def train_network(weights_file="weights.hdf5", classpath="Preproc/Train/", epochs=50, batch_size=20, val_split=0.25,tile=False):
np.random.seed(1)
from keras import backend as K
print("GPU available ", K.tensorflow_backend._get_available_gpus())
# prevent TF from consuming whole memory in GPU
config = tf.ConfigProto(device_count = {'GPU': 1})
config.gpu_options.allow_growth = True
# config.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config)
K.set_session(sess)
K.set_image_data_format('channels_last') #make sure we use current
# Get the data
X_train, Y_train, paths_train, class_names = build_dataset(path=classpath, batch_size=batch_size, tile=tile)
# Score the model against Test dataset
X_test, Y_test, paths_test, class_names_test = build_dataset(path=classpath+"../Test/", tile=tile)
shape=get_sample_dimensions(class_names,path=classpath)
n_epochs = [200, 200, 500] ## DNN-RNN-CNN
Random_Deep = [0, 0, 3] ## DNN-RNN-CNN
assert( class_names == class_names_test )
RMDL_Image.Image_Classification(X_train, Y_train, X_test, Y_test, shape, batch_size=batch_size,
sparse_categorical=True, random_deep=Random_Deep, epochs=n_epochs, plot=True)
* Refrenced paper : RMDL: Random Multimodel Deep Learning for Classification * Refrenced paper : An Improvement of Data Classification using Random Multimodel Deep Learning (RMDL) * Comments and Error: email: [email protected] ''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '' from keras.datasets import cifar10 from RMDL import RMDL_Image as RMDL if __name__ == "__main__": number_of_classes = 40 shape = (64, 64, 1) (x_train, y_train), (x_test, y_test) = cifar10.load_data() x_train = x_train.astype('float32') x_test = x_test.astype('float32') x_train /= 255 x_test /= 255 batch_size = 100 sparse_categorical = 0 n_epochs = [500, 500, 500] ## DNN--RNN-CNN Random_Deep = [3, 0, 3] ## DNN--RNN-CNN RMDL.Image_Classification(x_train, y_train, x_test, y_test, (32, 32, 3), batch_size=batch_size, random_deep=Random_Deep, epochs=n_epochs)
""" """""" """""" """""" """""" """""" """""" """""" """""" """""" ""
from keras.datasets import mnist
import numpy as np
from RMDL import RMDL_Image as RMDL
if __name__ == "__main__":
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train_D = X_train.reshape(X_train.shape[0], 28, 28, 1).astype('float32')
X_test_D = X_test.reshape(X_test.shape[0], 28, 28, 1).astype('float32')
X_train = X_train_D / 255.0
X_test = X_test_D / 255.0
number_of_classes = np.unique(y_train).shape[0]
shape = (28, 28, 1)
batch_size = 128
sparse_categorical = 0
n_epochs = [100, 100, 100] ## DNN--RNN-CNN
Random_Deep = [0, 0, 3] ## DNN--RNN-CNN
RMDL.Image_Classification(X_train,
y_train,
X_test,
y_test,
shape,
batch_size=batch_size,
sparse_categorical=True,
random_deep=Random_Deep,
epochs=n_epochs)
* Comments and Error: email: [email protected] ''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '''''' '' from sklearn.datasets import fetch_olivetti_faces from sklearn.model_selection import train_test_split from RMDL import RMDL_Image as RMDL if __name__ == "__main__": number_of_classes = 40 shape = (64, 64, 1) data = fetch_olivetti_faces() X_train, X_test, y_train, y_test = train_test_split(data.data, data.target, stratify=data.target, test_size=40) X_train = X_train.reshape(X_train.shape[0], 64, 64, 1).astype('float32') X_test = X_test.reshape(X_test.shape[0], 64, 64, 1).astype('float32') batch_size = 100 sparse_categorical = 0 n_epochs = [150, 150, 150] ## DNN--RNN-CNN Random_Deep = [0, 0, 3] ## DNN--RNN-CNN RMDL.Image_Classification(X_train, y_train, X_test, y_test, shape, random_optimizor=False, batch_size=batch_size, random_deep=Random_Deep, epochs=n_epochs)