Ejemplo n.º 1
0
def load_verbatimnet( layer, params='/fileserver/iam/iam-processed/models/fiel_1k.hdf5' ):

    print "Establishing Fiel's verbatim network"
    vnet = verbatimnet(layer)
    loadparams( vnet, params )
    vnet.compile( loss='mse', optimizer='sgd' )
    print "Compiled neural network up to FC7 layer"    
    
    return vnet
Ejemplo n.º 2
0
def load_verbatimnet( layer, input_shape=(1,56,56), params='/fileserver/iam/iam-processed/models/fiel_1k.hdf5' ):

    print "Establishing Fiel's verbatim network"
    vnet = verbatimnet(layer=layer, input_shape=input_shape)
    loadparams( vnet, params )
    vnet.compile( loss='mse', optimizer='sgd' )
    print "Compiled neural network up to FC7 layer"    
    
    return vnet
Ejemplo n.º 3
0

# ### Parameter Definitions
labels = h5py.File(hdf5authors, 'r')
num_authors=len(labels)
num_forms_per_author=-1
shingle_dim=(120,120)
batch_size=32
load_size=batch_size*1000
iterations = 1000
lr = 0.001

### Define your model
# Here, we're using the Fiel Network
# vnet = load_verbatimnet( 'fc7', paramsfile=paramsfile, compiling=False )
vnet = verbatimnet( layer='fc7', input_shape=(1,)+shingle_dim, compiling=False )
vnet.add(Dense(num_authors))
vnet.add(Activation('softmax'))
sgd = SGD(lr=lr, decay=1e-6, momentum=0.9, nesterov=True)
vnet.compile(loss='categorical_crossentropy', optimizer=sgd)
print "Finished compilation"


# ### Minibatcher (to load in your data for each batch)
if False:
    mini_m = Hdf5MiniBatcher(hdf5authors, num_authors, num_forms_per_author,
                            shingle_dim=shingle_dim, default_mode=MiniBatcher.TRAIN,
                            batch_size=batch_size, add_rotation=True)
else:
    mini_m = IAM_MiniBatcher(hdf5authors, num_authors, num_forms_per_author,
                            shingle_dim=shingle_dim, default_mode=MiniBatcher.TRAIN,
Ejemplo n.º 4
0
# ### Parameter Definitions
labels = h5py.File(hdf5authors, 'r')
num_authors = len(labels)
num_forms_per_author = -1
shingle_dim = (120, 120)
batch_size = 32
load_size = batch_size * 1000
iterations = 1000
lr = 0.001

### Define your model
# Here, we're using the Fiel Network
# vnet = load_verbatimnet( 'fc7', paramsfile=paramsfile, compiling=False )
vnet = verbatimnet(layer='fc7',
                   input_shape=(1, ) + shingle_dim,
                   compiling=False)
vnet.add(Dense(num_authors))
vnet.add(Activation('softmax'))
sgd = SGD(lr=lr, decay=1e-6, momentum=0.9, nesterov=True)
vnet.compile(loss='categorical_crossentropy', optimizer=sgd)
print "Finished compilation"

# ### Minibatcher (to load in your data for each batch)
if False:
    mini_m = Hdf5MiniBatcher(hdf5authors,
                             num_authors,
                             num_forms_per_author,
                             shingle_dim=shingle_dim,
                             default_mode=MiniBatcher.TRAIN,
                             batch_size=batch_size,