Merge branch 'master' of https://github.com/ilyamironov/models

research/object_detection/protos/losses.proto

@@ -60,6 +60,7 @@ message ClassificationLoss {
   oneof classification_loss {
     WeightedSigmoidClassificationLoss weighted_sigmoid = 1;
     WeightedSoftmaxClassificationLoss weighted_softmax = 2;
+    WeightedSoftmaxClassificationAgainstLogitsLoss weighted_logits_softmax = 5;
     BootstrappedSigmoidClassificationLoss bootstrapped_sigmoid = 3;
     SigmoidFocalClassificationLoss weighted_sigmoid_focal = 4;
   }
@@ -93,6 +94,17 @@ message WeightedSoftmaxClassificationLoss {
   optional float logit_scale = 2 [default = 1.0];
 }
 
+// Classification loss using a softmax function over class predictions and
+// a softmax function over the groundtruth labels (assumed to be logits).
+message WeightedSoftmaxClassificationAgainstLogitsLoss {
+  // DEPRECATED, do not use.
+  optional bool anchorwise_output = 1 [default = false];
+  // Scale and softmax groundtruth logits before calculating softmax
+  // classification loss. Typically used for softmax distillation with teacher
+  // annotations stored as logits.
+  optional float logit_scale = 2 [default = 1.0];
+}
+
 // Classification loss using a sigmoid function over the class prediction with
 // the highest prediction score.
 message BootstrappedSigmoidClassificationLoss {

research/object_detection/protos/ssd.proto

@@ -113,7 +113,8 @@ message SsdFeatureExtractor {
   optional int32 pad_to_multiple = 5 [default = 1];
 
   // Whether to use explicit padding when extracting SSD multiresolution
-  // features. Note that this does not apply to the base feature extractor.
+  // features. This will also apply to the base feature extractor if a MobileNet
+  // architecture is used.
   optional bool use_explicit_padding = 7 [default=false];
 
   // Whether to use depthwise separable convolutions for to extract additional

research/object_detection/samples/configs/faster_rcnn_resnet101_ava_v2.1.config

+# Faster R-CNN with Resnet-101 (v1), configuration for AVA v2.1.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 80
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 600
+        max_dimension: 1024
+      }
+    }
+    feature_extractor {
+      type: 'faster_rcnn_resnet101'
+      first_stage_features_stride: 16
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 16
+        width_stride: 16
+      }
+    }
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 14
+    maxpool_kernel_size: 2
+    maxpool_stride: 2
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 300
+      }
+      score_converter: SIGMOID
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+    second_stage_classification_loss {
+      weighted_sigmoid {
+        anchorwise_output: true
+      }
+    }
+  }
+}
+
+train_config: {
+  batch_size: 1
+  num_steps: 1500000
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.0003
+          schedule {
+            step: 1200000
+            learning_rate: .00003
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  merge_multiple_label_boxes: true
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  max_number_of_boxes: 100
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/ava_train.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/ava_label_map_v2.1.pbtxt"
+}
+
+eval_config: {
+  metrics_set: "pascal_voc_detection_metrics"
+  use_moving_averages: false
+  num_examples: 57371
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED/ava_val.record"
+  }
+  label_map_path: "PATH_TO_BE_CONFIGURED/ava_label_map_v2.1.pbtxt"
+  shuffle: false
+  num_readers: 1
+}
+

research/object_detection/samples/configs/ssd_mobilenet_v2_coco.config

@@ -54,6 +54,7 @@ model {
         use_dropout: false
         dropout_keep_probability: 0.8
         kernel_size: 3
+        use_depthwise: true
         box_code_size: 4
         apply_sigmoid_to_scores: false
         conv_hyperparams {
@@ -105,7 +106,6 @@ model {
           epsilon: 0.001,
         }
       }
-      batch_norm_trainable: true
     }
     loss {
       classification_loss {

research/object_detection/utils/ops.py

@@ -774,8 +774,8 @@ def nearest_neighbor_upsampling(input_tensor, scale):
 
   Nearest neighbor upsampling function that maps input tensor with shape
   [batch_size, height, width, channels] to [batch_size, height * scale
-  , width * scale, channels]. This implementation only uses reshape and tile to
-  make it compatible with certain hardware.
+  , width * scale, channels]. This implementation only uses reshape and
+  broadcasting to make it TPU compatible.
 
   Args:
     input_tensor: A float32 tensor of size [batch, height_in, width_in,
@@ -785,13 +785,14 @@ def nearest_neighbor_upsampling(input_tensor, scale):
     data_up: A float32 tensor of size
       [batch, height_in*scale, width_in*scale, channels].
   """
-  shape = shape_utils.combined_static_and_dynamic_shape(input_tensor)
-  shape_before_tile = [shape[0], shape[1], 1, shape[2], 1, shape[3]]
-  shape_after_tile = [shape[0], shape[1] * scale, shape[2] * scale, shape[3]]
-  data_reshaped = tf.reshape(input_tensor, shape_before_tile)
-  resized_tensor = tf.tile(data_reshaped, [1, 1, scale, 1, scale, 1])
-  resized_tensor = tf.reshape(resized_tensor, shape_after_tile)
-  return resized_tensor
+  with tf.name_scope('nearest_neighbor_upsampling'):
+    (batch_size, height, width,
+     channels) = shape_utils.combined_static_and_dynamic_shape(input_tensor)
+    output_tensor = tf.reshape(
+        input_tensor, [batch_size, height, 1, width, 1, channels]) * tf.ones(
+            [1, 1, scale, 1, scale, 1], dtype=input_tensor.dtype)
+    return tf.reshape(output_tensor,
+                      [batch_size, height * scale, width * scale, channels])
 
 
 def matmul_gather_on_zeroth_axis(params, indices, scope=None):

research/object_detection/utils/visualization_utils.py

@@ -689,3 +689,32 @@ def add_cdf_image_summary(values, name):
     return image
   cdf_plot = tf.py_func(cdf_plot, [values], tf.uint8)
   tf.summary.image(name, cdf_plot)
+
+
+def add_hist_image_summary(values, bins, name):
+  """Adds a tf.summary.image for a histogram plot of the values.
+
+  Plots the histogram of values and creates a tf image summary.
+
+  Args:
+    values: a 1-D float32 tensor containing the values.
+    bins: bin edges which will be directly passed to np.histogram.
+    name: name for the image summary.
+  """
+
+  def hist_plot(values, bins):
+    """Numpy function to plot hist."""
+    fig = plt.figure(frameon=False)
+    ax = fig.add_subplot('111')
+    y, x = np.histogram(values, bins=bins)
+    ax.plot(x[:-1], y)
+    ax.set_ylabel('count')
+    ax.set_xlabel('value')
+    fig.canvas.draw()
+    width, height = fig.get_size_inches() * fig.get_dpi()
+    image = np.fromstring(
+        fig.canvas.tostring_rgb(), dtype='uint8').reshape(
+            1, int(height), int(width), 3)
+    return image
+  hist_plot = tf.py_func(hist_plot, [values, bins], tf.uint8)
+  tf.summary.image(name, hist_plot)

research/object_detection/utils/visualization_utils_test.py

@@ -187,6 +187,15 @@ class VisualizationUtilsTest(tf.test.TestCase):
     with self.test_session():
       cdf_image_summary.eval()
 
+  def test_add_hist_image_summary(self):
+    values = [0.1, 0.2, 0.3, 0.4, 0.42, 0.44, 0.46, 0.48, 0.50]
+    bins = [0.01 * i for i in range(101)]
+    visualization_utils.add_hist_image_summary(values, bins,
+                                               'ScoresDistribution')
+    hist_image_summary = tf.get_collection(key=tf.GraphKeys.SUMMARIES)[0]
+    with self.test_session():
+      hist_image_summary.eval()
+
 
 if __name__ == '__main__':
   tf.test.main()

research/slim/nets/cyclegan.py

@@ -97,14 +97,19 @@ def cyclegan_upsample(net, num_outputs, stride, method='conv2d_transpose'):
           net, [stride[0] * height, stride[1] * width])
       net = tf.pad(net, spatial_pad_1, 'REFLECT')
       net = layers.conv2d(net, num_outputs, kernel_size=[3, 3], padding='valid')
-    if method == 'bilinear_upsample_conv':
+    elif method == 'bilinear_upsample_conv':
       net = tf.image.resize_bilinear(
           net, [stride[0] * height, stride[1] * width])
       net = tf.pad(net, spatial_pad_1, 'REFLECT')
       net = layers.conv2d(net, num_outputs, kernel_size=[3, 3], padding='valid')
     elif method == 'conv2d_transpose':
+      # This corrects 1 pixel offset for images with even width and height.
+      # conv2d is left aligned and conv2d_transpose is right aligned for even
+      # sized images (while doing 'SAME' padding).
+      # Note: This doesn't reflect actual model in paper.
       net = layers.conv2d_transpose(
-          net, num_outputs, kernel_size=[3, 3], stride=stride, padding='same')
+          net, num_outputs, kernel_size=[3, 3], stride=stride, padding='valid')
+      net = net[:, 1:, 1:, :]
     else:
       raise ValueError('Unknown method: [%s]', method)
 

research/slim/nets/mobilenet/conv_blocks.py

@@ -175,6 +175,7 @@ def expanded_conv(input_tensor,
                   depthwise_channel_multiplier=1,
                   endpoints=None,
                   use_explicit_padding=False,
+                  padding='SAME',
                   scope=None):
   """Depthwise Convolution Block with expansion.
 
@@ -214,6 +215,7 @@ def expanded_conv(input_tensor,
     use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
       inputs so that the output dimensions are the same as if 'SAME' padding
       were used.
+    padding: Padding type to use if `use_explicit_padding` is not set.
     scope: optional scope.
 
   Returns:
@@ -228,8 +230,10 @@ def expanded_conv(input_tensor,
     if  depthwise_location not in [None, 'input', 'output', 'expansion']:
       raise TypeError('%r is unknown value for depthwise_location' %
                       depthwise_location)
-    padding = 'SAME'
     if use_explicit_padding:
+      if padding != 'SAME':
+        raise TypeError('`use_explicit_padding` should only be used with '
+                        '"SAME" padding.')
       padding = 'VALID'
     depthwise_func = functools.partial(
         slim.separable_conv2d,

research/slim/nets/mobilenet/mobilenet.py

@@ -114,6 +114,37 @@ def op(opfunc, **params):
   return _Op(opfunc, params=params, multiplier_func=multiplier)
 
 
+class NoOpScope(object):
+  """No-op context manager."""
+
+  def __enter__(self):
+    return None
+
+  def __exit__(self, exc_type, exc_value, traceback):
+    return False
+
+
+def safe_arg_scope(funcs, **kwargs):
+  """Returns `slim.arg_scope` with all None arguments removed.
+
+  Arguments:
+    funcs: Functions to pass to `arg_scope`.
+    **kwargs: Arguments to pass to `arg_scope`.
+
+  Returns:
+    arg_scope or No-op context manager.
+
+  Note: can be useful if None value should be interpreted as "do not overwrite
+    this parameter value".
+  """
+  filtered_args = {name: value for name, value in kwargs.items()
+                   if value is not None}
+  if filtered_args:
+    return slim.arg_scope(funcs, **filtered_args)
+  else:
+    return NoOpScope()
+
+
 @slim.add_arg_scope
 def mobilenet_base(  # pylint: disable=invalid-name
     inputs,
@@ -163,7 +194,9 @@ def mobilenet_base(  # pylint: disable=invalid-name
       only. It is safe to set it to the value matching
       training_scope(is_training=...). It is also safe to explicitly set
       it to False, even if there is outer training_scope set to to training.
-      (The network will be built in inference mode).
+      (The network will be built in inference mode). If this is set to None,
+      no arg_scope is added for slim.batch_norm's is_training parameter.
+
   Returns:
     tensor_out: output tensor.
     end_points: a set of activations for external use, for example summaries or
@@ -194,7 +227,7 @@ def mobilenet_base(  # pylint: disable=invalid-name
   # c) set all defaults
   # d) set all extra overrides.
   with _scope_all(scope, default_scope='Mobilenet'), \
-      slim.arg_scope([slim.batch_norm], is_training=is_training), \
+      safe_arg_scope([slim.batch_norm], is_training=is_training), \
       _set_arg_scope_defaults(conv_defs_defaults), \
       _set_arg_scope_defaults(conv_defs_overrides):
     # The current_stride variable keeps track of the output stride of the
@@ -394,14 +427,16 @@ def training_scope(is_training=True,
      # initialized appropriately.
   Args:
     is_training: if set to False this will ensure that all customizations are
-    set to non-training mode. This might be helpful for code that is reused
-    across both training/evaluation, but most of the time training_scope with
-    value False is not needed.
+      set to non-training mode. This might be helpful for code that is reused
+      across both training/evaluation, but most of the time training_scope with
+      value False is not needed. If this is set to None, the parameters is not
+      added to the batch_norm arg_scope.
 
     weight_decay: The weight decay to use for regularizing the model.
     stddev: Standard deviation for initialization, if negative uses xavier.
-    dropout_keep_prob: dropout keep probability
-    bn_decay: decay for the batch norm moving averages.
+    dropout_keep_prob: dropout keep probability (not set if equals to None).
+    bn_decay: decay for the batch norm moving averages (not set if equals to
+      None).
 
   Returns:
     An argument scope to use via arg_scope.
@@ -409,10 +444,9 @@ def training_scope(is_training=True,
   # Note: do not introduce parameters that would change the inference
   # model here (for example whether to use bias), modify conv_def instead.
   batch_norm_params = {
-      'is_training': is_training,
       'decay': bn_decay,
+      'is_training': is_training
   }
-
   if stddev < 0:
     weight_intitializer = slim.initializers.xavier_initializer()
   else:
@@ -424,8 +458,8 @@ def training_scope(is_training=True,
       weights_initializer=weight_intitializer,
       normalizer_fn=slim.batch_norm), \
       slim.arg_scope([mobilenet_base, mobilenet], is_training=is_training),\
-      slim.arg_scope([slim.batch_norm], **batch_norm_params), \
-      slim.arg_scope([slim.dropout], is_training=is_training,
+      safe_arg_scope([slim.batch_norm], **batch_norm_params), \
+      safe_arg_scope([slim.dropout], is_training=is_training,
                      keep_prob=dropout_keep_prob), \
       slim.arg_scope([slim.conv2d], \
                      weights_regularizer=slim.l2_regularizer(weight_decay)), \

research/slim/nets/mobilenet/mobilenet_example.ipynb

 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "name": "Mobilenet Example.ipynb",
-      "version": "0.3.2",
-      "provenance": [],
-      "collapsed_sections": [
-        "T_cETKXHDTXu"
-      ]
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
   "cells": [
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
-        "colab_type": "text"
-      },
-      "source": [
-        "[View in Colaboratory](https://colab.research.google.com/github/marksandler2/models/blob/master/research/slim/nets/mobilenet/mobilenet_example.ipynb)"
-      ]
-    },
-    {
-      "metadata": {
-        "id": "aUVxY7xOGD1G",
-        "colab_type": "toc"
+        "colab_type": "toc",
+        "id": "aUVxY7xOGD1G"
       },
-      "cell_type": "markdown",
       "source": [
-        ">[Prerequisites (downloading tensorflow_models and checkpoints)](#scrollTo=T_cETKXHDTXu)\n",
+        "\u003e[Prerequisites (downloading tensorflow_models and checkpoints)](#scrollTo=T_cETKXHDTXu)\n",
         "\n",
-        ">[Checkpoint based inference](#scrollTo=fxMe7_pkk_Vo)\n",
+        "\u003e[Checkpoint based inference](#scrollTo=fxMe7_pkk_Vo)\n",
         "\n",
-        ">[Frozen inference](#scrollTo=PlwvpK3ElBk6)\n",
+        "\u003e[Frozen inference](#scrollTo=PlwvpK3ElBk6)\n",
         "\n"
       ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
-        "id": "T_cETKXHDTXu",
-        "colab_type": "text"
+        "colab_type": "text",
+        "id": "T_cETKXHDTXu"
       },
-      "cell_type": "markdown",
       "source": [
         "# Prerequisites (downloading tensorflow_models and checkpoints)"
       ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "zo5GyseklSVH",
+        "colab": {
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          },
+          "base_uri": "https://localhost:8080/",
+          "height": 125,
+          "output_extras": [
+            {}
+          ]
+        },
         "colab_type": "code",
-        "colab": {}
+        "executionInfo": {
+          "elapsed": 31129,
+          "status": "ok",
+          "timestamp": 1521483961674,
+          "user": {
+            "displayName": "Mark Sandler",
+            "photoUrl": "//lh5.googleusercontent.com/-CjnV3zpGrlw/AAAAAAAAAAI/AAAAAAAABRU/dfjRy_tzX5M/s50-c-k-no/photo.jpg",
+            "userId": "108034853522252017283"
+          },
+          "user_tz": 420
+        },
+        "id": "zo5GyseklSVH",
+        "outputId": "e12a8a80-c0d2-4ebc-9230-b170f11d236e"
       },
-      "cell_type": "code",
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Cloning into 'models'...\n",
+            "remote: Counting objects: 13504, done.\u001b[K\n",
+            "remote: Total 13504 (delta 2), reused 2 (delta 2), pack-reused 13501\u001b[K\n",
+            "Receiving objects: 100% (13504/13504), 422.07 MiB | 37.42 MiB/s, done.\n",
+            "Resolving deltas: 100% (7635/7635), done.\n",
+            "Checking out files: 100% (1946/1946), done.\n"
+          ]
+        }
+      ],
       "source": [
         "!git clone https://github.com/tensorflow/models"
-      ],
-      "execution_count": 0,
-      "outputs": []
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "obaW6O8bz3mA",
-        "colab_type": "code",
+        "cellView": "both",
         "colab": {
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          },
           "base_uri": "https://localhost:8080/",
-          "height": 35
+          "height": 35,
+          "output_extras": [
+            {}
+          ]
+        },
+        "colab_type": "code",
+        "executionInfo": {
+          "elapsed": 4504,
+          "status": "ok",
+          "timestamp": 1521493157017,
+          "user": {
+            "displayName": "Mark Sandler",
+            "photoUrl": "//lh5.googleusercontent.com/-CjnV3zpGrlw/AAAAAAAAAAI/AAAAAAAABRU/dfjRy_tzX5M/s50-c-k-no/photo.jpg",
+            "userId": "108034853522252017283"
+          },
+          "user_tz": 420
         },
-        "outputId": "5b096d87-68dc-4475-bf49-0d4e80c4f42e"
+        "id": "obaW6O8bz3mA",
+        "outputId": "79b3fb23-caa7-4683-9575-ba7c2f55ebdb"
       },
-      "cell_type": "code",
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Successfully downloaded the checkpoint. It is available as mobilenet_v2_1.0_224.ckpt\n"
+          ]
+        }
+      ],
       "source": [
         "from __future__ import print_function\n",
         "from IPython import display \n",
-        "base_name = 'mobilenet_v2_1.0_224' #@param\n",
-        "url = 'https://storage.googleapis.com/mobilenet_v2/checkpoints/' + base_name + '.tgz'\n",
+        "checkpoint_name = 'mobilenet_v2_1.0_224' #@param\n",
+        "url = 'https://storage.googleapis.com/mobilenet_v2/checkpoints/' + checkpoint_name + '.tgz'\n",
         "print('Downloading from ', url)\n",
         "!wget {url}\n",
         "print('Unpacking')\n",
@@ -89,93 +127,105 @@
         "display.clear_output()\n",
         "print('Successfully downloaded checkpoint from ', url,\n",
         "      '. It is available as', checkpoint)\n"
-      ],
-      "execution_count": 2,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Successfully downloaded checkpoint from  https://storage.googleapis.com/mobilenet_v2/checkpoints/mobilenet_v2_1.0_224.tgz . It is available as mobilenet_v2_1.0_224.ckpt\n"
-          ],
-          "name": "stdout"
-        }
       ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "qZDfLegf3hpw",
-        "colab_type": "code",
         "colab": {
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          },
           "base_uri": "https://localhost:8080/",
-          "height": 215
+          "height": 215,
+          "output_extras": [
+            {}
+          ]
+        },
+        "colab_type": "code",
+        "executionInfo": {
+          "elapsed": 1486,
+          "status": "ok",
+          "timestamp": 1521485010457,
+          "user": {
+            "displayName": "Mark Sandler",
+            "photoUrl": "//lh5.googleusercontent.com/-CjnV3zpGrlw/AAAAAAAAAAI/AAAAAAAABRU/dfjRy_tzX5M/s50-c-k-no/photo.jpg",
+            "userId": "108034853522252017283"
+          },
+          "user_tz": 420
         },
-        "outputId": "ea332b4f-8073-4913-97bd-733be77544b7"
+        "id": "qZDfLegf3hpw",
+        "outputId": "334ed084-b90e-4bd0-bd5e-125434a9a30f"
       },
-      "cell_type": "code",
-      "source": [
-        "!wget https://upload.wikimedia.org/wikipedia/commons/f/fe/Giant_Panda_in_Beijing_Zoo_1.JPG -O panda.jpg"
-      ],
-      "execution_count": 3,
       "outputs": [
         {
+          "name": "stdout",
           "output_type": "stream",
           "text": [
-            "--2018-03-25 04:33:46--  https://upload.wikimedia.org/wikipedia/commons/f/fe/Giant_Panda_in_Beijing_Zoo_1.JPG\n",
-            "Resolving upload.wikimedia.org (upload.wikimedia.org)... 198.35.26.112, 2620:0:863:ed1a::2:b\n",
-            "Connecting to upload.wikimedia.org (upload.wikimedia.org)|198.35.26.112|:443... connected.\n",
+            "--2018-03-19 18:43:29--  https://upload.wikimedia.org/wikipedia/commons/f/fe/Giant_Panda_in_Beijing_Zoo_1.JPG\n",
+            "Resolving upload.wikimedia.org (upload.wikimedia.org)... 208.80.154.240, 2620:0:860:ed1a::2:b\n",
+            "Connecting to upload.wikimedia.org (upload.wikimedia.org)|208.80.154.240|:443... connected.\n",
             "HTTP request sent, awaiting response... 200 OK\n",
             "Length: 116068 (113K) [image/jpeg]\n",
             "Saving to: ‘panda.jpg’\n",
             "\n",
-            "panda.jpg           100%[===================>] 113.35K  --.-KB/s    in 0.05s   \n",
+            "panda.jpg           100%[===================\u003e] 113.35K  --.-KB/s    in 0.03s   \n",
             "\n",
-            "2018-03-25 04:33:46 (2.10 MB/s) - ‘panda.jpg’ saved [116068/116068]\n",
+            "2018-03-19 18:43:30 (3.18 MB/s) - ‘panda.jpg’ saved [116068/116068]\n",
             "\n"
-          ],
-          "name": "stdout"
+          ]
         }
+      ],
+      "source": [
+        "!wget https://upload.wikimedia.org/wikipedia/commons/f/fe/Giant_Panda_in_Beijing_Zoo_1.JPG -O panda.jpg"
       ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "g0H2RDadndug",
-        "colab_type": "code",
         "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 17
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          }
         },
-        "outputId": "f239ad90-64ec-49e4-b5da-fa018c7eca24"
+        "colab_type": "code",
+        "id": "g0H2RDadndug"
       },
-      "cell_type": "code",
+      "outputs": [],
       "source": [
         "# setup path\n",
         "import sys\n",
         "sys.path.append('/content/models/research/slim')"
-      ],
-      "execution_count": 4,
-      "outputs": []
+      ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
-        "id": "fxMe7_pkk_Vo",
-        "colab_type": "text"
+        "colab_type": "text",
+        "id": "fxMe7_pkk_Vo"
       },
-      "cell_type": "markdown",
       "source": [
         "# Checkpoint based inference"
       ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "GrQemT66CxXt",
-        "colab_type": "code",
         "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 17
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          }
         },
-        "outputId": "d533c94d-26f2-45ff-d889-02785cfceeaf"
+        "colab_type": "code",
+        "id": "GrQemT66CxXt"
       },
-      "cell_type": "code",
+      "outputs": [],
       "source": [
         "import tensorflow as tf\n",
         "from nets.mobilenet import mobilenet_v2\n",
@@ -203,129 +253,193 @@
         "vars = ema.variables_to_restore()\n",
         "\n",
         "saver = tf.train.Saver(vars)  "
-      ],
-      "execution_count": 5,
-      "outputs": []
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "TJbLYo_FCxXy",
-        "colab_type": "code",
         "colab": {
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          },
           "base_uri": "https://localhost:8080/",
-          "height": 666
+          "height": 666,
+          "output_extras": [
+            {},
+            {}
+          ]
+        },
+        "colab_type": "code",
+        "executionInfo": {
+          "elapsed": 1422,
+          "status": "ok",
+          "timestamp": 1521493723379,
+          "user": {
+            "displayName": "Mark Sandler",
+            "photoUrl": "//lh5.googleusercontent.com/-CjnV3zpGrlw/AAAAAAAAAAI/AAAAAAAABRU/dfjRy_tzX5M/s50-c-k-no/photo.jpg",
+            "userId": "108034853522252017283"
+          },
+          "user_tz": 420
         },
-        "outputId": "60f490cb-baca-4146-d110-fd9f0e208b48"
+        "id": "TJbLYo_FCxXy",
+        "outputId": "17a4fbaa-dec0-4997-b233-15ba69806083"
       },
-      "cell_type": "code",
-      "source": [
-        "from IPython import display\n",
-        "import pylab\n",
-        "from datasets import imagenet\n",
-        "import PIL\n",
-        "display.display(display.Image('panda.jpg'))\n",
-        "\n",
-        "with tf.Session() as sess:\n",
-        "  saver.restore(sess,  checkpoint)\n",
-        "  x = endpoints['Predictions'].eval(feed_dict={file_input: 'panda.jpg'})\n",
-        "label_map = imagenet.create_readable_names_for_imagenet_labels()  \n",
-        "print(\"Top 1 prediction: \", x.argmax(),label_map[x.argmax()], x.max())\n"
-      ],
-      "execution_count": 6,
       "outputs": [
         {
-          "output_type": "display_data",
           "data": {
             "image/jpeg": "/9j/4AAQSkZJRgABAQEAYABgAAD/4SjTRXhpZgAASUkqAAgAAAAKAA8BAgASAAAAhgAAABABAgAK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\nsvj4Ejqg8oXv9K9VEKf/2Q==\n",
             "text/plain": [
-              "<IPython.core.display.Image object>"
+              "\u003cIPython.core.display.Image object\u003e"
             ]
           },
           "metadata": {
             "tags": []
-          }
+          },
+          "output_type": "display_data"
         },
         {
+          "name": "stdout",
           "output_type": "stream",
           "text": [
             "INFO:tensorflow:Restoring parameters from mobilenet_v2_1.0_224.ckpt\n",
-            "Top 1 prediction:  389 giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca 0.8499991\n"
-          ],
-          "name": "stdout"
+            "Top 1 prediction:  389 giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca 0.90984344\n"
+          ]
         }
+      ],
+      "source": [
+        "from IPython import display\n",
+        "import pylab\n",
+        "from datasets import imagenet\n",
+        "import PIL\n",
+        "display.display(display.Image('panda.jpg'))\n",
+        "\n",
+        "with tf.Session() as sess:\n",
+        "  saver.restore(sess,  checkpoint)\n",
+        "  x = endpoints['Predictions'].eval(feed_dict={file_input: 'panda.jpg'})\n",
+        "label_map = imagenet.create_readable_names_for_imagenet_labels()  \n",
+        "print(\"Top 1 prediction: \", x.argmax(),label_map[x.argmax()], x.max())\n"
       ]
     },
     {
+      "cell_type": "markdown",
       "metadata": {
-        "id": "PlwvpK3ElBk6",
-        "colab_type": "text"
+        "colab_type": "text",
+        "id": "PlwvpK3ElBk6"
       },
-      "cell_type": "markdown",
       "source": [
         "# Frozen inference"
       ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "o0BIbQUUlVrf",
-        "colab_type": "code",
         "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 17
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          }
         },
-        "outputId": "029626e1-6b6d-4768-db76-e4a22c7cbd48"
+        "colab_type": "code",
+        "id": "o0BIbQUUlVrf"
       },
-      "cell_type": "code",
+      "outputs": [],
       "source": [
         "import numpy as np\n",
         "img = np.array(PIL.Image.open('panda.jpg').resize((224, 224))).astype(np.float) / 128 - 1\n",
         "gd = tf.GraphDef.FromString(open(base_name + '_frozen.pb', 'rb').read())\n",
         "inp, predictions = tf.import_graph_def(gd,  return_elements = ['input:0', 'MobilenetV2/Predictions/Reshape_1:0'])"
-      ],
-      "execution_count": 7,
-      "outputs": []
+      ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "qSU2h5NRlN7V",
-        "colab_type": "code",
         "colab": {
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          },
           "base_uri": "https://localhost:8080/",
-          "height": 35
+          "height": 35,
+          "output_extras": [
+            {}
+          ]
+        },
+        "colab_type": "code",
+        "executionInfo": {
+          "elapsed": 1350,
+          "status": "ok",
+          "timestamp": 1521493472822,
+          "user": {
+            "displayName": "Mark Sandler",
+            "photoUrl": "//lh5.googleusercontent.com/-CjnV3zpGrlw/AAAAAAAAAAI/AAAAAAAABRU/dfjRy_tzX5M/s50-c-k-no/photo.jpg",
+            "userId": "108034853522252017283"
+          },
+          "user_tz": 420
         },
-        "outputId": "1fbdbade-b0e8-422d-a2b2-9a6b6192ee6a"
+        "id": "qSU2h5NRlN7V",
+        "outputId": "4fb09105-b729-45c3-b5ef-83c8da30a215"
       },
-      "cell_type": "code",
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Top 1 Prediction:  389 giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca 0.9220208\n"
+          ]
+        }
+      ],
       "source": [
         "with tf.Session(graph=inp.graph):\n",
         "  x = predictions.eval(feed_dict={inp: img.reshape(1, 224,224, 3)})\n",
         "\n",
         "label_map = imagenet.create_readable_names_for_imagenet_labels()  \n",
         "print(\"Top 1 Prediction: \", x.argmax(),label_map[x.argmax()], x.max())"
-      ],
-      "execution_count": 8,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Top 1 Prediction:  389 giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca 0.8914295\n"
-          ],
-          "name": "stdout"
-        }
       ]
     },
     {
+      "cell_type": "code",
+      "execution_count": 0,
       "metadata": {
-        "id": "CU8dJF8kCo6X",
+        "colab": {
+          "autoexec": {
+            "startup": false,
+            "wait_interval": 0
+          }
+        },
         "colab_type": "code",
-        "colab": {}
+        "id": "CU8dJF8kCo6X"
       },
-      "cell_type": "code",
+      "outputs": [],
       "source": [
         ""
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "collapsed_sections": [
+        "T_cETKXHDTXu"
       ],
-      "execution_count": 0,
-      "outputs": []
+      "default_view": {},
+      "name": "Mobilenet Example.ipynb",
+      "provenance": [
+        {
+          "file_id": "1ylt6hB0JlXmWU9Bm6O1zGKVPgc2csZf5",
+          "timestamp": 1521507068201
+        }
+      ],
+      "version": "0.3.2",
+      "views": {}
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
     }
-  ]
-}
\ No newline at end of file
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

research/slim/nets/mobilenet/mobilenet_v2_test.py

@@ -171,6 +171,19 @@ class MobilenetV2Test(tf.test.TestCase):
         use_explicit_padding=True)
     self.assertEqual(out.get_shape().as_list()[1:3], [14, 14])
 
+  def testBatchNormScopeDoesNotHaveIsTrainingWhenItsSetToNone(self):
+    sc = mobilenet.training_scope(is_training=None)
+    self.assertNotIn('is_training', sc[slim.arg_scope_func_key(
+        slim.batch_norm)])
+
+  def testBatchNormScopeDoesHasIsTrainingWhenItsNotNone(self):
+    sc = mobilenet.training_scope(is_training=False)
+    self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
+    sc = mobilenet.training_scope(is_training=True)
+    self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
+    sc = mobilenet.training_scope()
+    self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
+
 
 if __name__ == '__main__':
   tf.test.main()

research/slim/nets/mobilenet_v1.py

@@ -434,7 +434,8 @@ def mobilenet_v1_arg_scope(is_training=True,
   """Defines the default MobilenetV1 arg scope.
 
   Args:
-    is_training: Whether or not we're training the model.
+    is_training: Whether or not we're training the model. If this is set to
+      None, the parameter is not added to the batch_norm arg_scope.
     weight_decay: The weight decay to use for regularizing the model.
     stddev: The standard deviation of the trunctated normal weight initializer.
     regularize_depthwise: Whether or not apply regularization on depthwise.
@@ -446,12 +447,13 @@ def mobilenet_v1_arg_scope(is_training=True,
     An `arg_scope` to use for the mobilenet v1 model.
   """
   batch_norm_params = {
-      'is_training': is_training,
       'center': True,
       'scale': True,
       'decay': batch_norm_decay,
       'epsilon': batch_norm_epsilon,
   }
+  if is_training is not None:
+    batch_norm_params['is_training'] = is_training
 
   # Set weight_decay for weights in Conv and DepthSepConv layers.
   weights_init = tf.truncated_normal_initializer(stddev=stddev)

research/slim/nets/mobilenet_v1_test.py

@@ -517,6 +517,18 @@ class MobilenetV1Test(tf.test.TestCase):
       logits_out = sess.run(logits)
       self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])
 
+  def testBatchNormScopeDoesNotHaveIsTrainingWhenItsSetToNone(self):
+    sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=None)
+    self.assertNotIn('is_training', sc[slim.arg_scope_func_key(
+        slim.batch_norm)])
+
+  def testBatchNormScopeDoesHasIsTrainingWhenItsNotNone(self):
+    sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=True)
+    self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
+    sc = mobilenet_v1.mobilenet_v1_arg_scope(is_training=False)
+    self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
+    sc = mobilenet_v1.mobilenet_v1_arg_scope()
+    self.assertIn('is_training', sc[slim.arg_scope_func_key(slim.batch_norm)])
 
 if __name__ == '__main__':
   tf.test.main()

research/slim/nets/pix2pix.py

@@ -154,9 +154,6 @@ def pix2pix_generator(net,
   blocks = blocks or _default_generator_blocks()
 
   input_size = net.get_shape().as_list()
-  height, width = input_size[1], input_size[2]
-  if height != width:
-    raise ValueError('The input height must match the input width.')
 
   input_size[3] = num_outputs
 
@@ -213,7 +210,10 @@ def pix2pix_generator(net,
         end_points['decoder%d' % block_id] = net
 
   with tf.variable_scope('output'):
-    logits = layers.conv2d(net, num_outputs, [4, 4], activation_fn=None)
+    # Explicitly set the normalizer_fn to None to override any default value
+    # that may come from an arg_scope, such as pix2pix_arg_scope.
+    logits = layers.conv2d(
+        net, num_outputs, [4, 4], activation_fn=None, normalizer_fn=None)
     logits = tf.reshape(logits, input_size)
 
     end_points['logits'] = logits

research/slim/nets/pix2pix_test.py

@@ -24,18 +24,6 @@ from nets import pix2pix
 
 class GeneratorTest(tf.test.TestCase):
 
-  def test_nonsquare_inputs_raise_exception(self):
-    batch_size = 2
-    height, width = 240, 320
-    num_outputs = 4
-
-    images = tf.ones((batch_size, height, width, 3))
-
-    with self.assertRaises(ValueError):
-      with tf.contrib.framework.arg_scope(pix2pix.pix2pix_arg_scope()):
-        pix2pix.pix2pix_generator(
-            images, num_outputs, upsample_method='nn_upsample_conv')
-
   def _reduced_default_blocks(self):
     """Returns the default blocks, scaled down to make test run faster."""
     return [pix2pix.Block(b.num_filters // 32, b.decoder_keep_prob)

research/slim/nets/resnet_v1.py

@@ -65,6 +65,16 @@ resnet_arg_scope = resnet_utils.resnet_arg_scope
 slim = tf.contrib.slim
 
 
+class NoOpScope(object):
+  """No-op context manager."""
+
+  def __enter__(self):
+    return None
+
+  def __exit__(self, exc_type, exc_value, traceback):
+    return False
+
+
 @slim.add_arg_scope
 def bottleneck(inputs,
                depth,
@@ -169,7 +179,9 @@ def resnet_v1(inputs,
       is a resnet_utils.Block object describing the units in the block.
     num_classes: Number of predicted classes for classification tasks.
       If 0 or None, we return the features before the logit layer.
-    is_training: whether batch_norm layers are in training mode.
+    is_training: whether batch_norm layers are in training mode. If this is set
+      to None, the callers can specify slim.batch_norm's is_training parameter
+      from an outer slim.arg_scope.
     global_pool: If True, we perform global average pooling before computing the
       logits. Set to True for image classification, False for dense prediction.
     output_stride: If None, then the output will be computed at the nominal
@@ -211,7 +223,8 @@ def resnet_v1(inputs,
     with slim.arg_scope([slim.conv2d, bottleneck,
                          resnet_utils.stack_blocks_dense],
                         outputs_collections=end_points_collection):
-      with slim.arg_scope([slim.batch_norm], is_training=is_training):
+      with (slim.arg_scope([slim.batch_norm], is_training=is_training)
+            if is_training is not None else NoOpScope()):
         net = inputs
         if include_root_block:
           if output_stride is not None:

research/slim/nets/resnet_v1_test.py

@@ -353,6 +353,25 @@ class ResnetCompleteNetworkTest(tf.test.TestCase):
     self.assertListEqual(end_points['global_pool'].get_shape().as_list(),
                          [2, 1, 1, 32])
 
+  def testClassificationEndPointsWithNoBatchNormArgscope(self):
+    global_pool = True
+    num_classes = 10
+    inputs = create_test_input(2, 224, 224, 3)
+    with slim.arg_scope(resnet_utils.resnet_arg_scope()):
+      logits, end_points = self._resnet_small(inputs, num_classes,
+                                              global_pool=global_pool,
+                                              spatial_squeeze=False,
+                                              is_training=None,
+                                              scope='resnet')
+    self.assertTrue(logits.op.name.startswith('resnet/logits'))
+    self.assertListEqual(logits.get_shape().as_list(), [2, 1, 1, num_classes])
+    self.assertTrue('predictions' in end_points)
+    self.assertListEqual(end_points['predictions'].get_shape().as_list(),
+                         [2, 1, 1, num_classes])
+    self.assertTrue('global_pool' in end_points)
+    self.assertListEqual(end_points['global_pool'].get_shape().as_list(),
+                         [2, 1, 1, 32])
+
   def testEndpointNames(self):
     # Like ResnetUtilsTest.testEndPointsV1(), but for the public API.
     global_pool = True

research/slim/train_image_classifier.py

@@ -552,8 +552,6 @@ def main(_):
     # Merge all summaries together.
     summary_op = tf.summary.merge(list(summaries), name='summary_op')
 
-    # Add config to avoid 'could not satisfy explicit device' problem 
-    sess_config = tf.ConfigProto(allow_soft_placement=True)
 
     ###########################
     # Kicks off the training. #
@@ -569,8 +567,7 @@ def main(_):
         log_every_n_steps=FLAGS.log_every_n_steps,
         save_summaries_secs=FLAGS.save_summaries_secs,
         save_interval_secs=FLAGS.save_interval_secs,
-        sync_optimizer=optimizer if FLAGS.sync_replicas else None,
-        session_config=sess_config)
+        sync_optimizer=optimizer if FLAGS.sync_replicas else None)
 
 
 if __name__ == '__main__':

samples/core/get_started/eager.ipynb

@@ -7,7 +7,11 @@
       "version": "0.3.2",
       "views": {},
       "default_view": {},
-      "provenance": []
+      "provenance": [],
+      "collapsed_sections": [
+        "rwxGnsA92emp"
+      ],
+      "toc_visible": true
     },
     "kernelspec": {
       "name": "python3",
@@ -22,7 +26,7 @@
       },
       "cell_type": "markdown",
       "source": [
-        "**Copyright 2018 The TensorFlow Authors.**\n",
+        "##### Copyright 2018 The TensorFlow Authors.\n",
         "\n",
         "Licensed under the Apache License, Version 2.0 (the \"License\");"
       ]
@@ -37,11 +41,11 @@
             "wait_interval": 0
           }
         },
-        "cellView": "form"
+        "cellView": "code"
       },
       "cell_type": "code",
       "source": [
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
         "# You may obtain a copy of the License at\n",
         "#\n",
@@ -65,8 +69,22 @@
       "source": [
         "# Get Started with Eager Execution\n",
         "\n",
-        "Note: you can run **[this notebook, live in Google Colab](https://colab.research.google.com/github/tensorflow/models/blob/master/samples/core/get_started/eager.ipynb)** with zero setup.\n",
         "\n",
+        "<table align=\"left\"><td>\n",
+        "<a target=\"_blank\"  href=\"https://colab.sandbox.google.com/github/tensorflow/models/blob/master/samples/core/get_started/eager.ipynb\">\n",
+        "    <img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>  \n",
+        "</td><td>\n",
+        "<a target=\"_blank\"  href=\"https://github.com/tensorflow/models/blob/master/samples/core/get_started/eager.ipynb\"><img width=32px src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on Github</a></td></table>\n",
+        "\n"
+      ]
+    },
+    {
+      "metadata": {
+        "id": "LDrzLFXE8T1l",
+        "colab_type": "text"
+      },
+      "cell_type": "markdown",
+      "source": [
         "This tutorial describes how to use machine learning to *categorize* Iris flowers by species. It uses [TensorFlow](https://www.tensorflow.org)'s eager execution to (1) build a *model*, (2) *train* the model on example data, and (3) use the model to make *predictions* on unknown data. Machine learning experience isn't required to follow this guide, but you'll need to read some Python code.\n",
         "\n",
         "## TensorFlow programming\n",
@@ -114,7 +132,7 @@
       "source": [
         "### Install the latest version of TensorFlow\n",
         "\n",
-        "This tutorial uses eager execution, which is available in [TensorFlow 1.7](https://www.tensorflow.org/install/). (You may need to restart the runtime after upgrading.)"
+        "This tutorial uses eager execution, which is available in [TensorFlow 1.8](https://www.tensorflow.org/install/). (You may need to restart the runtime after upgrading.)"
       ]
     },
     {
@@ -374,7 +392,7 @@
         "train_dataset = train_dataset.batch(32)\n",
         "\n",
         "# View a single example entry from a batch\n",
-        "features, label = tfe.Iterator(train_dataset).next()\n",
+        "features, label = iter(train_dataset).next()\n",
         "print(\"example features:\", features[0])\n",
         "print(\"example label:\", label[0])"
       ],
@@ -508,7 +526,7 @@
         "\n",
         "\n",
         "def grad(model, inputs, targets):\n",
-        "  with tfe.GradientTape() as tape:\n",
+        "  with tf.GradientTape() as tape:\n",
         "    loss_value = loss(model, inputs, targets)\n",
         "  return tape.gradient(loss_value, model.variables)"
       ],
@@ -522,7 +540,7 @@
       },
       "cell_type": "markdown",
       "source": [
-        "The `grad` function uses the `loss` function and the [tfe.GradientTape](https://www.tensorflow.org/api_docs/python/tf/contrib/eager/GradientTape) to record operations that compute the *[gradients](https://developers.google.com/machine-learning/crash-course/glossary#gradient)* used to optimize our model. For more examples of this, see the [eager execution guide](https://www.tensorflow.org/programmers_guide/eager)."
+        "The `grad` function uses the `loss` function and the [tf.GradientTape](https://www.tensorflow.org/api_docs/python/tf/GradientTape) to record operations that compute the *[gradients](https://developers.google.com/machine-learning/crash-course/glossary#gradient)* used to optimize our model. For more examples of this, see the [eager execution guide](https://www.tensorflow.org/programmers_guide/eager)."
       ]
     },
     {
@@ -614,7 +632,7 @@
         "  epoch_accuracy = tfe.metrics.Accuracy()\n",
         "\n",
         "  # Training loop - using batches of 32\n",
-        "  for x, y in tfe.Iterator(train_dataset):\n",
+        "  for x, y in train_dataset:\n",
         "    # Optimize the model\n",
         "    grads = grad(model, x, y)\n",
         "    optimizer.apply_gradients(zip(grads, model.variables),\n",
@@ -680,9 +698,7 @@
         "\n",
         "axes[1].set_ylabel(\"Accuracy\", fontsize=14)\n",
         "axes[1].set_xlabel(\"Epoch\", fontsize=14)\n",
-        "axes[1].plot(train_accuracy_results)\n",
-        "\n",
-        "plt.show()"
+        "axes[1].plot(train_accuracy_results);"
       ],
       "execution_count": 0,
       "outputs": []
@@ -800,7 +816,7 @@
       "source": [
         "test_accuracy = tfe.metrics.Accuracy()\n",
         "\n",
-        "for (x, y) in tfe.Iterator(test_dataset):\n",
+        "for (x, y) in test_dataset:\n",
         "  prediction = tf.argmax(model(x), axis=1, output_type=tf.int32)\n",
         "  test_accuracy(prediction, y)\n",
         "\n",
@@ -871,4 +887,4 @@
       ]
     }
   ]
-}
+}
\ No newline at end of file