import changes relative to skluc

main/deepfriedConvnetMnist.py

@@ -13,8 +13,8 @@ Zichao Yang, Marcin Moczulski, Misha Denil, Nando de Freitas, Alex Smola, Le Son
 import tensorflow as tf
 import numpy as np
 import skluc.mldatasets as dataset
-from skluc.neural_networks import convolution_mnist, classification_mnist, batch_generator
-from skluc.kernel_approximation.fasfood_layer import fast_food
+from skluc.tensorflow.utils import convolution_mnist, classification_mnist, batch_generator
+from skluc.tensorflow.kernel_approximation import fastfood_layer
 
 tf.logging.set_verbosity(tf.logging.ERROR)
 
@@ -54,7 +54,7 @@ if __name__ == '__main__':
         # out_fc = tf.nn.relu(fast_food(h_conv, SIGMA, nbr_stack=2))
         # out_fc = tf.nn.relu(fast_food(h_conv, SIGMA, nbr_stack=2, trainable=True))
         # out_fc = tf.nn.relu(fast_food(h_conv, SIGMA, trainable=True))  # 84% accuracy (conv) | 59% accuracy (noconv)
-        out_fc = fast_food(h_conv, SIGMA, nbr_stack=1, trainable=True)  # 84% accuracy (conv) | 59% accuracy (noconv)
+        out_fc = fastfood_layer(h_conv, SIGMA, nbr_stack=1, trainable=True)  # 84% accuracy (conv) | 59% accuracy (noconv)
         # out_fc = random_features(h_conv, SIGMA)  # 82% accuracy (conv) | 47% accuracy (noconv)
 
         # classification

main/experiments/global_speed.py

@@ -25,12 +25,12 @@ Options:
 import tensorflow as tf
 import numpy as np
 
-from skluc.kernel_approximation.nystrom.nystrom_approx import nystrom_layer
-from skluc.neural_networks import inference_mnist, batch_generator, convolution_mnist, classification_mnist, \
+from skluc.tensorflow.kernel_approximation.nystrom_approx import nystrom_layer
+from skluc.tensorflow.utils import inference_mnist, batch_generator, convolution_mnist, classification_mnist, \
     inference_cifar10, convolution_cifar, classification_cifar
 import skluc.mldatasets as dataset
 
-from skluc.kernel_approximation.fasfood_layer import fast_food
+from skluc.tensorflow.kernel_approximation import fastfood_layer
 
 import docopt
 
@@ -113,7 +113,7 @@ def fct_deepfriedconvnet(X_train, Y_train, data_shape, output_dim, dataname, bat
         # Representation layer
 
         h_conv = convolution(x_image)
-        out_fc = tf.nn.relu(fast_food(h_conv, sigma, nbr_stack=fastfood_stack_number, trainable=True))  # 84% accuracy (conv) | 59% accuracy (noconv)
+        out_fc = tf.nn.relu(fastfood_layer(h_conv, sigma, nbr_stack=fastfood_stack_number, trainable=True))  # 84% accuracy (conv) | 59% accuracy (noconv)
         # out_fc = fully_connected(h_conv)  # 95% accuracy
         # out_fc = tf.nn.relu(fast_food(h_conv, SIGMA, nbr_stack=1))  # 83% accuracy (conv) | 56% accuracy (noconv)
         # out_fc = tf.nn.relu(fast_food(h_conv, SIGMA, nbr_stack=2))

main/experiments/nystrom_vs_deepstrom.py

@@ -21,8 +21,8 @@ import skluc.mldatasets as dataset
 from sklearn.kernel_approximation import Nystroem
 from sklearn.svm import SVC
 
-from skluc.kernel_approximation.nystrom.nystrom_approx import nystrom_layer
-from skluc.neural_networks import batch_generator, classification_mnist
+from skluc.tensorflow.kernel_approximation.nystrom_approx import nystrom_layer
+from skluc.tensorflow.utils import batch_generator, classification_mnist
 
 tf.logging.set_verbosity(tf.logging.ERROR)
 

main/time_batch_subsample_ops.py

@@ -3,9 +3,9 @@ import numpy as np
 from sklearn.metrics.pairwise import rbf_kernel
 
 import skluc.mldatasets as dataset
-from skluc.neural_networks import fully_connected, get_next_batch, tf_op, conv_relu_pool
+from skluc.tensorflow.utils import fully_connected, get_next_batch, tf_op, conv_relu_pool
 from skluc.utils import time_fct
-from skluc.kernel_approximation.nystrom.nystrom_approx import tf_rbf_kernel
+from skluc.tensorflow.kernel_approximation.nystrom_approx import tf_rbf_kernel
 
 tf.logging.set_verbosity(tf.logging.ERROR)