from keras.layers.convolutional import Convolution2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from sklearn.metrics import confusion_matrix
import imageDataExtract as dataset
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load data
matrix_path = 'numpy-matrix/main-0.npy'
label_path = 'numpy-matrix/label-0.npy'
X_train, y_train, X_test, y_test = dataset.load_matrix(matrix_path, label_path)
# normalize inputs from 0-255 to 0.0-1.0
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
print X_train.shape
print X_test.shape
X_train = X_train / 255.0
X_test = X_test / 255.0
# one hot encode outputs
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]
from keras.layers.convolutional import Convolution2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from sklearn.metrics import confusion_matrix
import imageDataExtract as dataset
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load data
matrix_path = 'numpy-matrix/main-0.npy'
label_path = 'numpy-matrix/label-0.npy'
X_train, y_train, X_test, y_test = dataset.load_matrix(matrix_path, label_path)
# normalize inputs from 0-255 to 0.0-1.0
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
print X_train.shape
print X_test.shape
X_train = X_train / 255.0
X_test = X_test / 255.0
# one hot encode outputs