batch_size = 128
debug = 0
model = Model()
train_data = MNIST(name='train',
path=data_path)
valid_data = MNIST(name='valid',
path=data_path)
# Choose the random initialization method
init_W = InitCell('rand')
init_b = InitCell('zeros')
# Define nodes: objects
x, y = train_data.theano_vars()
mn_x, mn_y = valid_data.theano_vars()
# You must use THEANO_FLAGS="compute_test_value=raise" python -m ipdb
if debug:
x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
y.tag.test_value = np.zeros((batch_size, 1), dtype=np.float32)
mn_x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
mn_y.tag.test_value = np.zeros((batch_size, 1), dtype=np.float32)
h1 = FullyConnectedLayer(name='h1',
parent=['x'],
parent_dim=[784],
nout=1000,
unit='relu',
init_W=init_W,
init_b=init_b)
save_path = '/home/junyoung/src/cle/saved/'
batch_size = 128
debug = 0
model = Model()
train_data = MNIST(name='train', path=data_path)
valid_data = MNIST(name='valid', path=data_path)
# Choose the random initialization method
init_W = InitCell('randn')
init_b = InitCell('zeros')
# Define nodes: objects
x, y = train_data.theano_vars()
# You must use THEANO_FLAGS="compute_test_value=raise" python -m ipdb
if debug:
x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
y.tag.test_value = np.zeros((batch_size, 1), dtype=np.float32)
h1 = FullyConnectedLayer(name='h1',
parent=['x'],
parent_dim=[784],
nout=1000,
unit='relu',
init_W=init_W,
init_b=init_b)
output = FullyConnectedLayer(name='output',
parent=['h1'],
inpsz = 784
latsz = 100
n_steps = 64
debug = 0
model = Model()
data = MNIST(name='train',
unsupervised=1,
path=datapath)
init_W = InitCell('rand')
init_U = InitCell('ortho')
init_b = InitCell('zeros')
init_b_sig = InitCell('const', mean=0.6)
x, _ = data.theano_vars()
if debug:
x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
error = ErrorLayer(name='error',
parent=['x'],
recurrent=['canvas'],
batch_size=batch_size)
read_param = FullyConnectedLayer(name='read_param',
parent=['dec_tm1'],
parent_dim=[256],
nout=5,
unit='linear',
init_W=init_W,
init_b=init_b)
# Set your dataset
data_path = '/data/lisa/data/mnist/mnist.pkl'
save_path = '/u/chungjun/src/cle/saved/'
batch_size = 128
debug = 0
model = Model()
train_data = MNIST(name='train',
path=data_path)
valid_data = MNIST(name='valid',
path=data_path)
# Define nodes: objects
x, y = train_data.theano_vars()
# You must use THEANO_FLAGS="compute_test_value=raise" python -m ipdb
if debug:
x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
y.tag.test_value = np.zeros((batch_size, 1), dtype=np.float32)
# Choose the random initialization method
init_W = InitCell('rand')
init_b = InitCell('zeros')
h1 = FullyConnectedLayer(name='h1',
parent=['x'],
parent_dim=[784],
nout=1000,
unit='relu',
batch_size = 100
input_dim = 784
latent_dim = 100
n_steps = 64
debug = 0
model = Model()
data = MNIST(name='train', unsupervised=1, path=datapath)
init_W = InitCell('rand')
init_U = InitCell('ortho')
init_b = InitCell('zeros')
init_b_sig = InitCell('const', mean=0.6)
x, _ = data.theano_vars()
if debug:
x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
error = ErrorLayer(name='error',
parent=['x'],
recurrent=['canvas'],
batch_size=batch_size)
read_param = FullyConnectedLayer(name='read_param',
parent=['dec_tm1'],
parent_dim=[256],
nout=5,
unit='linear',
init_W=init_W,
init_b=init_b)
#save_path = '/home/junyoung/src/cle/saved/'
batch_size = 128
debug = 0
model = Model()
train_data = MNIST(name='train', path=data_path)
valid_data = MNIST(name='valid', path=data_path)
# Choose the random initialization method
init_W = InitCell('rand')
init_b = InitCell('zeros')
# Define nodes: objects
x, y = train_data.theano_vars()
mn_x, mn_y = valid_data.theano_vars()
# You must use THEANO_FLAGS="compute_test_value=raise" python -m ipdb
if debug:
x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
y.tag.test_value = np.zeros((batch_size, 1), dtype=np.float32)
mn_x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
mn_y.tag.test_value = np.zeros((batch_size, 1), dtype=np.float32)
h1 = FullyConnectedLayer(name='h1',
parent=['x'],
parent_dim=[784],
nout=1000,
unit='relu',
init_W=init_W,
init_b=init_b)
batch_size = 128
debug = 0
model = Model()
trdata = MNIST(name='train',
path=data_path)
valdata = MNIST(name='valid',
path=data_path)
# Choose the random initialization method
init_W = InitCell('randn')
init_b = InitCell('zeros')
# Define nodes: objects
model.inputs = trdata.theano_vars()
x, y = model.inputs
# You must use THEANO_FLAGS="compute_test_value=raise" python -m ipdb
if debug:
x.tag.test_value = np.zeros((batch_size, 784), dtype=np.float32)
y.tag.test_value = np.zeros((batch_size, 1), dtype=np.float32)
inputs = [x, y]
inputs_dim = {'x':784, 'y':1}
onehot = OnehotLayer(name='onehot',
parent=['y'],
nout=10)
h1 = FullyConnectedLayer(name='h1',
parent=['x'],