def __init__(self,
numpy_rng=None,
theano_rng=None,
conv_layer_configs=[],
non_maximum_erasing=False,
use_fast=False):
self.conv_layers = []
if not theano_rng:
theano_rng = RandomStreams(numpy_rng.randint(2**30))
# allocate symbolic variables for the data
self.x = T.tensor4('x')
self.conv_layer_num = len(conv_layer_configs)
for i in xrange(self.conv_layer_num):
if i == 0:
input = self.x
else:
input = self.conv_layers[-1].output
config = conv_layer_configs[i]
conv_layer = ConvLayerForward(numpy_rng=numpy_rng,
input=input,
filter_shape=config['filter_shape'],
poolsize=config['poolsize'],
activation=config['activation'],
flatten=config['flatten'],
use_fast=use_fast)
self.conv_layers.append(conv_layer)
def __init__(self,
numpy_rng=None,
theano_rng=None,
cfg=[],
non_maximum_erasing=False,
use_fast=False):
self.conv_layers = []
self.n_outs = cfg.n_outs
self.layers = []
self.extra_layers = []
self.conv_layer_num = len(cfg.conv_layer_configs)
self.dnn_layer_num = len(cfg.hidden_layers_sizes)
self.extra_layers_sizes = cfg.extra_layers_sizes
self.x = T.tensor4('x')
self.extra_x = T.matrix('extra_x')
for i in xrange(self.conv_layer_num):
if i == 0:
input = self.x
else:
input = self.conv_layers[-1].output
config = cfg.conv_layer_configs[i]
print config['filter_shape']
conv_layer = ConvLayerForward(numpy_rng=numpy_rng,
input=input,
filter_shape=config['filter_shape'],
poolsize=config['poolsize'],
activation=config['activation'],
flatten=config['flatten'],
use_fast=use_fast)
self.layers.append(conv_layer)
self.conv_layers.append(conv_layer)
self.conv_output_dim = config['output_shape'][1] * config[
'output_shape'][2] * config['output_shape'][3]
cfg.n_ins = config['output_shape'][1] * config['output_shape'][
2] * config['output_shape'][3]
print self.conv_output_dim
print cfg.n_ins
print 'Extra input dimension: ' + str(cfg.extra_dim)
for i in xrange(len(self.extra_layers_sizes)):
if i == 0:
input_size = cfg.extra_dim
layer_input = self.extra_x
else:
input_size = self.extra_layers_sizes[i - 1]
layer_input = self.extra_layers[-1].output
W = None
b = None
attend_layer = HiddenLayer(rng=numpy_rng,
input=layer_input,
n_in=input_size,
n_out=self.extra_layers_sizes[i],
W=W,
b=b)
self.extra_layers.append(attend_layer)
self.extra_output = self.extra_layers[-1].output
self.extra_output = T.nnet.softmax(self.extra_layers[-1].output)
print 'layer num: ' + str(len(self.layers) - 1)
for i in xrange(self.dnn_layer_num):
if i == 0:
# 1. Join two features (magnitude + phase)
input_size = self.conv_output_dim + self.extra_layers_sizes[-1]
layer_input = T.join(1, self.layers[-1].output,
self.extra_output)
# 2. Weighted Sum (magnitude * phase)
#input_size = self.conv_output_dim
#layer_input = self.layers[-1].output * self.extra_output
else:
input_size = cfg.hidden_layers_sizes[i - 1]
layer_input = self.layers[-1].output
W = None
b = None
hidden_layer = HiddenLayer(rng=numpy_rng,
input=layer_input,
n_in=input_size,
n_out=cfg.hidden_layers_sizes[i],
W=W,
b=b)
self.layers.append(hidden_layer)
print 'layer num: ' + str(len(self.layers) - 1)
logLayer = OutputLayer(input=self.layers[-1].output,
n_in=cfg.hidden_layers_sizes[-1],
n_out=self.n_outs)
self.layers.append(logLayer)
print 'layer num: ' + str(len(self.layers) - 1)
def __init__(self,
numpy_rng=None,
theano_rng=None,
cfg=None,
non_maximum_erasing=False,
use_fast=False):
self.n_outs = cfg.n_outs
self.layers = []
self.extra_layers = []
self.conv_layer_num = len(cfg.conv_layer_configs)
self.dnn_layer_num = len(cfg.hidden_layers_sizes)
self.extra_layers_sizes = cfg.extra_layers_sizes
self.x = T.tensor4('x')
self.extra_x = T.matrix('extra_x')
for i in xrange(self.conv_layer_num):
if i == 0:
input = self.x
else:
input = self.layers[-1].output
config = cfg.conv_layer_configs[i]
conv_layer = ConvLayerForward(numpy_rng=numpy_rng,
input=input,
filter_shape=config['filter_shape'],
poolsize=config['poolsize'],
activation=config['activation'],
flatten=config['flatten'],
use_fast=use_fast)
self.layers.append(conv_layer)
self.conv_output_dim = config['output_shape'][1] * config[
'output_shape'][2] * config['output_shape'][3]
cfg.n_ins = config['output_shape'][1] * config['output_shape'][
2] * config['output_shape'][3]
for i in xrange(len(self.extra_layers_sizes)):
if i == 0:
input_size = 6400 * 5
input_size = cfg.extra_dim
layer_input = self.extra_x
else:
input_size = self.extra_layers_sizes[i - 1]
layer_input = self.extra_layers[-1].output
W = None
b = None
attend_layer = HiddenLayer(rng=numpy_rng,
input=layer_input,
n_in=input_size,
n_out=self.extra_layers_sizes[i],
W=W,
b=b)
self.extra_layers.append(attend_layer)
self.extra_layers[-1].att_e_tl = self.extra_layers[-1].output
self.extra_layers[-1].att_a_tl = T.nnet.softmax(
self.extra_layers[-1].att_e_tl)
#self.extra_layers[-1].att_a_tl = T.exp(self.extra_layers[-1].att_e_tl)/(T.exp(self.extra_layers[-1].att_e_tl)).sum(0,keepdims=True)
for i in xrange(self.dnn_layer_num):
if i == 0:
#input_size = self.conv_output_dim
#layer_input = (self.extra_layers[-1].att_a_tl*self.layers[-1].output)
input_size = self.conv_output_dim + self.extra_layers_sizes[-1]
layer_input = T.join(1, self.extra_layers[-1].att_a_tl,
self.layers[-1].output)
else:
input_size = cfg.hidden_layers_sizes[i - 1]
layer_input = self.layers[-1].output
W = None
b = None
hidden_layer = HiddenLayer(rng=numpy_rng,
input=layer_input,
n_in=input_size,
n_out=cfg.hidden_layers_sizes[i],
W=W,
b=b)
self.layers.append(hidden_layer)
logLayer = OutputLayer(input=self.layers[-1].output,
n_in=cfg.hidden_layers_sizes[-1],
n_out=self.n_outs)
self.layers.append(logLayer)