, 16, width=5, stride=2, padding="VALID")
result = tf.nn.tanh(result)
result = layer.conv(result, 16, 16, width=3, stride=2, padding="VALID")
result = tf.nn.tanh(result)
result = layer.conv(result, 16, 32, width=3, padding="VALID")
result = tf.nn.tanh(result)
result = layer.conv(result, 32, 32, width=3, padding="VALID")
result = tf.nn.tanh(result)
result = tf.nn.dropout(result, keep_prob)
result = layer.conv_relu(result, 32, 10, width=1, padding="VALID")
return result
def convolve(self, image, training, keep_prob):
result = layer.batch_normalization(image, training)
result = layer.conv_relu(result, 1, 18, width=5)
result = layer.resnet_block(result, 18, 3, training, momentum=0.99)
result = layer.max_pool(result) # 14
result = layer.resnet_block(result, 18, 3, training, momentum=0.99)
result = layer.conv_relu(result, 18, 24, width=5)
result = layer.resnet_block(result, 24, 3, training, momentum=0.99)
result = layer.max_pool(result) # 7
result = layer.resnet_block(result, 24, 3, training, momentum=0.99)
result = layer.conv_relu(result, 24, 32, width=5, padding="VALID")
result = layer.resnet_block(result, 32, 3, training, momentum=0.99)
result = tf.nn.dropout(result, keep_prob)
return layer.conv(result, 32, 10, width=3, padding="VALID")
def convolve(self, image, training, keep_prob):
result = layer.batch_normalization(image, training)
result = layer.conv_relu(result, 1, 18, width=5)
result = layer.max_pool(result) # 14
result = layer.resnet_block(result, 18, 3, training)
result = layer.conv_relu(result, 18, 24, width=3)
result = layer.max_pool(result) # 7
result = layer.resnet_block(result, 24, 3, training)
result = layer.resnet_block(result, 24, 3, training)
return layer.drop_conv(keep_prob,
result,
24,
10,
width=7,
padding="VALID")
def convolve(self, image, training, keep_prob):
result = layer.batch_normalization(image, training)
result = layer.conv_relu(result, 1, 18, width=5, padding="VALID")
result = layer.max_pool(result) # 12
result = layer.resnet_block(result, 18, 3, training)
result = layer.resnet_block(result, 18, 3, training)
result = layer.max_pool(result) # 6
result = layer.conv_relu(result, 18, 24, width=1)
result = layer.resnet_narrow(result, 24, 3, training)
result = layer.resnet_narrow(result, 24, 3, training)
result = layer.max_pool(result) # 3
result = layer.conv_relu(result, 24, 32, width=1)
result = layer.resnet_narrow(result, 32, 3, training)
result = layer.resnet_narrow(result, 32, 3, training)
return layer.drop_conv(keep_prob,
result,
32,
10,
width=3,
padding="VALID")
