def __init__(self,which_set,numclass,
base_path = '/data/vision/billf/manifold-learning/DL/Data/icml_2013_emotions',
start = 0,
stop = -1,
options = [0],
axes = ('b', 0, 1, 'c'),
fit_test_preprocessor = False,
):
files = {'train': 'train.csv', 'public_test' : 'test.csv'}
try:
file_path = files[which_set]
except KeyError:
raise ValueError("Unrecognized dataset name: " + which_set)
X, y = self.loadFile(base_path + '/' + file_path, start,stop)
# train_index
if flip:
X_list_flipLR, X_list_flipUD = self.flipData(X)
X = X + X_list_flipLR
y = y + y
view_converter = DefaultViewConverter(shape=(48,48,1), axes=axes)
super(ICML_emotion, self).__init__(X=X, y=self.label_id2arr(y,numclass), view_converter=view_converter)
if options[0] == 1:
fit_preprocessor = False
from pylearn2.datasets.preprocessing import GlobalContrastNormalization
preprocessor = GlobalContrastNormalization(sqrt_bias = 10,use_std = 1)
preprocessor.apply(self, can_fit=fit_preprocessor)
def preprocess(self):
pre = GlobalContrastNormalization(sqrt_bias=10, use_std=1)
self = pre.apply(self)
def preprocess(self):
pre = GlobalContrastNormalization(sqrt_bias = 10,use_std = 1)
self = pre.apply(self)
def make_majority_vote():
model_paths = ['convnet_' + str(i + 1) + '.pkl' for i in range(10)]
out_path = 'submission.csv'
models = []
for model_path in model_paths:
print('Loading ' + model_path + '...')
try:
with open(model_path, 'rb') as f:
models.append(pkl.load(f))
except Exception as e:
try:
with gzip.open(model_path, 'rb') as f:
models.append(pkl.load(f))
except Exception as e:
usage()
print(
model_path +
"doesn't seem to be a valid model path, I got this error when trying to load it: "
)
print(e)
# load the test set
with open('test_data_for_pylearn2.pkl', 'rb') as f:
dataset = pkl.load(f)
dataset = DenseDesignMatrix(X=dataset,
view_converter=DefaultViewConverter(
shape=[32, 32, 1], axes=['b', 0, 1, 'c']))
preprocessor = GlobalContrastNormalization(subtract_mean=True,
sqrt_bias=0.0,
use_std=True)
preprocessor.apply(dataset)
predictions = []
print('Model description:')
print('')
print(models[1])
print('')
for model in models:
model.set_batch_size(dataset.X.shape[0])
X = model.get_input_space().make_batch_theano()
Y = model.fprop(X) # forward prop the test data
y = T.argmax(Y, axis=1)
f = function([X], y)
x_arg = dataset.get_topological_view()
y = f(x_arg.astype(X.dtype))
assert y.ndim == 1
assert y.shape[0] == dataset.X.shape[0]
# add one to the results!
y += 1
predictions.append(y)
predictions = np.array(predictions, dtype='int32')
y = mode(predictions.T, axis=1)[0]
y = np.array(y, dtype='int32')
import itertools
y = list(itertools.chain(*y))
assert len(y) == dataset.X.shape[0]
util.write_results(y, out_path)
print('Wrote predictions to submission.csv.')
return np.reshape(y, (1, -1))
from pylearn2.datasets.preprocessing import Standardize, LeCunLCN, GlobalContrastNormalization
from pylearn2.datasets.tfd import TFD
import cPickle as pkl
theano.subtensor_merge_bug=False
if __name__ == "__main__":
weights_file = "../out/pae_mnist_enc_weights.npy"
input = T.matrix("X", dtype=theano.config.floatX)
tfd_ds = TFD("unlabeled")
print "TFD shape: ", tfd_ds.X.shape
gcn = GlobalContrastNormalization()
standardizer = Standardize()
lcn = LeCunLCN(img_shape=(48, 48), channels=[0])
gcn.apply(tfd_ds, can_fit=True)
standardizer.apply(tfd_ds, can_fit=True)
lcn.apply(tfd_ds)
rnd = numpy.random.RandomState(1231)
powerup = PowerupAutoencoder(input,
nvis=48*48,
nhid=500,
momentum=0.66,
rho=0.92,
num_pieces=4,
cost_type="MeanSquaredCost",
L2_reg=8.2*1e-5,
L1_reg=1.2 * 1e-5,
L1_act_reg=8.8*1e-4,
def make_majority_vote():
model_paths = ['convnet_' + str(i+1) + '.pkl' for i in range(10)]
out_path = 'submission.csv'
models = []
for model_path in model_paths:
print('Loading ' + model_path + '...')
try:
with open(model_path, 'rb') as f:
models.append(pkl.load(f))
except Exception as e:
try:
with gzip.open(model_path, 'rb') as f:
models.append(pkl.load(f))
except Exception as e:
usage()
print(model_path + "doesn't seem to be a valid model path, I got this error when trying to load it: ")
print(e)
# load the test set
with open('test_data_for_pylearn2.pkl', 'rb') as f:
dataset = pkl.load(f)
dataset = DenseDesignMatrix(X=dataset, view_converter=DefaultViewConverter(shape=[32, 32, 1], axes=['b', 0, 1, 'c']))
preprocessor = GlobalContrastNormalization(subtract_mean=True, sqrt_bias=0.0, use_std=True)
preprocessor.apply(dataset)
predictions = []
print('Model description:')
print('')
print(models[1])
print('')
for model in models:
model.set_batch_size(dataset.X.shape[0])
X = model.get_input_space().make_batch_theano()
Y = model.fprop(X) # forward prop the test data
y = T.argmax(Y, axis=1)
f = function([X], y)
x_arg = dataset.get_topological_view()
y = f(x_arg.astype(X.dtype))
assert y.ndim == 1
assert y.shape[0] == dataset.X.shape[0]
# add one to the results!
y += 1
predictions.append(y)
predictions = np.array(predictions, dtype='int32')
y = mode(predictions.T, axis=1)[0]
y = np.array(y, dtype='int32')
import itertools
y = list(itertools.chain(*y))
assert len(y) == dataset.X.shape[0]
util.write_results(y, out_path)
print('Wrote predictions to submission.csv.')
return np.reshape(y, (1, -1))
from pylearn2.datasets.tfd import TFD
import pickle as pkl
theano.subtensor_merge_bug = False
if __name__ == "__main__":
weights_file = "../out/pae_mnist_enc_weights.npy"
input = T.matrix("X", dtype=theano.config.floatX)
tfd_ds = TFD("unlabeled")
print(("TFD shape: ", tfd_ds.X.shape))
gcn = GlobalContrastNormalization()
standardizer = Standardize()
lcn = LeCunLCN(img_shape=(48, 48), channels=[0])
gcn.apply(tfd_ds, can_fit=True)
standardizer.apply(tfd_ds, can_fit=True)
lcn.apply(tfd_ds)
rnd = numpy.random.RandomState(1231)
powerup = PowerupAutoencoder(input,
nvis=48 * 48,
nhid=500,
momentum=0.66,
rho=0.92,
num_pieces=4,
cost_type="MeanSquaredCost",
L2_reg=8.2 * 1e-5,
L1_reg=1.2 * 1e-5,
L1_act_reg=8.8 * 1e-4,
