from scae_destin.convnet import SigmoidConvLayer
from scae_destin.model import ConvAutoEncoder
from scae_destin.convnet import MaxPoolingSameSize, MaxPooling
from scae_destin.convnet import Flattener
from scae_destin.model import FeedForward
from scae_destin.optimize import gd_updates
from scae_destin.cost import mean_square_cost
from scae_destin.cost import categorical_cross_entropy_cost
from scae_destin.cost import L2_regularization
start_time = time.time()
n_epochs = 100
batch_size = 100
nkerns = 100
Xtr, Ytr, Xte, Yte = ds.load_CIFAR10("../cifar-10-batches-py/")
Xtr = np.mean(Xtr, 3)
Xte = np.mean(Xte, 3)
Xtrain = Xtr.reshape(Xtr.shape[0], Xtr.shape[1] * Xtr.shape[2]) / 255.0
Xtest = Xte.reshape(Xte.shape[0], Xte.shape[1] * Xte.shape[2]) / 255.0
train_set_x, train_set_y = ds.shared_dataset((Xtrain, Ytr))
test_set_x, test_set_y = ds.shared_dataset((Xtest, Yte))
n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
n_test_batches = test_set_x.get_value(borrow=True).shape[0] / batch_size
print "[MESSAGE] The data is loaded"
################################## FIRST LAYER #######################################
import numpy as np;
import sys
import theano;
import theano.tensor as T;
sys.path.append("..")
import scae_destin.datasets as ds;
from scae_destin.convnet import ReLUConvLayer;
from scae_destin.convnet import LCNLayer
n_epochs=1;
batch_size=100;
Xtr, Ytr, Xte, Yte=ds.load_CIFAR10("/home/tejas/Desktop/cifar-10-batches-py");
Xtr=np.mean(Xtr, 3);
Xte=np.mean(Xte, 3);
Xtrain=Xtr.reshape(Xtr.shape[0], Xtr.shape[1]*Xtr.shape[2])
Xtest=Xte.reshape(Xte.shape[0], Xte.shape[1]*Xte.shape[2])
train_set_x, train_set_y=ds.shared_dataset((Xtrain, Ytr));
test_set_x, test_set_y=ds.shared_dataset((Xtest, Yte));
n_train_batches=train_set_x.get_value(borrow=True).shape[0]/batch_size;
n_test_batches=test_set_x.get_value(borrow=True).shape[0]/batch_size;
print "[MESSAGE] The data is loaded"
X=T.matrix("data");
from scae_destin.model import ConvAutoEncoder
from scae_destin.convnet import MaxPooling
from scae_destin.convnet import Flattener
from scae_destin.model import FeedForward
from scae_destin.optimize import gd_updates
from scae_destin.cost import mean_square_cost
from scae_destin.cost import categorical_cross_entropy_cost
from scae_destin.cost import L2_regularization
#def conv():
n_epochs=1
batch_size=100
nkerns=100
Xtr, Ytr, Xte, Yte=ds.load_CIFAR10("../cifar-10-batches-py/")
Xtr=np.mean(Xtr, 3)
Xte=np.mean(Xte, 3)
Xtrain=Xtr.reshape(Xtr.shape[0], Xtr.shape[1]*Xtr.shape[2])/255.0
Xtest=Xte.reshape(Xte.shape[0], Xte.shape[1]*Xte.shape[2])/255.0
train_set_x, train_set_y=ds.shared_dataset((Xtrain, Ytr))
test_set_x, test_set_y=ds.shared_dataset((Xtest, Yte))
n_train_batches=train_set_x.get_value(borrow=True).shape[0]/batch_size
n_test_batches=test_set_x.get_value(borrow=True).shape[0]/batch_size
print "[MESSAGE] The data is loaded"
################################## FIRST LAYER #######################################
import numpy as np;
import sys
import theano;
import theano.tensor as T;
sys.path.append("..")
import scae_destin.datasets as ds;
from scae_destin.convnet import ReLUConvLayer;
from scae_destin.convnet import LCNLayer
n_epochs=1;
batch_size=100;
Xtr, Ytr, Xte, Yte=ds.load_CIFAR10("/home/icog/convAE+destin/cifar-10-batches-py");
Xtr=np.mean(Xtr, 3);
Xte=np.mean(Xte, 3);
Xtrain=Xtr.reshape(Xtr.shape[0], Xtr.shape[1]*Xtr.shape[2])
Xtest=Xte.reshape(Xte.shape[0], Xte.shape[1]*Xte.shape[2])
train_set_x, train_set_y=ds.shared_dataset((Xtrain, Ytr));
test_set_x, test_set_y=ds.shared_dataset((Xtest, Yte));
n_train_batches=train_set_x.get_value(borrow=True).shape[0]/batch_size;
n_test_batches=test_set_x.get_value(borrow=True).shape[0]/batch_size;
print "[MESSAGE] The data is loaded"
X=T.matrix("data");