Changed deprecated tf.initialize_all_variables() to tf.global_variables_initializer()

slim/nets/overfeat_test.py

@@ -137,7 +137,7 @@ class OverFeatTest(tf.test.TestCase):
     with self.test_session() as sess:
       inputs = tf.random_uniform((batch_size, height, width, 3))
       logits, _ = overfeat.overfeat(inputs)
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(logits)
       self.assertTrue(output.any())
 

slim/nets/resnet_v1_test.py

@@ -104,7 +104,7 @@ class ResnetUtilsTest(tf.test.TestCase):
     y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1])
 
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       self.assertAllClose(y1.eval(), y1_expected.eval())
       self.assertAllClose(y2.eval(), y2_expected.eval())
       self.assertAllClose(y3.eval(), y3_expected.eval())
@@ -145,7 +145,7 @@ class ResnetUtilsTest(tf.test.TestCase):
     y4_expected = y2_expected
 
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       self.assertAllClose(y1.eval(), y1_expected.eval())
       self.assertAllClose(y2.eval(), y2_expected.eval())
       self.assertAllClose(y3.eval(), y3_expected.eval())
@@ -240,7 +240,7 @@ class ResnetUtilsTest(tf.test.TestCase):
               tf.get_variable_scope().reuse_variables()
               # Feature extraction at the nominal network rate.
               expected = self._stack_blocks_nondense(inputs, blocks)
-              sess.run(tf.initialize_all_variables())
+              sess.run(tf.global_variables_initializer())
               output, expected = sess.run([output, expected])
               self.assertAllClose(output, expected, atol=1e-4, rtol=1e-4)
 
@@ -388,7 +388,7 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
             # Feature extraction at the nominal network rate.
             expected, _ = self._resnet_small(inputs, None, is_training=False,
                                              global_pool=False)
-            sess.run(tf.initialize_all_variables())
+            sess.run(tf.global_variables_initializer())
             self.assertAllClose(output.eval(), expected.eval(),
                                 atol=1e-4, rtol=1e-4)
 
@@ -407,7 +407,7 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
                          [None, 1, 1, num_classes])
     images = create_test_input(batch, height, width, 3)
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(logits, {inputs: images.eval()})
       self.assertEqual(output.shape, (batch, 1, 1, num_classes))
 
@@ -422,7 +422,7 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
                          [batch, None, None, 32])
     images = create_test_input(batch, height, width, 3)
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(output, {inputs: images.eval()})
       self.assertEqual(output.shape, (batch, 3, 3, 32))
 
@@ -441,7 +441,7 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
                          [batch, None, None, 32])
     images = create_test_input(batch, height, width, 3)
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(output, {inputs: images.eval()})
       self.assertEqual(output.shape, (batch, 9, 9, 32))
 

slim/nets/resnet_v2_test.py

@@ -104,7 +104,7 @@ class ResnetUtilsTest(tf.test.TestCase):
     y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1])
 
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       self.assertAllClose(y1.eval(), y1_expected.eval())
       self.assertAllClose(y2.eval(), y2_expected.eval())
       self.assertAllClose(y3.eval(), y3_expected.eval())
@@ -145,7 +145,7 @@ class ResnetUtilsTest(tf.test.TestCase):
     y4_expected = y2_expected
 
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       self.assertAllClose(y1.eval(), y1_expected.eval())
       self.assertAllClose(y2.eval(), y2_expected.eval())
       self.assertAllClose(y3.eval(), y3_expected.eval())
@@ -240,7 +240,7 @@ class ResnetUtilsTest(tf.test.TestCase):
               tf.get_variable_scope().reuse_variables()
               # Feature extraction at the nominal network rate.
               expected = self._stack_blocks_nondense(inputs, blocks)
-              sess.run(tf.initialize_all_variables())
+              sess.run(tf.global_variables_initializer())
               output, expected = sess.run([output, expected])
               self.assertAllClose(output, expected, atol=1e-4, rtol=1e-4)
 
@@ -390,7 +390,7 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
             expected, _ = self._resnet_small(inputs, None,
                                              is_training=False,
                                              global_pool=False)
-            sess.run(tf.initialize_all_variables())
+            sess.run(tf.global_variables_initializer())
             self.assertAllClose(output.eval(), expected.eval(),
                                 atol=1e-4, rtol=1e-4)
 
@@ -409,7 +409,7 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
                          [None, 1, 1, num_classes])
     images = create_test_input(batch, height, width, 3)
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(logits, {inputs: images.eval()})
       self.assertEqual(output.shape, (batch, 1, 1, num_classes))
 
@@ -425,7 +425,7 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
                          [batch, None, None, 32])
     images = create_test_input(batch, height, width, 3)
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(output, {inputs: images.eval()})
       self.assertEqual(output.shape, (batch, 3, 3, 32))
 
@@ -444,7 +444,7 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
                          [batch, None, None, 32])
     images = create_test_input(batch, height, width, 3)
     with self.test_session() as sess:
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(output, {inputs: images.eval()})
       self.assertEqual(output.shape, (batch, 9, 9, 32))
 

slim/nets/vgg_test.py

@@ -148,7 +148,7 @@ class VGGATest(tf.test.TestCase):
     with self.test_session() as sess:
       inputs = tf.random_uniform((batch_size, height, width, 3))
       logits, _ = vgg.vgg_a(inputs)
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(logits)
       self.assertTrue(output.any())
 
@@ -292,7 +292,7 @@ class VGG16Test(tf.test.TestCase):
     with self.test_session() as sess:
       inputs = tf.random_uniform((batch_size, height, width, 3))
       logits, _ = vgg.vgg_16(inputs)
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(logits)
       self.assertTrue(output.any())
 
@@ -447,7 +447,7 @@ class VGG19Test(tf.test.TestCase):
     with self.test_session() as sess:
       inputs = tf.random_uniform((batch_size, height, width, 3))
       logits, _ = vgg.vgg_19(inputs)
-      sess.run(tf.initialize_all_variables())
+      sess.run(tf.global_variables_initializer())
       output = sess.run(logits)
       self.assertTrue(output.any())
 

slim/slim_walkthough.ipynb

@@ -300,7 +300,7 @@
     "    # This is good for training, but not for testing.\n",
     "    total_loss2 = slim.losses.get_total_loss(add_regularization_losses=True)\n",
     "    \n",
-    "    init_op = tf.initialize_all_variables()\n",
+    "    init_op = tf.global_variables_initializer()\n",
     "    \n",
     "    with tf.Session() as sess:\n",
     "        sess.run(init_op) # Will initialize the parameters with random weights.\n",
@@ -568,7 +568,7 @@
     "    probabilities = tf.nn.softmax(logits)\n",
     "  \n",
     "    # Initialize all the variables (including parameters) randomly.\n",
-    "    init_op = tf.initialize_all_variables()\n",
+    "    init_op = tf.global_variables_initializer()\n",
     "  \n",
     "    with tf.Session() as sess:\n",
     "        # Run the init_op, evaluate the model outputs and print the results:\n",

street/python/vgsl_model_test.py

@@ -180,7 +180,7 @@ class VgslModelTest(tf.test.TestCase):
           filename,
           model_spec='4,0,0,1[Cr5,5,16 Mp3,3 Lfys16 Lfxs16]O0s12',
           mode='train')
-      tf.initialize_all_variables().run(session=sess)
+      tf.global_variables_initializer().run(session=sess)
       coord = tf.train.Coordinator()
       tf.train.start_queue_runners(sess=sess, coord=coord)
       _, step = model.TrainAStep(sess)
@@ -204,7 +204,7 @@ class VgslModelTest(tf.test.TestCase):
           filename,
           model_spec='2,0,0,1[Cr5,5,16 Mp3,3 Lfys16 Lbx100]O1c105',
           mode='train')
-      tf.initialize_all_variables().run(session=sess)
+      tf.global_variables_initializer().run(session=sess)
       coord = tf.train.Coordinator()
       tf.train.start_queue_runners(sess=sess, coord=coord)
       _, step = model.TrainAStep(sess)
@@ -228,7 +228,7 @@ class VgslModelTest(tf.test.TestCase):
           filename,
           model_spec='8,0,0,1[Cr5,5,16 Mp3,3 Lfys16 Lfx64 Lrx64 Lfx64]O1s12',
           mode='train')
-      tf.initialize_all_variables().run(session=sess)
+      tf.global_variables_initializer().run(session=sess)
       coord = tf.train.Coordinator()
       tf.train.start_queue_runners(sess=sess, coord=coord)
       _, step = model.TrainAStep(sess)

street/python/vgslspecs_test.py

@@ -55,7 +55,7 @@ class VgslspecsTest(tf.test.TestCase):
         target_widths = tf.div(self.in_widths, factor).eval()
         target_heights = tf.div(self.in_heights, factor).eval()
         # Run with the 'real' data.
-        tf.initialize_all_variables().run()
+        tf.global_variables_initializer().run()
         res_image, res_widths, res_heights = sess.run(
             [outputs, vgsl.GetLengths(2), vgsl.GetLengths(1)],
             feed_dict={self.ph_image: self.in_image,

transformer/cluttered_mnist.py

@@ -135,7 +135,7 @@ accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
 # %% 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 now train in minibatches and report accuracy, loss:

transformer/example.py

@@ -55,7 +55,7 @@ with tf.variable_scope('spatial_transformer_0'):
 
 # %% Run session
 sess = tf.Session()
-sess.run(tf.initialize_all_variables())
+sess.run(tf.global_variables_initializer())
 y = sess.run(h_trans, feed_dict={x: batch})
 
 # plt.imshow(y[0])

video_prediction/prediction_train.py

@@ -207,7 +207,7 @@ def main(unused_argv):
     saver.restore(sess, FLAGS.pretrained_model)
 
   tf.train.start_queue_runners(sess)
-  sess.run(tf.initialize_all_variables())
+  sess.run(tf.global_variables_initializer())
 
   tf.logging.info('iteration number, cost')