from pylearn2.models import mlp, maxout
from pylearn2.costs.mlp.dropout import Dropout
from pylearn2.training_algorithms import sgd, learning_rule
from pylearn2.termination_criteria import EpochCounter
from pylearn2.datasets import cifar10
from kaggle_dataset import kaggle_cifar10
from pylearn2.datasets.preprocessing import Pipeline, ZCA
from pylearn2.datasets.preprocessing import GlobalContrastNormalization
from pylearn2.space import Conv2DSpace
from pylearn2.train import Train
from pylearn2.train_extensions import best_params, window_flip
from pylearn2.utils import serial
trn = kaggle_cifar10('train',
one_hot=True,
datapath='/home/kkastner/kaggle_data/kaggle-cifar10',
max_count=40000,
axes=('c', 0, 1, 'b'))
tst = cifar10.CIFAR10('test',
toronto_prepro=False,
one_hot=True,
axes=('c', 0, 1, 'b'))
in_space = Conv2DSpace(shape=(32, 32),
num_channels=3,
axes=('c', 0, 1, 'b'))
l1 = maxout.MaxoutConvC01B(layer_name='l1',
pad=4,
tied_b=1,
for i in xrange(ds.X.shape[0] / batch_size):
x_arg = ds.X[i * batch_size:(i + 1) * batch_size, :]
x_arg = ds.get_topological_view(x_arg)
yhat.append(f(x_arg.astype(X.dtype)))
return np.array(yhat)
preprocessor = serial.load('kaggle_cifar10_preprocessor.pkl')
mdl = serial.load('kaggle_cifar10_maxout_zca.pkl')
fname = 'kaggle_cifar10_results.csv'
test_size = 100000
sets = 300000 / test_size
res = np.zeros((sets, test_size), dtype='float32')
for n, i in enumerate([test_size * x for x in range(sets)]):
ds = kaggle_cifar10('test',
datapath='/home/kkastner/kaggle_data/kaggle-cifar10',
one_hot=True,
start_idx=i,
max_count=test_size,
axes=('c', 0, 1, 'b'))
ds.apply_preprocessor(preprocessor=preprocessor, can_fit=False)
yhat = process(mdl, ds)
print "start_idx", i
res[n, :] = yhat.ravel()
converted_results = [['id', 'label']] + [[n + 1, ds.unconvert(int(x))]
for n, x in enumerate(res.ravel())]
with open(fname, 'w') as f:
csv_f = csv.writer(f, delimiter=',', quoting=csv.QUOTE_NONE)
csv_f.writerows(converted_results)
