def inference2(input_tensor,
n_classes,
train=True,
regularizer=None,
evaluate=False):
input_tensor = layers.full_connect('fc1',
input_tensor,
out_nodes=512,
regularizer=regularizer)
# input_tensor = layers.full_connect('fc2', input_tensor, out_nodes=256, regularizer=regularizer)
# input_tensor = layers.full_connect('fc3', input_tensor, out_nodes=128, regularizer=regularizer)
output_tensor = layers.full_connect_not_relu('fc4',
input_tensor,
out_nodes=n_classes,
regularizer=regularizer)
return output_tensor
def inference(input_tensor,
n_classes,
train=True,
regularizer=None,
evaluate=False):
with tf.name_scope('cnn'):
input_tensor = layers.conv('conv1',
input_tensor,
out_channels=32,
kernel_size=[2, 2],
strides=[1, 2, 2, 1],
train=train)
input_tensor = layers.pool('pool1',
input_tensor,
kernel_size=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
by_max=True)
input_tensor = layers.conv('conv2',
input_tensor,
out_channels=64,
kernel_size=[2, 2],
strides=[1, 1, 1, 1],
train=train)
input_tensor = layers.batch_norm(input_tensor)
input_tensor = layers.pool('pool2',
input_tensor,
kernel_size=[1, 2, 2, 1],
strides=[1, 1, 1, 1],
by_max=True)
input_tensor = layers.full_connect('fc1',
input_tensor,
out_nodes=512,
regularizer=regularizer)
output_tensor = layers.full_connect_not_relu('fc2',
input_tensor,
out_nodes=n_classes,
regularizer=regularizer)
return output_tensor
def create_architecture(self, mode, hdf5_data):
"""Returns the architecture (i.e., caffe prototxt) of the model.
Jer: One day this should probably be written to be more general.
"""
arch = self.arch
pars = self.pars
n = caffe.NetSpec()
if mode == 'deploy':
n.data = L.DummyData(shape=[dict(dim=pars['deploy_dims'])])
elif mode == 'train':
n.data, n.label = L.HDF5Data(batch_size=pars['train_batch_size'],
source=hdf5_data,
ntop=pars['ntop'])
else: # Test.
n.data, n.label = L.HDF5Data(batch_size=pars['test_batch_size'],
source=hdf5_data,
ntop=pars['ntop'])
# print(n.to_proto())
in_layer = n.data1
for layer in arch:
layer_type, vals = layer
if layer_type == 'e2e':
in_layer = n.e2e = e2e_conv(in_layer, vals['n_filters'],
vals['kernel_h'], vals['kernel_w'])
elif layer_type == 'e2n':
in_layer = n.e2n = e2n_conv(in_layer, vals['n_filters'],
vals['kernel_h'], vals['kernel_w'])
elif layer_type == 'fc':
in_layer = n.fc = full_connect(in_layer, vals['n_filters'])
elif layer_type == 'out':
n.out = full_connect(in_layer, vals['n_filters'])
# Rename to user specified unique layer name.
# n.__setattr__('out', n.new_layer)
elif layer_type == 'dropout':
in_layer = n.dropout = L.Dropout(
in_layer,
in_place=True,
dropout_param=dict(dropout_ratio=vals['dropout_ratio']))
elif layer_type == 'relu':
in_layer = n.relu = L.ReLU(
in_layer,
in_place=True,
relu_param=dict(negative_slope=vals['negative_slope']))
else:
raise ValueError('Unknown layer type: ' + str(layer_type))
# ~ end for.
if mode != 'deploy':
if self.pars['loss'] == 'EuclideanLoss':
n.loss = L.EuclideanLoss(n.out, n.label)
else:
ValueError(
"Only 'EuclideanLoss' currently implemented for pars['loss']!"
)
return n