Upgrade code to be compatible with TensorFlow 1.0.0 (which introduced breaking API changes)

BioGeek · BioGeek · commit 746e415da0d2 · 2017-03-01T11:16:56.000+01:00
diff --git a/python/01_basics.py b/python/01_basics.py
@@ -36,7 +36,7 @@
 # We'll use our values from [-3, 3] to create a Gaussian Distribution
 sigma = 1.0
 mean = 0.0
-z = (tf.exp(tf.neg(tf.pow(x - mean, 2.0) /
+z = (tf.exp(tf.negative(tf.pow(x - mean, 2.0) /
                    (2.0 * tf.pow(sigma, 2.0)))) *
      (1.0 / (sigma * tf.sqrt(2.0 * 3.1415))))
 
@@ -60,7 +60,7 @@
 print(tf.shape(z).eval())
 
 # %% We can combine tensors like so:
-print(tf.pack([tf.shape(z), tf.shape(z), [3], [4]]).eval())
+print(tf.stack([tf.shape(z), tf.shape(z), [3], [4]]).eval())
 
 # %% Let's multiply the two to get a 2d gaussian
 z_2d = tf.matmul(tf.reshape(z, [n_values, 1]), tf.reshape(z, [1, n_values]))
@@ -71,7 +71,7 @@
 # %% For fun let's create a gabor patch:
 x = tf.reshape(tf.sin(tf.linspace(-3.0, 3.0, n_values)), [n_values, 1])
 y = tf.reshape(tf.ones_like(x), [1, n_values])
-z = tf.mul(tf.matmul(x, y), z_2d)
+z = tf.multiply(tf.matmul(x, y), z_2d)
 plt.imshow(z.eval())
 
 # %% We can also list all the operations of a graph:
@@ -81,14 +81,14 @@
 # %% Lets try creating a generic function for computing the same thing:
 def gabor(n_values=32, sigma=1.0, mean=0.0):
     x = tf.linspace(-3.0, 3.0, n_values)
-    z = (tf.exp(tf.neg(tf.pow(x - mean, 2.0) /
+    z = (tf.exp(tf.negative(tf.pow(x - mean, 2.0) /
                        (2.0 * tf.pow(sigma, 2.0)))) *
          (1.0 / (sigma * tf.sqrt(2.0 * 3.1415))))
     gauss_kernel = tf.matmul(
         tf.reshape(z, [n_values, 1]), tf.reshape(z, [1, n_values]))
     x = tf.reshape(tf.sin(tf.linspace(-3.0, 3.0, n_values)), [n_values, 1])
     y = tf.reshape(tf.ones_like(x), [1, n_values])
-    gabor_kernel = tf.mul(tf.matmul(x, y), gauss_kernel)
+    gabor_kernel = tf.multiply(tf.matmul(x, y), gauss_kernel)
     return gabor_kernel
 
 # %% Confirm this does something:
@@ -112,7 +112,7 @@ def convolve(img, W):
         img = tf.reshape(img, dims)
         # if the image is 3 channels, then our convolution
         # kernel needs to be repeated for each input channel
-        W = tf.concat(2, [W, W, W])
+        W = tf.concat(axis=2, values=[W, W, W])
 
     # Stride is how many values to skip for the dimensions of
     # num, height, width, channels
diff --git a/python/02_linear_regression.py b/python/02_linear_regression.py
@@ -30,7 +30,7 @@
 # methods.
 W = tf.Variable(tf.random_normal([1]), name='weight')
 b = tf.Variable(tf.random_normal([1]), name='bias')
-Y_pred = tf.add(tf.mul(X, W), b)
+Y_pred = tf.add(tf.multiply(X, W), b)
 
 # %% Loss function will measure the distance between our observations
 # and predictions and average over them.
@@ -52,7 +52,7 @@
 with tf.Session() as sess:
     # Here we tell tensorflow that we want to initialize all
     # the variables in the graph so we can use them
-    sess.run(tf.initialize_all_variables())
+    sess.run(tf.global_variables_initializer())
 
     # Fit all training data
     prev_training_cost = 0.0
diff --git a/python/03_polynomial_regression.py b/python/03_polynomial_regression.py
@@ -28,7 +28,7 @@
 Y_pred = tf.Variable(tf.random_normal([1]), name='bias')
 for pow_i in range(1, 5):
     W = tf.Variable(tf.random_normal([1]), name='weight_%d' % pow_i)
-    Y_pred = tf.add(tf.mul(tf.pow(X, pow_i), W), Y_pred)
+    Y_pred = tf.add(tf.multiply(tf.pow(X, pow_i), W), Y_pred)
 
 # %% Loss function will measure the distance between our observations
 # and predictions and average over them.
@@ -50,7 +50,7 @@
 with tf.Session() as sess:
     # Here we tell tensorflow that we want to initialize all
     # the variables in the graph so we can use them
-    sess.run(tf.initialize_all_variables())
+    sess.run(tf.global_variables_initializer())
 
     # Fit all training data
     prev_training_cost = 0.0
diff --git a/python/04_logistic_regression.py b/python/04_logistic_regression.py
@@ -75,7 +75,7 @@
 # %% We now create a new session to actually perform the initialization the
 # variables:
 sess = tf.Session()
-sess.run(tf.initialize_all_variables())
+sess.run(tf.global_variables_initializer())
 
 # %% Now actually do some training:
 batch_size = 100
diff --git a/python/05_basic_convnet.py b/python/05_basic_convnet.py
@@ -83,7 +83,7 @@
 # %% We now create a new session to actually perform the initialization the
 # variables:
 sess = tf.Session()
-sess.run(tf.initialize_all_variables())
+sess.run(tf.global_variables_initializer())
 
 # %% We'll train in minibatches and report accuracy:
 batch_size = 100
diff --git a/python/06_modern_convnet.py b/python/06_modern_convnet.py
@@ -51,7 +51,7 @@
 # %% We now create a new session to actually perform the initialization the
 # variables:
 sess = tf.Session()
-sess.run(tf.initialize_all_variables())
+sess.run(tf.global_variables_initializer())
 
 # %% We'll train in minibatches and report accuracy:
 n_epochs = 10
diff --git a/python/07_autoencoder.py b/python/07_autoencoder.py
@@ -84,7 +84,7 @@ def test_mnist():
     # %%
     # We create a session to use the graph
     sess = tf.Session()
-    sess.run(tf.initialize_all_variables())
+    sess.run(tf.global_variables_initializer())
 
     # %%
     # Fit all training data
diff --git a/python/08_denoising_autoencoder.py b/python/08_denoising_autoencoder.py
@@ -95,7 +95,7 @@ def test_mnist():
     # %%
     # We create a session to use the graph
     sess = tf.Session()
-    sess.run(tf.initialize_all_variables())
+    sess.run(tf.global_variables_initializer())
 
     # %%
     # Fit all training data
diff --git a/python/09_convolutional_autoencoder.py b/python/09_convolutional_autoencoder.py
@@ -102,7 +102,7 @@ def autoencoder(input_shape=[None, 784],
         output = lrelu(tf.add(
             tf.nn.conv2d_transpose(
                 current_input, W,
-                tf.pack([tf.shape(x)[0], shape[1], shape[2], shape[3]]),
+                tf.stack([tf.shape(x)[0], shape[1], shape[2], shape[3]]),
                 strides=[1, 2, 2, 1], padding='SAME'), b))
         current_input = output
 
@@ -137,7 +137,7 @@ def test_mnist():
     # %%
     # We create a session to use the graph
     sess = tf.Session()
-    sess.run(tf.initialize_all_variables())
+    sess.run(tf.global_variables_initializer())
 
     # %%
     # Fit all training data
diff --git a/python/10_residual_network.py b/python/10_residual_network.py
@@ -134,7 +134,7 @@ def test_mnist():
     # %% We now create a new session to actually perform the initialization the
     # variables:
     sess = tf.Session()
-    sess.run(tf.initialize_all_variables())
+    sess.run(tf.global_variables_initializer())
 
     # %% We'll train in minibatches and report accuracy:
     batch_size = 50
diff --git a/python/11_variational_autoencoder.py b/python/11_variational_autoencoder.py
@@ -55,7 +55,7 @@ def VAE(input_shape=[None, 784],
             [dims[0], n_hidden])
     else:
         epsilon = tf.random_normal(
-            tf.pack([tf.shape(x)[0], n_hidden]))
+            tf.stack([tf.shape(x)[0], n_hidden]))
 
     # Sample from posterior
     z = z_mu + tf.exp(z_log_sigma) * epsilon
@@ -117,7 +117,7 @@ def test_mnist():
     # %%
     # We create a session to use the graph
     sess = tf.Session()
-    sess.run(tf.initialize_all_variables())
+    sess.run(tf.global_variables_initializer())
 
     # %%
     # Fit all training data
diff --git a/python/libs/utils.py b/python/libs/utils.py
@@ -83,7 +83,7 @@ def corrupt(x):
     x_corrupted : Tensor
         50 pct of values corrupted.
     """
-    return tf.mul(x, tf.cast(tf.random_uniform(shape=tf.shape(x),
+    return tf.multiply(x, tf.cast(tf.random_uniform(shape=tf.shape(x),
                                                minval=0,
                                                maxval=2,
                                                dtype=tf.int32), tf.float32))
