Exemple #1
0
def load_dataset():
    br = BatchReader2.inputs()
    br2 = BatchReader2.inputs(testingData=True)
    X, Y = br.getNPArray(3)
    X_train = X[:50000 * 0.8].reshape(-1, 1, 48, 48)
    y_train = Y[:50000 * 0.8].astype('uint8')
    X_val = X[50000 * 0.8:].reshape(-1, 1, 48, 48)
    y_val = Y[50000 * 0.8:].astype('uint8')
    return X_train, y_train, X_val, y_val
def load_dataset():
    br = BatchReader2.inputs()
    br2 = BatchReader2.inputs(testingData = True)
    X, Y = br.getNPArray(3)
    X_train = X[:50000*0.8].reshape(-1, 1, 48, 48)
    y_train = Y[:50000*0.8].astype('uint8')
    X_val = X[50000*0.8:].reshape(-1, 1, 48, 48)
    y_val = Y[50000*0.8:].astype('uint8')
    return X_train, y_train, X_val, y_val
Exemple #3
0
def loadData():
    sizeTrain = 0.7
    sizeVal = 0.2
    br = BatchReader2.inputs()
    br2 = BatchReader2.inputs(testingData = True)
    X, Y = br.getNPArray(2)
    n = X.shape[0]
    testX = br2.getNPArray(2)
    trainX = X[:n*sizeTrain].reshape(-1,1,48,48)
    trainY = Y[:n*sizeTrain].astype('uint8')
    validationX = X[n*sizeTrain:n*(sizeTrain+sizeVal)+1].reshape(-1,1,48,48)
    validationY = Y[n*sizeTrain:n*(sizeTrain+sizeVal)+1].astype('uint8')
    print (trainX.shape)
    print (validationX.shape)
    print (validationY.shape)
    tX = X[n*(sizeTrain+sizeVal)+1:].reshape(-1,1,48,48)
    tY = Y[n*(sizeTrain+sizeVal)+1:].astype('uint8')
    print (tX.shape)
    testX = testX.reshape(-1,1,48,48)
    return trainX,trainY,validationX,validationY,tX,tY,testX
Exemple #4
0
from theano.tensor.signal import downsample
from theano.tensor.nnet import conv
from logistic_sgd import LogisticRegression, load_data
from mlp import HiddenLayer
import BatchReader2
import scipy.misc
import pickle
import CNNL
import CNN

theano.config.floatX = 'float32'

if __name__ == '__main__':

    rng = numpy.random.RandomState(42)
    br = BatchReader2.inputs()
    br2 = BatchReader2.inputs(testingData=True)
    X, Y = br.getNPArray(2)
    testX = br2.getNPArray(2)
    print testX.shape
    num_epochs = 200
    n = X.shape[0]
    sizeTrain = 0.8
    trainX = X[:n * sizeTrain].reshape(-1, 1, 48, 48)
    trainY = Y[:n * sizeTrain].astype('uint8')
    validationX = X[n * sizeTrain:].reshape(-1, 1, 48, 48)
    validationY = Y[n * sizeTrain:].astype('uint8')
    testX = testX.reshape(-1, 1, 48, 48)
    input_var = T.tensor4('inputs')
    target_var = T.ivector('targets')
    network = CNNL.convnetL(input_var)
from theano.tensor.signal import downsample
from theano.tensor.nnet import conv
from logistic_sgd import LogisticRegression, load_data
from mlp import HiddenLayer
import BatchReader2
import scipy.misc
import pickle
import CNNL
import CNN

theano.config.floatX = 'float32'

if __name__ == '__main__':
    
    rng = numpy.random.RandomState(42)
    br = BatchReader2.inputs()
    br2 = BatchReader2.inputs(testingData = True)
    X, Y = br.getNPArray(2)
    testX = br2.getNPArray(2)
    print testX.shape
    num_epochs = 200
    n = X.shape[0]
    sizeTrain = 0.8
    trainX = X[:n*sizeTrain].reshape(-1,1,48,48)
    trainY = Y[:n*sizeTrain].astype('uint8')
    validationX = X[n*sizeTrain:].reshape(-1,1,48,48)
    validationY = Y[n*sizeTrain:].astype('uint8')
    testX = testX.reshape(-1,1,48,48)
    input_var = T.tensor4('inputs')
    target_var = T.ivector('targets')
    network = CNNL.convnetL(input_var)