Always load the data from the data folder.

This work independently of the current directory.

Author: nouiz

code/DBN.py

@@ -257,7 +257,7 @@ def test_score():
 
 def test_DBN(finetune_lr=0.1, pretraining_epochs=100,
              pretrain_lr=0.01, k=1, training_epochs=1000,
-             dataset='../data/mnist.pkl.gz', batch_size=10):
+             dataset='mnist.pkl.gz', batch_size=10):
     """
     Demonstrates how to train and test a Deep Belief Network.
 

code/SdA.py

@@ -295,7 +295,7 @@ def test_score():
 
 def test_SdA(finetune_lr=0.1, pretraining_epochs=15,
              pretrain_lr=0.001, training_epochs=1000,
-             dataset='../data/mnist.pkl.gz', batch_size=1):
+             dataset='mnist.pkl.gz', batch_size=1):
     """
     Demonstrates how to train and test a stochastic denoising autoencoder.
 

code/cA.py

@@ -221,7 +221,7 @@ def get_cost_updates(self, contraction_level, learning_rate):
 
 
 def test_cA(learning_rate=0.01, training_epochs=20,
-            dataset='../data/mnist.pkl.gz',
+            dataset='mnist.pkl.gz',
             batch_size=10, output_folder='cA_plots', contraction_level=.1):
     """
     This demo is tested on MNIST

code/convolutional_mlp.py

@@ -104,7 +104,7 @@ def __init__(self, rng, input, filter_shape, image_shape, poolsize=(2, 2)):
 
 
 def evaluate_lenet5(learning_rate=0.1, n_epochs=200,
-                    dataset='../data/mnist.pkl.gz',
+                    dataset='mnist.pkl.gz',
                     nkerns=[20, 50], batch_size=500):
     """ Demonstrates lenet on MNIST dataset
 

code/dA.py

@@ -237,7 +237,7 @@ def get_cost_updates(self, corruption_level, learning_rate):
 
 
 def test_dA(learning_rate=0.1, training_epochs=15,
-            dataset='../data/mnist.pkl.gz',
+            dataset='mnist.pkl.gz',
             batch_size=20, output_folder='dA_plots'):
 
     """

code/logistic_cg.py

@@ -132,7 +132,7 @@ def errors(self, y):
             raise NotImplementedError()
 
 
-def cg_optimization_mnist(n_epochs=50, mnist_pkl_gz='../data/mnist.pkl.gz'):
+def cg_optimization_mnist(n_epochs=50, mnist_pkl_gz='mnist.pkl.gz'):
     """Demonstrate conjugate gradient optimization of a log-linear model
 
     This is demonstrated on MNIST.

code/logistic_sgd.py

@@ -157,6 +157,13 @@ def load_data(dataset):
 
     # Download the MNIST dataset if it is not present
     data_dir, data_file = os.path.split(dataset)
+    if data_dir == "" and not os.path.isfile(dataset):
+        # Check if dataset is in the data directory.
+        new_path = os.path.join(os.path.split(os.path.split(__file__)[0])[0],
+                                "data", dataset)
+        if os.path.isfile(new_path) or data_file == 'mnist.pkl.gz':
+            dataset = new_path
+
     if (not os.path.isfile(dataset)) and data_file == 'mnist.pkl.gz':
         import urllib
         origin = 'http://www.iro.umontreal.ca/~lisa/deep/data/mnist/mnist.pkl.gz'
@@ -211,7 +218,7 @@ def shared_dataset(data_xy, borrow=True):
 
 
 def sgd_optimization_mnist(learning_rate=0.13, n_epochs=1000,
-                           dataset='../data/mnist.pkl.gz',
+                           dataset='mnist.pkl.gz',
                            batch_size=600):
     """
     Demonstrate stochastic gradient descent optimization of a log-linear

code/mlp.py

@@ -174,7 +174,7 @@ def __init__(self, rng, input, n_in, n_hidden, n_out):
 
 
 def test_mlp(learning_rate=0.01, L1_reg=0.00, L2_reg=0.0001, n_epochs=1000,
-             dataset='../data/mnist.pkl.gz', batch_size=20, n_hidden=500):
+             dataset='mnist.pkl.gz', batch_size=20, n_hidden=500):
     """
     Demonstrate stochastic gradient descent optimization for a multilayer
     perceptron

code/rbm.py

@@ -315,7 +315,7 @@ def get_reconstruction_cost(self, updates, pre_sigmoid_nv):
 
 
 def test_rbm(learning_rate=0.1, training_epochs=15,
-             dataset='../data/mnist.pkl.gz', batch_size=20,
+             dataset='mnist.pkl.gz', batch_size=20,
              n_chains=20, n_samples=10, output_folder='rbm_plots',
              n_hidden=500):
     """