Merge commit for internal changes

22 files changed, 887 insertions, 290 deletions

diff --git a/tensorflow/contrib/autograph/examples/notebooks/rnn_keras_estimator.ipynb b/tensorflow/contrib/autograph/examples/notebooks/rnn_keras_estimator.ipynb
index 324b23c24b..44532cb078 100644
--- a/tensorflow/contrib/autograph/examples/notebooks/rnn_keras_estimator.ipynb
+++ b/tensorflow/contrib/autograph/examples/notebooks/rnn_keras_estimator.ipynb
@@ -190,7 +190,6 @@
         "    self.upper_cell = tf.contrib.rnn.LSTMBlockCell(128)\n",
         "    self.relu_layer = tf.layers.Dense(3, activation=tf.nn.relu)\n",
         "\n",
-        "\n",
         "  def _rnn_layer(self, chars, cell, batch_size, training):\n",
         "    \"\"\"A single RNN layer.\n",
         "\n",
@@ -203,13 +202,12 @@
         "    Returns:\n",
         "      A Tensor of shape (max_sequence_length, batch_size, output_size).\n",
         "    \"\"\"\n",
-        "    hidden_outputs = []\n",
-        "    autograph.utils.set_element_type(hidden_outputs, tf.float32)\n",
+        "    hidden_outputs = tf.TensorArray(tf.float32, 0, True)\n",
         "    state, output = cell.zero_state(batch_size, tf.float32)\n",
         "    for ch in chars:\n",
         "      cell_output, (state, output) = cell.call(ch, (state, output))\n",
         "      hidden_outputs.append(cell_output)\n",
-        "    hidden_outputs = hidden_outputs.stack()\n",
+        "    hidden_outputs = autograph.stack(hidden_outputs)\n",
         "    if training:\n",
         "      hidden_outputs = tf.nn.dropout(hidden_outputs, 0.5)\n",
         "    return hidden_outputs\n",
@@ -223,7 +221,7 @@
         "\n",
         "\n",
         "  def call(self, inputs, training=False):\n",
-        "    \"\"\"The RNN model code. Uses Eager and \n",
+        "    \"\"\"The RNN model code. Uses Eager.\n",
         "\n",
         "    The model consists of two RNN layers (made by lower_cell and upper_cell),\n",
         "    followed by a fully connected layer with ReLU activation.\n",
@@ -243,7 +241,8 @@
         "    seq = self._rnn_layer(seq, self.upper_cell, batch_size, training)\n",
         "\n",
         "    # Grab just the end-of-sequence from each output.\n",
-        "    indices = tf.stack([length - 1, range(batch_size)], axis=1)\n",
+        "    indices = (length - 1, range(batch_size))\n",
+        "    indices = tf.stack(indices, 1)\n",
         "    sequence_ends = tf.gather_nd(seq, indices)\n",
         "    return self.relu_layer(sequence_ends)\n",
         "\n",
@@ -381,7 +380,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 7,
+      "execution_count": 107,
       "metadata": {
         "colab": {
           "autoexec": {
@@ -392,9 +391,9 @@
         },
         "colab_type": "code",
         "executionInfo": {
-          "elapsed": 10604,
+          "elapsed": 5454,
           "status": "ok",
-          "timestamp": 1524095272039,
+          "timestamp": 1529952160455,
           "user": {
             "displayName": "",
             "photoUrl": "",
@@ -403,7 +402,7 @@
           "user_tz": 240
         },
         "id": "2pg1AfbxBJQq",
-        "outputId": "9c924b4f-06e1-4538-976c-a3e1ddac5660",
+        "outputId": "4aef3052-f7c7-4bb1-a0a2-73fef2e96efb",
         "slideshow": {
           "slide_type": "-"
         }
@@ -413,7 +412,7 @@
           "name": "stdout",
           "output_type": "stream",
           "text": [
-            "Eval loss at step 100: 0.0674834\n"
+            "Eval loss at step 100: 0.0705221\n"
           ]
         }
       ],
@@ -423,8 +422,8 @@
         "    'learning_rate': 0.01,\n",
         "}\n",
         "\n",
-        "train_url = \"https://raw.githubusercontent.com/random-forests/tensorflow-workshop/master/extras/colorbot/data/train.csv\"\n",
-        "test_url = \"https://raw.githubusercontent.com/random-forests/tensorflow-workshop/master/extras/colorbot/data/test.csv\"\n",
+        "train_url = \"https://raw.githubusercontent.com/random-forests/tensorflow-workshop/master/archive/extras/colorbot/data/train.csv\"\n",
+        "test_url = \"https://raw.githubusercontent.com/random-forests/tensorflow-workshop/master/archive/extras/colorbot/data/test.csv\"\n",
         "data_dir = \"tmp/rnn/data\"\n",
         "\n",
         "regressor = tf.estimator.Estimator(\n",
@@ -457,7 +456,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 8,
+      "execution_count": 108,
       "metadata": {
         "colab": {
           "autoexec": {
@@ -468,9 +467,9 @@
         },
         "colab_type": "code",
         "executionInfo": {
-          "elapsed": 7990,
+          "elapsed": 3432,
           "status": "ok",
-          "timestamp": 1524095280105,
+          "timestamp": 1529952163923,
           "user": {
             "displayName": "",
             "photoUrl": "",
@@ -479,7 +478,7 @@
           "user_tz": 240
         },
         "id": "dxHex2tUN_10",
-        "outputId": "2b889e5a-b9ed-4645-bf03-d98f26c72101",
+        "outputId": "1ff438f2-b045-4f4e-86a0-4dae7503f6b2",
         "slideshow": {
           "slide_type": "slide"
         }
@@ -491,12 +490,12 @@
               "\u003clink rel=stylesheet type=text/css href='/nbextensions/google.colab/tabbar.css'\u003e\u003c/link\u003e"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.HTML at 0x7f3f36aa6cd0\u003e"
+              "\u003cIPython.core.display.HTML at 0x7fcd7222a110\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "outputarea_id1"
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -507,12 +506,12 @@
               "\u003cscript src='/nbextensions/google.colab/tabbar_main.min.js'\u003e\u003c/script\u003e"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.HTML at 0x7f3eca67f7d0\u003e"
+              "\u003cIPython.core.display.HTML at 0x7fcd7222a8d0\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "outputarea_id1"
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -520,15 +519,15 @@
         {
           "data": {
             "text/html": [
-              "\u003cdiv id=\"id1\"\u003e\u003c/div\u003e"
+              "\u003cdiv id=\"id3\"\u003e\u003c/div\u003e"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.HTML at 0x7f3eca67f8d0\u003e"
+              "\u003cIPython.core.display.HTML at 0x7fcd7222a050\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "outputarea_id1"
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -536,16 +535,16 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"e8ddfa22-4362-11e8-91ec-c8d3ffb5fbe0\"] = colab_lib.createTabBar({\"contentBorder\": [\"0px\"], \"elementId\": \"id1\", \"borderColor\": [\"#a7a7a7\"], \"contentHeight\": [\"initial\"], \"tabNames\": [\"RNN Colorbot\"], \"location\": \"top\", \"initialSelection\": 0});\n",
-              "//# sourceURL=js_71b9087b6d"
+              "window[\"8a03307e-78a7-11e8-99f9-c8d3ffb5fbe0\"] = colab_lib.createTabBar({\"contentBorder\": [\"0px\"], \"elementId\": \"id3\", \"contentHeight\": [\"initial\"], \"tabNames\": [\"RNN Colorbot\"], \"location\": \"top\", \"initialSelection\": 0, \"borderColor\": [\"#a7a7a7\"]});\n",
+              "//# sourceURL=js_dc5d7f2784"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67f950\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222a190\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "outputarea_id1"
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -553,16 +552,16 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"e8ddfa23-4362-11e8-91ec-c8d3ffb5fbe0\"] = window[\"id1\"].setSelectedTabIndex(0);\n",
-              "//# sourceURL=js_e390445f33"
+              "window[\"8a03307f-78a7-11e8-99f9-c8d3ffb5fbe0\"] = window[\"id3\"].setSelectedTabIndex(0);\n",
+              "//# sourceURL=js_be7950150b"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67f990\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222ac90\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "outputarea_id1"
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -570,17 +569,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"e8ddfa24-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.getActiveOutputArea();\n",
-              "//# sourceURL=js_241dd76d85"
+              "window[\"8a033080-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.getActiveOutputArea();\n",
+              "//# sourceURL=js_d0c3bd4eaa"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fc50\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222aad0\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -588,17 +587,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"e8ddfa25-4362-11e8-91ec-c8d3ffb5fbe0\"] = document.querySelector(\"#id1_content_0\");\n",
-              "//# sourceURL=js_60c64e3d50"
+              "window[\"8a033081-78a7-11e8-99f9-c8d3ffb5fbe0\"] = document.querySelector(\"#id3_content_0\");\n",
+              "//# sourceURL=js_f10f6eba86"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fd90\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222aed0\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -606,17 +605,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"e8ddfa26-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"e8ddfa25-4362-11e8-91ec-c8d3ffb5fbe0\"]);\n",
-              "//# sourceURL=js_14ea437cbd"
+              "window[\"8a033082-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"8a033081-78a7-11e8-99f9-c8d3ffb5fbe0\"]);\n",
+              "//# sourceURL=js_ff29697179"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fe10\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222abd0\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -624,17 +623,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"e8ddfa27-4362-11e8-91ec-c8d3ffb5fbe0\"] = window[\"id1\"].setSelectedTabIndex(0);\n",
-              "//# sourceURL=js_09294c2226"
+              "window[\"8a033083-78a7-11e8-99f9-c8d3ffb5fbe0\"] = window[\"id3\"].setSelectedTabIndex(0);\n",
+              "//# sourceURL=js_ff85295dc7"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fcd0\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222ab90\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -642,17 +641,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec965514-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"e8ddfa24-4362-11e8-91ec-c8d3ffb5fbe0\"]);\n",
-              "//# sourceURL=js_e5e8266997"
+              "window[\"8b18d8dc-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"8a033080-78a7-11e8-99f9-c8d3ffb5fbe0\"]);\n",
+              "//# sourceURL=js_ed7aabfedb"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fe10\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222a110\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -660,17 +659,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec965515-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.getActiveOutputArea();\n",
-              "//# sourceURL=js_07a097f0ee"
+              "window[\"8b18d8dd-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.getActiveOutputArea();\n",
+              "//# sourceURL=js_c86f8feaf4"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fc90\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222acd0\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -678,17 +677,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec965516-4362-11e8-91ec-c8d3ffb5fbe0\"] = document.querySelector(\"#id1_content_0\");\n",
-              "//# sourceURL=js_790d669ca8"
+              "window[\"8b18d8de-78a7-11e8-99f9-c8d3ffb5fbe0\"] = document.querySelector(\"#id3_content_0\");\n",
+              "//# sourceURL=js_4d0fde6662"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67f8d0\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222ae50\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -696,17 +695,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec965517-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"ec965516-4362-11e8-91ec-c8d3ffb5fbe0\"]);\n",
-              "//# sourceURL=js_d30df771f0"
+              "window[\"8b18d8df-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"8b18d8de-78a7-11e8-99f9-c8d3ffb5fbe0\"]);\n",
+              "//# sourceURL=js_3f66d52720"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fd90\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222a210\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -714,32 +713,32 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec965518-4362-11e8-91ec-c8d3ffb5fbe0\"] = window[\"id1\"].setSelectedTabIndex(0);\n",
-              "//# sourceURL=js_8a43a2da4b"
+              "window[\"8b18d8e0-78a7-11e8-99f9-c8d3ffb5fbe0\"] = window[\"id3\"].setSelectedTabIndex(0);\n",
+              "//# sourceURL=js_375f5ae6d7"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fc50\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd7222a310\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
         },
         {
           "data": {
-            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAQwAAAENCAYAAAD60Fs2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAQwAAAENCAYAAAD60Fs2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
             "text/plain": [
-              "\u003cmatplotlib.figure.Figure at 0x7f3ecc00bf10\u003e"
+              "\u003cmatplotlib.figure.Figure at 0x7fcd0d02dc90\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1",
+              "id3_content_0",
+              "outputarea_id3",
               "user_output"
             ]
           },
@@ -748,17 +747,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec965519-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"ec965515-4362-11e8-91ec-c8d3ffb5fbe0\"]);\n",
-              "//# sourceURL=js_893ad561f4"
+              "window[\"8b18d8e1-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"8b18d8dd-78a7-11e8-99f9-c8d3ffb5fbe0\"]);\n",
+              "//# sourceURL=js_34b0509660"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31b55c90\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6e850\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -766,17 +765,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec96551a-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.getActiveOutputArea();\n",
-              "//# sourceURL=js_2d99e0ac17"
+              "window[\"8b18d8e2-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.getActiveOutputArea();\n",
+              "//# sourceURL=js_518a0f26fe"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67fe50\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6ec90\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -784,17 +783,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec96551b-4362-11e8-91ec-c8d3ffb5fbe0\"] = document.querySelector(\"#id1_content_0\");\n",
-              "//# sourceURL=js_5c19462e32"
+              "window[\"8b18d8e3-78a7-11e8-99f9-c8d3ffb5fbe0\"] = document.querySelector(\"#id3_content_0\");\n",
+              "//# sourceURL=js_17eb3ff612"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31b55dd0\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6eb50\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -802,17 +801,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec96551c-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"ec96551b-4362-11e8-91ec-c8d3ffb5fbe0\"]);\n",
-              "//# sourceURL=js_b9c8b7567b"
+              "window[\"8b18d8e4-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"8b18d8e3-78a7-11e8-99f9-c8d3ffb5fbe0\"]);\n",
+              "//# sourceURL=js_99da807c8e"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31b55a50\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6eb90\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -820,17 +819,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec96551d-4362-11e8-91ec-c8d3ffb5fbe0\"] = window[\"id1\"].setSelectedTabIndex(0);\n",
-              "//# sourceURL=js_fd05186348"
+              "window[\"8b18d8e5-78a7-11e8-99f9-c8d3ffb5fbe0\"] = window[\"id3\"].setSelectedTabIndex(0);\n",
+              "//# sourceURL=js_dee01cb4b6"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31b55810\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6e610\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -838,16 +837,16 @@
         {
           "data": {
             "text/html": [
-              "\u003cdiv class=id_888646481 style=\"margin-right:10px; display:flex;align-items:center;\"\u003e\u003cspan style=\"margin-right: 3px;\"\u003e\u003c/span\u003e\u003c/div\u003e"
+              "\u003cdiv class=id_853612217 style=\"margin-right:10px; display:flex;align-items:center;\"\u003e\u003cspan style=\"margin-right: 3px;\"\u003e\u003c/span\u003e\u003c/div\u003e"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.HTML at 0x7f3f32414810\u003e"
+              "\u003cIPython.core.display.HTML at 0x7fcd7222aa10\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1",
+              "id3_content_0",
+              "outputarea_id3",
               "user_output"
             ]
           },
@@ -856,17 +855,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec96551e-4362-11e8-91ec-c8d3ffb5fbe0\"] = jQuery(\".id_888646481 span\");\n",
-              "//# sourceURL=js_efef96e882"
+              "window[\"8b18d8e6-78a7-11e8-99f9-c8d3ffb5fbe0\"] = jQuery(\".id_853612217 span\");\n",
+              "//# sourceURL=js_8c378be329"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31b55710\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6e990\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1",
+              "id3_content_0",
+              "outputarea_id3",
               "user_output"
             ]
           },
@@ -875,17 +874,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ec96551f-4362-11e8-91ec-c8d3ffb5fbe0\"] = window[\"ec96551e-4362-11e8-91ec-c8d3ffb5fbe0\"].text(\"Give me a color name (or press 'enter' to exit): \");\n",
-              "//# sourceURL=js_6eca889864"
+              "window[\"8b18d8e7-78a7-11e8-99f9-c8d3ffb5fbe0\"] = window[\"8b18d8e6-78a7-11e8-99f9-c8d3ffb5fbe0\"].text(\"Give me a color name (or press 'enter' to exit): \");\n",
+              "//# sourceURL=js_f0b946600c"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3eca67f990\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6e310\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1",
+              "id3_content_0",
+              "outputarea_id3",
               "user_output"
             ]
           },
@@ -894,17 +893,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ed8ea972-4362-11e8-91ec-c8d3ffb5fbe0\"] = jQuery(\".id_888646481 input\");\n",
-              "//# sourceURL=js_f02070cc60"
+              "window[\"8b18d8e9-78a7-11e8-99f9-c8d3ffb5fbe0\"] = jQuery(\".id_853612217 input\");\n",
+              "//# sourceURL=js_9e21b1373a"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31b553d0\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6ea90\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1",
+              "id3_content_0",
+              "outputarea_id3",
               "user_output"
             ]
           },
@@ -913,17 +912,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ed8ea973-4362-11e8-91ec-c8d3ffb5fbe0\"] = window[\"ed8ea972-4362-11e8-91ec-c8d3ffb5fbe0\"].remove();\n",
-              "//# sourceURL=js_ed9faba660"
+              "window[\"8b18d8ea-78a7-11e8-99f9-c8d3ffb5fbe0\"] = window[\"8b18d8e9-78a7-11e8-99f9-c8d3ffb5fbe0\"].remove();\n",
+              "//# sourceURL=js_a7764968c6"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31a95450\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6e5d0\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1",
+              "id3_content_0",
+              "outputarea_id3",
               "user_output"
             ]
           },
@@ -932,17 +931,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ed8ea974-4362-11e8-91ec-c8d3ffb5fbe0\"] = jQuery(\".id_888646481 span\");\n",
-              "//# sourceURL=js_f3458d7074"
+              "window[\"8b18d8eb-78a7-11e8-99f9-c8d3ffb5fbe0\"] = jQuery(\".id_853612217 span\");\n",
+              "//# sourceURL=js_74279d3ff0"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31a95250\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6e890\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1",
+              "id3_content_0",
+              "outputarea_id3",
               "user_output"
             ]
           },
@@ -951,17 +950,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ed8ea975-4362-11e8-91ec-c8d3ffb5fbe0\"] = window[\"ed8ea974-4362-11e8-91ec-c8d3ffb5fbe0\"].text(\"Give me a color name (or press 'enter' to exit): \");\n",
-              "//# sourceURL=js_3ffd97bd6f"
+              "window[\"8b18d8ec-78a7-11e8-99f9-c8d3ffb5fbe0\"] = window[\"8b18d8eb-78a7-11e8-99f9-c8d3ffb5fbe0\"].text(\"Give me a color name (or press 'enter' to exit): \");\n",
+              "//# sourceURL=js_82b6c34cdb"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31a953d0\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6e8d0\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1",
+              "id3_content_0",
+              "outputarea_id3",
               "user_output"
             ]
           },
@@ -970,17 +969,17 @@
         {
           "data": {
             "application/javascript": [
-              "window[\"ed8ea976-4362-11e8-91ec-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"ec96551a-4362-11e8-91ec-c8d3ffb5fbe0\"]);\n",
-              "//# sourceURL=js_7f73e8bcca"
+              "window[\"8b18d8ed-78a7-11e8-99f9-c8d3ffb5fbe0\"] = google.colab.output.setActiveOutputArea(window[\"8b18d8e2-78a7-11e8-99f9-c8d3ffb5fbe0\"]);\n",
+              "//# sourceURL=js_ff6144734a"
             ],
             "text/plain": [
-              "\u003cIPython.core.display.Javascript at 0x7f3f31b55710\u003e"
+              "\u003cIPython.core.display.Javascript at 0x7fcd08e6e8d0\u003e"
             ]
           },
           "metadata": {
             "tags": [
-              "id1_content_0",
-              "outputarea_id1"
+              "id3_content_0",
+              "outputarea_id3"
             ]
           },
           "output_type": "display_data"
@@ -1043,28 +1042,6 @@
         "kind": "local"
       },
       "name": "RNN Colorbot using Keras and Estimators",
-      "provenance": [
-        {
-          "file_id": "1CtzefX39ffFibX_BqE6cRbT0UW_DdVKl",
-          "timestamp": 1523579810961
-        },
-        {
-          "file_id": "1DcfimonWU11tmyivKBGVrbpAl3BIOaRG",
-          "timestamp": 1523016192637
-        },
-        {
-          "file_id": "1wCZUh73zTNs1jzzYjqoxMIdaBWCdKJ2K",
-          "timestamp": 1522238054357
-        },
-        {
-          "file_id": "1_HpC-RrmIv4lNaqeoslUeWaX8zH5IXaJ",
-          "timestamp": 1521743157199
-        },
-        {
-          "file_id": "1mjO2fQ2F9hxpAzw2mnrrUkcgfb7xSGW-",
-          "timestamp": 1520522344607
-        }
-      ],
       "version": "0.3.2",
       "views": {}
     },
diff --git a/tensorflow/contrib/cmake/tf_c.cmake b/tensorflow/contrib/cmake/tf_c.cmake
index 2e0a2fcef4..7a30eb94f5 100644
--- a/tensorflow/contrib/cmake/tf_c.cmake
+++ b/tensorflow/contrib/cmake/tf_c.cmake
@@ -36,16 +36,3 @@ add_dependencies(
   tf_cc_while_loop
   tf_core_lib
   tf_protos_cc)
-
-if(tensorflow_BUILD_PYTHON_BINDINGS)
-  add_library(tf_c_python_api OBJECT
-    "${tensorflow_source_dir}/tensorflow/c/python_api.cc"
-    "${tensorflow_source_dir}/tensorflow/c/python_api.h"
-  )
-  add_dependencies(
-    tf_c_python_api
-    tf_c
-    tf_core_lib
-    tf_core_framework
-    tf_protos_cc)
-endif()
diff --git a/tensorflow/contrib/cmake/tf_python.cmake b/tensorflow/contrib/cmake/tf_python.cmake
index 786ea05c74..e3b59001bc 100755
--- a/tensorflow/contrib/cmake/tf_python.cmake
+++ b/tensorflow/contrib/cmake/tf_python.cmake
@@ -456,6 +456,18 @@ add_custom_command(
       COMMENT "Running SWIG to generate Python wrappers"
       VERBATIM )
 
+add_library(tf_c_python_api OBJECT
+  "${tensorflow_source_dir}/tensorflow/c/python_api.cc"
+  "${tensorflow_source_dir}/tensorflow/c/python_api.h"
+)
+add_dependencies(
+  tf_c_python_api
+  tf_c
+  tf_core_lib
+  tf_core_framework
+  tf_protos_cc
+  tf_python_protos_cc)
+
 set (pywrap_tensorflow_internal_src
     "${tensorflow_source_dir}/tensorflow/core/profiler/internal/print_model_analysis.h"
     "${tensorflow_source_dir}/tensorflow/core/profiler/internal/print_model_analysis.cc"
diff --git a/tensorflow/contrib/data/kernels/prefetching_kernels.cc b/tensorflow/contrib/data/kernels/prefetching_kernels.cc
index a2bfce0362..0fc3773475 100644
--- a/tensorflow/contrib/data/kernels/prefetching_kernels.cc
+++ b/tensorflow/contrib/data/kernels/prefetching_kernels.cc
@@ -269,18 +269,20 @@ class FunctionBufferResourceHandleOp : public OpKernel {
     std::vector<Tensor> func_args;
     func_args.push_back(*string_arg);
 
+    const string& source_device = ctx->device()->name();
+
     // Obtain and canonicalize target_device.
     const Tensor* target_arg;
     OP_REQUIRES_OK(ctx, ctx->input("target_device", &target_arg));
-    const string& target_device =
-        DeviceNameUtils::CanonicalizeDeviceName(target_arg->scalar<string>()());
+    string target_device;
+    OP_REQUIRES_OK(ctx, DeviceNameUtils::CanonicalizeDeviceName(
+                            target_arg->scalar<string>()(), source_device,
+                            &target_device));
 
     FunctionLibraryRuntime* lib = ctx->function_library();
     OP_REQUIRES(ctx, lib != nullptr,
                 errors::Internal("No function library is provided."));
 
-    const string& source_device = ctx->device()->name();
-
     mutex_lock l(mu_);
     if (!initialized_) {
       OP_REQUIRES_OK(ctx, cinfo_.Init(ctx->resource_manager(), def()));
diff --git a/tensorflow/contrib/data/python/kernel_tests/prefetching_ops_test.py b/tensorflow/contrib/data/python/kernel_tests/prefetching_ops_test.py
index b08132cd72..9c7040de9e 100644
--- a/tensorflow/contrib/data/python/kernel_tests/prefetching_ops_test.py
+++ b/tensorflow/contrib/data/python/kernel_tests/prefetching_ops_test.py
@@ -235,6 +235,36 @@ class PrefetchToDeviceTest(test.TestCase):
       with self.assertRaises(errors.OutOfRangeError):
         sess.run(next_element)
 
+  def testPrefetchToSameDevice(self):
+    host_dataset = dataset_ops.Dataset.range(10)
+    device_dataset = host_dataset.apply(
+        prefetching_ops.prefetch_to_device(
+            "/job:localhost/replica:0/task:0/device:CPU:0"))
+
+    # NOTE(mrry): This device block creates the "host" dataset and iterator on
+    # /cpu:0, and ensures that the prefetching is across devices. In typical use
+    # this would not be necessary, because the GPU device would not support any
+    # of the dataset-related ops.
+    with ops.device("/cpu:0"):
+      iterator = device_dataset.make_one_shot_iterator()
+
+    self.assertEqual(host_dataset.output_types, device_dataset.output_types)
+    self.assertEqual(host_dataset.output_types, iterator.output_types)
+    self.assertEqual(host_dataset.output_shapes, device_dataset.output_shapes)
+    self.assertEqual(host_dataset.output_shapes, iterator.output_shapes)
+    self.assertEqual(host_dataset.output_classes, device_dataset.output_classes)
+    self.assertEqual(host_dataset.output_classes, iterator.output_classes)
+
+    next_element = iterator.get_next()
+    self.assertEqual(dtypes.int64, next_element.dtype)
+    self.assertEqual([], next_element.shape)
+
+    with self.test_session() as sess:
+      for i in range(10):
+        self.assertEqual(i, sess.run(next_element))
+      with self.assertRaises(errors.OutOfRangeError):
+        sess.run(next_element)
+
   def testPrefetchDictToDevice(self):
     host_dataset = dataset_ops.Dataset.range(10).map(lambda x: {"a": x})
     device_dataset = host_dataset.apply(
diff --git a/tensorflow/contrib/eager/python/examples/revnet/blocks.py b/tensorflow/contrib/eager/python/examples/revnet/blocks.py
index af41f64286..74c1825a49 100644
--- a/tensorflow/contrib/eager/python/examples/revnet/blocks.py
+++ b/tensorflow/contrib/eager/python/examples/revnet/blocks.py
@@ -24,6 +24,7 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
+import six
 import tensorflow as tf
 from tensorflow.contrib.eager.python.examples.revnet import ops
 
@@ -93,9 +94,18 @@ class RevBlock(tf.keras.Model):
 
     for i in reversed(range(len(self.blocks))):
       block = self.blocks[i]
-      y_inv = x if i == 0 else block.backward(y, training=training)
+      if i == 0:
+        y_inv = x
+      else:
+        # Don't update running stats when reconstructing activations
+        vars_and_vals = block.get_moving_stats()
+        y_inv = block.backward(y, training=training)
+        block.restore_moving_stats(vars_and_vals)
+
+      # Update running stats when computing gradients during training
       dy, grads, vars_ = block.backward_grads_and_vars(
           y_inv, dy, training=training)
+
       grads_all += grads
       vars_all += vars_
 
@@ -159,17 +169,18 @@ class _Residual(tf.keras.Model):
     """Apply residual block to inputs."""
 
     x1, x2 = tf.split(x, num_or_size_splits=2, axis=self.axis)
-    f_x2 = self.f.call(x2, training=training)
+    f_x2 = self.f(x2, training=training)
     # TODO(lxuechen): Replace with simpler downsampling
     x1_down = ops.downsample(
         x1, self.filters // 2, self.strides, axis=self.axis)
     x2_down = ops.downsample(
         x2, self.filters // 2, self.strides, axis=self.axis)
     y1 = f_x2 + x1_down
-    g_y1 = self.g.call(y1, training=training)  # self.g(y1) gives pylint error
+    g_y1 = self.g(y1, training=training)
     y2 = g_y1 + x2_down
-    if not concat:  # Concat option needed for correct backward grads
+    if not concat:  # For correct backward grads
       return y1, y2
+
     return tf.concat([y1, y2], axis=self.axis)
 
   def backward(self, y, training=True):
@@ -178,9 +189,9 @@ class _Residual(tf.keras.Model):
     assert self.strides == (1, 1)
 
     y1, y2 = tf.split(y, num_or_size_splits=2, axis=self.axis)
-    g_y1 = self.g.call(y1, training=training)
+    g_y1 = self.g(y1, training=training)
     x2 = y2 - g_y1
-    f_x2 = self.f.call(x2, training=training)
+    f_x2 = self.f(x2, training=training)
     x1 = y1 - f_x2
 
     return tf.concat([x1, x2], axis=self.axis)
@@ -216,6 +227,22 @@ class _Residual(tf.keras.Model):
 
     return tf.concat([dx1, dx2], axis=self.axis), grads, vars_
 
+  def get_moving_stats(self):
+    vars_and_vals = {}
+
+    def _is_moving_var(v):  # pylint: disable=invalid-name
+      n = v.name
+      return n.endswith("moving_mean:0") or n.endswith("moving_variance:0")
+
+    for v in filter(_is_moving_var, self.f.variables + self.g.variables):
+      vars_and_vals[v] = v.read_value()
+
+    return vars_and_vals
+
+  def restore_moving_stats(self, vars_and_vals):
+    for var_, val in six.iteritems(vars_and_vals):
+      var_.assign(val)
+
 
 def _BottleneckResidualInner(filters,
                              strides,
diff --git a/tensorflow/contrib/eager/python/examples/revnet/blocks_test.py b/tensorflow/contrib/eager/python/examples/revnet/blocks_test.py
index f4436fd925..a28ca6e3e0 100644
--- a/tensorflow/contrib/eager/python/examples/revnet/blocks_test.py
+++ b/tensorflow/contrib/eager/python/examples/revnet/blocks_test.py
@@ -240,13 +240,12 @@ class _ResidualTest(tf.test.TestCase):
       x = tf.random_normal(shape=data_shape)
       residual = blocks._Residual(
           filters=16, strides=(1, 1), input_shape=input_shape)
+
       y_tr, y_ev = residual(x, training=True), residual(x, training=False)
-      x_ = residual.backward(y_tr, training=True)
-      # The numerical loss is alarming; reconstructed inputs could differ from
-      # the original inputs often by more than 1e-3
-      self.assertAllClose(x, x_, rtol=1e-01, atol=1e-01)
       x_ = residual.backward(y_ev, training=False)
-      self.assertAllClose(x, x_, rtol=1e-01, atol=1e-01)
+      self.assertAllClose(x, x_, rtol=1e-1, atol=1e-1)
+      x_ = residual.backward(y_tr, training=True)  # This updates moving avg
+      self.assertAllClose(x, x_, rtol=1e-1, atol=1e-1)
 
   def test_backward_channels_last(self):
     """Test `backward` function with `channels_last` data format."""
@@ -259,12 +258,12 @@ class _ResidualTest(tf.test.TestCase):
           strides=(1, 1),
           input_shape=input_shape,
           data_format="channels_last")
+
       y_tr, y_ev = residual(x, training=True), residual(x, training=False)
-      x_ = residual.backward(y_tr, training=True)
-      # Egregious numerical error
-      self.assertAllClose(x, x_, rtol=1e-01, atol=1e-01)
       x_ = residual.backward(y_ev, training=False)
-      self.assertAllClose(x, x_, rtol=1e-01, atol=1e-01)
+      self.assertAllClose(x, x_, rtol=1e-1, atol=1e-1)
+      x_ = residual.backward(y_tr, training=True)  # This updates moving avg
+      self.assertAllClose(x, x_, rtol=1e-1, atol=1e-1)
 
   def test_backward_grads_and_vars_channels_first(self):
     """Test `backward_grads` function with `channels_first` data format."""
@@ -278,6 +277,8 @@ class _ResidualTest(tf.test.TestCase):
       dy = tf.random_normal(shape=data_shape)
       residual = blocks._Residual(
           filters=16, strides=(1, 1), input_shape=input_shape)
+
+      vars_and_vals = residual.get_moving_stats()
       dx_tr, grads_tr, vars_tr = residual.backward_grads_and_vars(
           x, dy=dy, training=True)
       dx_ev, grads_ev, vars_ev = residual.backward_grads_and_vars(
@@ -289,10 +290,23 @@ class _ResidualTest(tf.test.TestCase):
       self.assertTrue(isinstance(vars_ev, list))
       for grad_tr, var_tr, grad_ev, var_ev in zip(grads_tr, vars_tr, grads_ev,
                                                   vars_ev):
-        if grad_tr is not None:  # Batch norm moving mean, var gives None grad
-          self.assertEqual(grad_tr.shape, grad_ev.shape)
-          self.assertEqual(var_tr.shape, var_ev.shape)
-          self.assertEqual(grad_tr.shape, var_tr.shape)
+        self.assertEqual(grad_tr.shape, grad_ev.shape)
+        self.assertEqual(var_tr.shape, var_ev.shape)
+        self.assertEqual(grad_tr.shape, var_tr.shape)
+
+      # Compare against the true gradient computed by the tape
+      residual.restore_moving_stats(vars_and_vals)
+      with tf.GradientTape(persistent=True) as tape:
+        tape.watch(x)
+        y = residual(x, training=True)
+      grads = tape.gradient(
+          y, [x] + residual.trainable_variables, output_gradients=[dy])
+      dx_tr_true, grads_tr_true = grads[0], grads[1:]
+
+      del tape
+
+      self.assertAllClose(dx_tr, dx_tr_true, rtol=1e-1, atol=1e-1)
+      self.assertAllClose(grads_tr, grads_tr_true, rtol=1e-1, atol=1e-1)
 
   def test_backward_grads_and_vars_channels_last(self):
     """Test `backward_grads` function with `channels_last` data format."""
@@ -306,6 +320,7 @@ class _ResidualTest(tf.test.TestCase):
           strides=(1, 1),
           input_shape=input_shape,
           data_format="channels_last")
+
       dx_tr, grads_tr, vars_tr = residual.backward_grads_and_vars(
           x, dy=dy, training=True)
       dx_ev, grads_ev, vars_ev = residual.backward_grads_and_vars(
@@ -317,10 +332,9 @@ class _ResidualTest(tf.test.TestCase):
       self.assertTrue(isinstance(vars_ev, list))
       for grad_tr, var_tr, grad_ev, var_ev in zip(grads_tr, vars_tr, grads_ev,
                                                   vars_ev):
-        if grad_tr is not None:  # Batch norm moving mean, var gives None grad
-          self.assertEqual(grad_tr.shape, grad_ev.shape)
-          self.assertEqual(var_tr.shape, var_ev.shape)
-          self.assertEqual(grad_tr.shape, var_tr.shape)
+        self.assertEqual(grad_tr.shape, grad_ev.shape)
+        self.assertEqual(var_tr.shape, var_ev.shape)
+        self.assertEqual(grad_tr.shape, var_tr.shape)
 
 
 class _ResidualInnerTest(tf.test.TestCase):
diff --git a/tensorflow/contrib/eager/python/examples/revnet/cifar_input.py b/tensorflow/contrib/eager/python/examples/revnet/cifar_input.py
index 3bc69da5ad..e1d8b3a055 100644
--- a/tensorflow/contrib/eager/python/examples/revnet/cifar_input.py
+++ b/tensorflow/contrib/eager/python/examples/revnet/cifar_input.py
@@ -26,8 +26,6 @@ import tensorflow as tf
 IMAGE_HEIGHT = 32
 IMAGE_WIDTH = 32
 NUM_CHANNEL = 3
-NUM_TRAIN_IMG = 50000
-NUM_TEST_IMG = 10000
 
 
 def get_ds_from_tfrecords(data_dir,
@@ -37,8 +35,8 @@ def get_ds_from_tfrecords(data_dir,
                           epochs=None,
                           shuffle=True,
                           data_format="channels_first",
-                          num_parallel_calls=4,
-                          prefetch=True,
+                          num_parallel_calls=8,
+                          prefetch=0,
                           div255=True,
                           dtype=tf.float32):
   """Returns a tf.train.Dataset object from reading tfrecords.
@@ -48,11 +46,12 @@ def get_ds_from_tfrecords(data_dir,
       split: "train", "validation", or "test"
       data_aug: Apply data augmentation if True
       batch_size: Batch size of dataset object
-      epochs: Number of epochs to repeat the dataset
+      epochs: Number of epochs to repeat the dataset; default `None` means
+          repeating indefinitely
       shuffle: Shuffle the dataset if True
       data_format: `channels_first` or `channels_last`
       num_parallel_calls: Number of threads for dataset preprocess
-      prefetch: Apply prefetch for the dataset if True
+      prefetch: Buffer size for prefetch
       div255: Divide the images by 255 if True
       dtype: Data type of images
   Returns:
@@ -62,7 +61,7 @@ def get_ds_from_tfrecords(data_dir,
       ValueError: Unknown split
   """
 
-  if split not in ["train", "validation", "test"]:
+  if split not in ["train", "validation", "test", "train_all"]:
     raise ValueError("Unknown split {}".format(split))
 
   def _parser(serialized_example):
@@ -74,7 +73,11 @@ def get_ds_from_tfrecords(data_dir,
             "label": tf.FixedLenFeature([], tf.int64),
         })
     image = tf.decode_raw(features["image"], tf.uint8)
-    image = tf.reshape(image, [IMAGE_HEIGHT, IMAGE_WIDTH, NUM_CHANNEL])
+    # Initially reshaping to [H, W, C] does not work
+    image = tf.reshape(image, [NUM_CHANNEL, IMAGE_HEIGHT, IMAGE_WIDTH])
+    # This is needed for `tf.image.resize_image_with_crop_or_pad`
+    image = tf.transpose(image, [1, 2, 0])
+
     image = tf.cast(image, dtype)
     label = tf.cast(features["label"], tf.int32)
 
@@ -93,13 +96,21 @@ def get_ds_from_tfrecords(data_dir,
     return image, label
 
   filename = os.path.join(data_dir, split + ".tfrecords")
-  dataset = tf.data.TFRecordDataset(filename).repeat(epochs)
+  dataset = tf.data.TFRecordDataset(filename)
+  dataset = dataset.repeat(epochs)
   dataset = dataset.map(_parser, num_parallel_calls=num_parallel_calls)
+  dataset = dataset.prefetch(prefetch)
 
-  if prefetch:
-    dataset = dataset.prefetch(batch_size)
   if shuffle:
-    dataset = dataset.shuffle(NUM_TRAIN_IMG)
+    # Find the right size according to the split
+    size = {
+        "train": 40000,
+        "validation": 10000,
+        "test": 10000,
+        "train_all": 50000
+    }[split]
+    dataset = dataset.shuffle(size)
+
   dataset = dataset.batch(batch_size)
 
   return dataset
diff --git a/tensorflow/contrib/eager/python/examples/revnet/config.py b/tensorflow/contrib/eager/python/examples/revnet/config.py
index 263a65dc76..30b0edbf43 100644
--- a/tensorflow/contrib/eager/python/examples/revnet/config.py
+++ b/tensorflow/contrib/eager/python/examples/revnet/config.py
@@ -61,12 +61,13 @@ def get_hparams_cifar_38():
   config.add_hparam("max_train_iter", 80000)
   config.add_hparam("seed", 1234)
   config.add_hparam("shuffle", True)
-  config.add_hparam("prefetch", True)
-  config.add_hparam("log_every", 50)
-  config.add_hparam("save_every", 50)
+  config.add_hparam("log_every", 500)
+  config.add_hparam("save_every", 500)
   config.add_hparam("dtype", tf.float32)
-  config.add_hparam("eval_batch_size", 500)
+  config.add_hparam("eval_batch_size", 1000)
   config.add_hparam("div255", True)
+  # TODO(lxuechen): This is imprecise, when training with validation set,
+  # we only have 40k images in training data
   config.add_hparam("iters_per_epoch", 50000 // config.batch_size)
   config.add_hparam("epochs", config.max_train_iter // config.iters_per_epoch)
 
@@ -104,11 +105,10 @@ def get_hparams_imagenet_56():
   config.add_hparam("max_train_iter", 600000)
   config.add_hparam("seed", 1234)
   config.add_hparam("shuffle", True)
-  config.add_hparam("prefetch", True)
   config.add_hparam("log_every", 50)
   config.add_hparam("save_every", 50)
   config.add_hparam("dtype", tf.float32)
-  config.add_hparam("eval_batch_size", 500)
+  config.add_hparam("eval_batch_size", 1000)
   config.add_hparam("div255", True)
   # TODO(lxuechen): Update this according to ImageNet data
   config.add_hparam("iters_per_epoch", 50000 // config.batch_size)
diff --git a/tensorflow/contrib/eager/python/examples/revnet/main.py b/tensorflow/contrib/eager/python/examples/revnet/main.py
index 9ef11f8e9b..1065592509 100644
--- a/tensorflow/contrib/eager/python/examples/revnet/main.py
+++ b/tensorflow/contrib/eager/python/examples/revnet/main.py
@@ -19,9 +19,11 @@ from __future__ import division
 from __future__ import print_function
 
 import os
+import sys
 
 from absl import flags
 import tensorflow as tf
+from tqdm import tqdm
 from tensorflow.contrib.eager.python.examples.revnet import cifar_input
 from tensorflow.contrib.eager.python.examples.revnet import config as config_
 from tensorflow.contrib.eager.python.examples.revnet import revnet
@@ -38,28 +40,54 @@ def main(_):
 
   tf.enable_eager_execution()
   config = config_.get_hparams_cifar_38()
-  model = revnet.RevNet(config=config)
-
-  ds_train = cifar_input.get_ds_from_tfrecords(
-      data_dir=FLAGS.data_dir,
-      split="train",
-      data_aug=True,
-      batch_size=config.batch_size,
-      epochs=config.epochs,
-      shuffle=config.shuffle,
-      data_format=config.data_format,
-      dtype=config.dtype,
-      prefetch=config.prefetch)
 
-  ds_validation = cifar_input.get_ds_from_tfrecords(
+  if FLAGS.validate:
+    # 40k Training set
+    ds_train = cifar_input.get_ds_from_tfrecords(
+        data_dir=FLAGS.data_dir,
+        split="train",
+        data_aug=True,
+        batch_size=config.batch_size,
+        epochs=config.epochs,
+        shuffle=config.shuffle,
+        data_format=config.data_format,
+        dtype=config.dtype,
+        prefetch=config.batch_size)
+    # 10k Training set
+    ds_validation = cifar_input.get_ds_from_tfrecords(
+        data_dir=FLAGS.data_dir,
+        split="validation",
+        data_aug=False,
+        batch_size=config.eval_batch_size,
+        epochs=1,
+        shuffle=False,
+        data_format=config.data_format,
+        dtype=config.dtype,
+        prefetch=config.eval_batch_size)
+  else:
+    # 50k Training set
+    ds_train = cifar_input.get_ds_from_tfrecords(
+        data_dir=FLAGS.data_dir,
+        split="train_all",
+        data_aug=True,
+        batch_size=config.batch_size,
+        epochs=config.epochs,
+        shuffle=config.shuffle,
+        data_format=config.data_format,
+        dtype=config.dtype,
+        prefetch=config.batch_size)
+
+  # Always compute loss and accuracy on whole training and test set
+  ds_train_one_shot = cifar_input.get_ds_from_tfrecords(
       data_dir=FLAGS.data_dir,
-      split="validation",
+      split="train_all",
       data_aug=False,
       batch_size=config.eval_batch_size,
       epochs=1,
+      shuffle=False,
       data_format=config.data_format,
       dtype=config.dtype,
-      prefetch=config.prefetch)
+      prefetch=config.eval_batch_size)
 
   ds_test = cifar_input.get_ds_from_tfrecords(
       data_dir=FLAGS.data_dir,
@@ -67,69 +95,116 @@ def main(_):
       data_aug=False,
       batch_size=config.eval_batch_size,
       epochs=1,
+      shuffle=False,
       data_format=config.data_format,
       dtype=config.dtype,
-      prefetch=config.prefetch)
+      prefetch=config.eval_batch_size)
 
+  model = revnet.RevNet(config=config)
   global_step = tfe.Variable(1, trainable=False)
-
-  def learning_rate():  # TODO(lxuechen): Remove once cl/201089859 is in place
-    return tf.train.piecewise_constant(global_step, config.lr_decay_steps,
-                                       config.lr_list)
-
-  optimizer = tf.train.MomentumOptimizer(learning_rate, momentum=0.9)
-  checkpoint = tf.train.Checkpoint(
+  learning_rate = tf.train.piecewise_constant(
+      global_step, config.lr_decay_steps, config.lr_list)
+  optimizer = tf.train.MomentumOptimizer(
+      learning_rate, momentum=config.momentum)
+  checkpointer = tf.train.Checkpoint(
       optimizer=optimizer, model=model, optimizer_step=global_step)
 
   if FLAGS.train_dir:
     summary_writer = tf.contrib.summary.create_file_writer(FLAGS.train_dir)
     if FLAGS.restore:
       latest_path = tf.train.latest_checkpoint(FLAGS.train_dir)
-      checkpoint.restore(latest_path)
+      checkpointer.restore(latest_path)
+      print("Restored latest checkpoint at path:\"{}\" "
+            "with global_step: {}".format(latest_path, global_step.numpy()))
+      sys.stdout.flush()
+
+  warmup(model, config)
 
   for x, y in ds_train:
     loss = train_one_iter(model, x, y, optimizer, global_step=global_step)
 
-    if global_step % config.log_every == 0:
-      it_validation = ds_validation.make_one_shot_iterator()
+    if global_step.numpy() % config.log_every == 0:
+      it_train = ds_train_one_shot.make_one_shot_iterator()
+      acc_train, loss_train = evaluate(model, it_train)
       it_test = ds_test.make_one_shot_iterator()
-      acc_validation = evaluate(model, it_validation)
-      acc_test = evaluate(model, it_test)
-      print("Iter {}, "
-            "train loss {}, "
-            "validation accuracy {}, "
-            "test accuracy {}".format(global_step.numpy(), loss, acc_validation,
-                                      acc_test))
+      acc_test, loss_test = evaluate(model, it_test)
+      if FLAGS.validate:
+        it_validation = ds_validation.make_one_shot_iterator()
+        acc_validation, loss_validation = evaluate(model, it_validation)
+        print("Iter {}, "
+              "training set accuracy {:.4f}, loss {:.4f}; "
+              "validation set accuracy {:.4f}, loss {:4.f}"
+              "test accuracy {:.4f}, loss {:.4f}".format(
+                  global_step.numpy(), acc_train, loss_train, acc_validation,
+                  loss_validation, acc_test, loss_test))
+      else:
+        print("Iter {}, "
+              "training set accuracy {:.4f}, loss {:.4f}; "
+              "test accuracy {:.4f}, loss {:.4f}".format(
+                  global_step.numpy(), acc_train, loss_train, acc_test,
+                  loss_test))
+      sys.stdout.flush()
 
       if FLAGS.train_dir:
         with summary_writer.as_default():
           with tf.contrib.summary.always_record_summaries():
-            tf.contrib.summary.scalar("Validation accuracy", acc_validation)
-            tf.contrib.summary.scalar("Test accuracy", acc_test)
             tf.contrib.summary.scalar("Training loss", loss)
+            tf.contrib.summary.scalar("Test accuracy", acc_test)
+            if FLAGS.validate:
+              tf.contrib.summary.scalar("Validation accuracy", acc_validation)
 
     if global_step.numpy() % config.save_every == 0 and FLAGS.train_dir:
-      checkpoint.save(file_prefix=FLAGS.train_dir + "ckpt")
+      saved_path = checkpointer.save(
+          file_prefix=os.path.join(FLAGS.train_dir, "ckpt"))
+      print("Saved checkpoint at path: \"{}\" "
+            "with global_step: {}".format(saved_path, global_step.numpy()))
+      sys.stdout.flush()
+
 
+def warmup(model, config, steps=1):
+  mock_input = tf.random_normal((config.batch_size,) + config.input_shape)
+  for _ in range(steps):
+    model(mock_input, training=False)
 
-def train_one_iter(model, inputs, labels, optimizer, global_step=None):
+
+def train_one_iter(model,
+                   inputs,
+                   labels,
+                   optimizer,
+                   global_step=None,
+                   verbose=False):
   """Train for one iteration."""
-  grads, vars_, loss = model.compute_gradients(inputs, labels, training=True)
-  optimizer.apply_gradients(zip(grads, vars_), global_step=global_step)
+  if FLAGS.manual_grad:
+    if verbose:
+      print("Using manual gradients")
+    grads, vars_, loss = model.compute_gradients(inputs, labels)
+    optimizer.apply_gradients(zip(grads, vars_), global_step=global_step)
+  else:  # For correctness validation
+    if verbose:
+      print("Not using manual gradients")
+    with tf.GradientTape() as tape:
+      logits, _ = model(inputs, training=True)
+      loss = model.compute_loss(logits=logits, labels=labels)
+    grads = tape.gradient(loss, model.trainable_variables)
+    optimizer.apply_gradients(
+        zip(grads, model.trainable_variables), global_step=global_step)
 
   return loss.numpy()
 
 
 def evaluate(model, iterator):
   """Compute accuracy with the given dataset iterator."""
+  mean_loss = tfe.metrics.Mean()
   accuracy = tfe.metrics.Accuracy()
-  for x, y in iterator:
+  for x, y in tqdm(iterator):
     logits, _ = model(x, training=False)
+    loss = model.compute_loss(logits=logits, labels=y)
     accuracy(
         labels=tf.cast(y, tf.int64),
         predictions=tf.argmax(logits, axis=1, output_type=tf.int64))
+    mean_loss(loss)
 
-  return accuracy.result().numpy()
+  return accuracy.result().numpy(), mean_loss.result().numpy()
 
 
 if __name__ == "__main__":
@@ -138,10 +213,18 @@ if __name__ == "__main__":
       default=None,
       help="[Optional] Directory to store the training information")
   flags.DEFINE_string(
-      "data_dir", default=None, help="Directory to load tfrecords.")
+      "data_dir", default=None, help="Directory to load tfrecords")
   flags.DEFINE_boolean(
       "restore",
-      default=True,
+      default=False,
       help="[Optional] Restore the latest checkpoint from `train_dir` if True")
+  flags.DEFINE_boolean(
+      "validate",
+      default=False,
+      help="[Optional] Use the validation set or not for hyperparameter search")
+  flags.DEFINE_boolean(
+      "manual_grad",
+      default=False,
+      help="[Optional] Use manual gradient graph to save memory")
   FLAGS = flags.FLAGS
   tf.app.run(main)
diff --git a/tensorflow/contrib/eager/python/examples/revnet/revnet.py b/tensorflow/contrib/eager/python/examples/revnet/revnet.py
index b3b8c262b1..0228bff6fa 100644
--- a/tensorflow/contrib/eager/python/examples/revnet/revnet.py
+++ b/tensorflow/contrib/eager/python/examples/revnet/revnet.py
@@ -27,6 +27,7 @@ from __future__ import print_function
 import functools
 import operator
 
+import six
 import tensorflow as tf
 from tensorflow.contrib.eager.python.examples.revnet import blocks
 
@@ -47,6 +48,7 @@ class RevNet(tf.keras.Model):
     self._init_block = self._construct_init_block()
     self._block_list = self._construct_intermediate_blocks()
     self._final_block = self._construct_final_block()
+    self._moving_stats_vars = None
 
   def _construct_init_block(self):
     init_block = tf.keras.Sequential(
@@ -153,7 +155,6 @@ class RevNet(tf.keras.Model):
   def call(self, inputs, training=True):
     """Forward pass."""
 
-    # Only store hidden states during training
     if training:
       saved_hidden = [inputs]
 
@@ -181,17 +182,22 @@ class RevNet(tf.keras.Model):
   def compute_gradients(self, inputs, labels, training=True):
     """Manually computes gradients.
 
+    This method also SILENTLY updates the running averages of batch
+    normalization when `training` is set to True.
+
     Args:
       inputs: Image tensor, either NHWC or NCHW, conforming to `data_format`
       labels: One-hot labels for classification
-      training: for batch normalization
+      training: Use the mini-batch stats in batch norm if set to True
 
     Returns:
-      list of tuple each being (grad, var) for optimizer use
+      list of tuples each being (grad, var) for optimizer to use
     """
 
-    # Forward pass record hidden states before downsampling
+    # Run forward pass to record hidden states; avoid updating running averages
+    vars_and_vals = self.get_moving_stats()
     _, saved_hidden = self.call(inputs, training=training)
+    self.restore_moving_stats(vars_and_vals)
 
     grads_all = []
     vars_all = []
@@ -201,6 +207,7 @@ class RevNet(tf.keras.Model):
     with tf.GradientTape() as tape:
       x = tf.identity(x)  # TODO(lxuechen): Remove after b/110264016 is fixed
       tape.watch(x)
+      # Running stats updated below
       logits = self._final_block(x, training=training)
       loss = self.compute_loss(logits, labels)
 
@@ -226,16 +233,38 @@ class RevNet(tf.keras.Model):
 
     with tf.GradientTape() as tape:
       x = tf.identity(x)  # TODO(lxuechen): Remove after b/110264016 is fixed
+      # Running stats updated below
       y = self._init_block(x, training=training)
 
     grads_all += tape.gradient(
         y, self._init_block.trainable_variables, output_gradients=[dy])
     vars_all += self._init_block.trainable_variables
 
+    # Apply weight decay
     grads_all = self._apply_weight_decay(grads_all, vars_all)
 
     return grads_all, vars_all, loss
 
   def _apply_weight_decay(self, grads, vars_):
     """Update gradients to reflect weight decay."""
-    return [g + self.config.weight_decay * v for g, v in zip(grads, vars_)]
+    # Don't decay bias
+    return [
+        g + self.config.weight_decay * v if v.name.endswith("kernel:0") else g
+        for g, v in zip(grads, vars_)
+    ]
+
+  def get_moving_stats(self):
+    vars_and_vals = {}
+
+    def _is_moving_var(v):
+      n = v.name
+      return n.endswith("moving_mean:0") or n.endswith("moving_variance:0")
+
+    for v in filter(_is_moving_var, self.variables):
+      vars_and_vals[v] = v.read_value()
+
+    return vars_and_vals
+
+  def restore_moving_stats(self, vars_and_vals):
+    for var_, val in six.iteritems(vars_and_vals):
+      var_.assign(val)
diff --git a/tensorflow/contrib/eager/python/examples/revnet/revnet_test.py b/tensorflow/contrib/eager/python/examples/revnet/revnet_test.py
index cb3bac13f9..a5f240436a 100644
--- a/tensorflow/contrib/eager/python/examples/revnet/revnet_test.py
+++ b/tensorflow/contrib/eager/python/examples/revnet/revnet_test.py
@@ -36,10 +36,11 @@ def train_one_iter(model, inputs, labels, optimizer, global_step=None):
   return loss
 
 
-class RevnetTest(tf.test.TestCase):
+class RevNetTest(tf.test.TestCase):
 
   def setUp(self):
-    super(RevnetTest, self).setUp()
+    super(RevNetTest, self).setUp()
+    tf.set_random_seed(1)
     config = config_.get_hparams_imagenet_56()
     shape = (config.batch_size,) + config.input_shape
     self.model = revnet.RevNet(config=config)
@@ -56,7 +57,7 @@ class RevnetTest(tf.test.TestCase):
     del self.x
     del self.t
     del self.config
-    super(RevnetTest, self).tearDown()
+    super(RevNetTest, self).tearDown()
 
   def test_call(self):
     """Test `call` function."""
@@ -67,7 +68,8 @@ class RevnetTest(tf.test.TestCase):
   def test_compute_gradients(self):
     """Test `compute_gradients` function."""
 
-    grads, vars_, _ = self.model.compute_gradients(inputs=self.x, labels=self.t)
+    grads, vars_, _ = self.model.compute_gradients(
+        inputs=self.x, labels=self.t, training=True)
     self.assertTrue(isinstance(grads, list))
     self.assertTrue(isinstance(vars_, list))
     self.assertEqual(len(grads), len(vars_))
@@ -84,7 +86,7 @@ class RevnetTest(tf.test.TestCase):
   def test_compute_gradients_defun(self):
     """Test `compute_gradients` function with defun."""
     compute_gradients = tfe.defun(self.model.compute_gradients)
-    grads, vars_, _ = compute_gradients(self.x, self.t)
+    grads, vars_, _ = compute_gradients(self.x, self.t, training=True)
     self.assertTrue(isinstance(grads, list))
     self.assertTrue(isinstance(vars_, list))
     self.assertEqual(len(grads), len(vars_))
@@ -144,7 +146,7 @@ class MockIterator(object):
     return self._tensors
 
 
-class RevnetBenchmark(tf.test.Benchmark):
+class RevNetBenchmark(tf.test.Benchmark):
   """Eager and graph benchmarks for RevNet."""
 
   def _train_batch_sizes(self):
diff --git a/tensorflow/contrib/estimator/python/estimator/dnn.py b/tensorflow/contrib/estimator/python/estimator/dnn.py
index f1c60a912c..4bb90cf81b 100644
--- a/tensorflow/contrib/estimator/python/estimator/dnn.py
+++ b/tensorflow/contrib/estimator/python/estimator/dnn.py
@@ -53,6 +53,18 @@ class DNNEstimator(estimator.Estimator):
         l1_regularization_strength=0.001
       ))
 
+  # Or estimator using an optimizer with a learning rate decay.
+  estimator = DNNEstimator(
+      head=tf.contrib.estimator.multi_label_head(n_classes=3),
+      feature_columns=[sparse_feature_a_emb, sparse_feature_b_emb],
+      hidden_units=[1024, 512, 256],
+      optimizer=lambda: tf.AdamOptimizer(
+          learning_rate=tf.exponential_decay(
+              learning_rate=0.1,
+              global_step=tf.get_global_step(),
+              decay_steps=10000,
+              decay_rate=0.96))
+
   # Or estimator with warm-starting from a previous checkpoint.
   estimator = DNNEstimator(
       head=tf.contrib.estimator.multi_label_head(n_classes=3),
@@ -115,8 +127,9 @@ class DNNEstimator(estimator.Estimator):
       model_dir: Directory to save model parameters, graph and etc. This can
         also be used to load checkpoints from the directory into a estimator to
         continue training a previously saved model.
-      optimizer: An instance of `tf.Optimizer` used to train the model. Defaults
-        to Adagrad optimizer.
+      optimizer: An instance of `tf.Optimizer` used to train the model. Can also
+        be a string (one of 'Adagrad', 'Adam', 'Ftrl', 'RMSProp', 'SGD'), or
+        callable. Defaults to Adagrad optimizer.
       activation_fn: Activation function applied to each layer. If `None`, will
         use `tf.nn.relu`.
       dropout: When not `None`, the probability we will drop out a given
diff --git a/tensorflow/contrib/estimator/python/estimator/dnn_linear_combined.py b/tensorflow/contrib/estimator/python/estimator/dnn_linear_combined.py
index ccaf1128bf..894a295498 100644
--- a/tensorflow/contrib/estimator/python/estimator/dnn_linear_combined.py
+++ b/tensorflow/contrib/estimator/python/estimator/dnn_linear_combined.py
@@ -53,12 +53,19 @@ class DNNLinearCombinedEstimator(estimator.Estimator):
       dnn_hidden_units=[1000, 500, 100],
       dnn_optimizer=tf.train.ProximalAdagradOptimizer(...))
 
-  # To apply L1 and L2 regularization, you can set optimizers as follows:
+  # To apply L1 and L2 regularization, you can set dnn_optimizer to:
   tf.train.ProximalAdagradOptimizer(
       learning_rate=0.1,
       l1_regularization_strength=0.001,
       l2_regularization_strength=0.001)
-  # It is same for FtrlOptimizer.
+  # To apply learning rate decay, you can set dnn_optimizer to a callable:
+  lambda: tf.AdamOptimizer(
+      learning_rate=tf.exponential_decay(
+          learning_rate=0.1,
+          global_step=tf.get_global_step(),
+          decay_steps=10000,
+          decay_rate=0.96)
+  # It is the same for linear_optimizer.
 
   # Input builders
   def input_fn_train: # returns x, y
@@ -116,12 +123,16 @@ class DNNLinearCombinedEstimator(estimator.Estimator):
         used by linear part of the model. All items in the set must be
         instances of classes derived from `FeatureColumn`.
       linear_optimizer: An instance of `tf.Optimizer` used to apply gradients to
-        the linear part of the model. Defaults to FTRL optimizer.
+        the linear part of the model. Can also be a string (one of 'Adagrad',
+        'Adam', 'Ftrl', 'RMSProp', 'SGD'), or callable. Defaults to FTRL
+        optimizer.
       dnn_feature_columns: An iterable containing all the feature columns used
         by deep part of the model. All items in the set must be instances of
         classes derived from `FeatureColumn`.
       dnn_optimizer: An instance of `tf.Optimizer` used to apply gradients to
-        the deep part of the model. Defaults to Adagrad optimizer.
+        the deep part of the model. Can also be a string (one of 'Adagrad',
+        'Adam', 'Ftrl', 'RMSProp', 'SGD'), or callable. Defaults to Adagrad
+        optimizer.
       dnn_hidden_units: List of hidden units per layer. All layers are fully
         connected.
       dnn_activation_fn: Activation function applied to each layer. If None,
diff --git a/tensorflow/contrib/estimator/python/estimator/linear.py b/tensorflow/contrib/estimator/python/estimator/linear.py
index 3bf4abe83d..b960b16f1b 100644
--- a/tensorflow/contrib/estimator/python/estimator/linear.py
+++ b/tensorflow/contrib/estimator/python/estimator/linear.py
@@ -39,6 +39,18 @@ class LinearEstimator(estimator.Estimator):
       feature_columns=[categorical_column_a,
                        categorical_feature_a_x_categorical_feature_b])
 
+  # Or estimator using an optimizer with a learning rate decay.
+  estimator = LinearEstimator(
+      head=tf.contrib.estimator.multi_label_head(n_classes=3),
+      feature_columns=[categorical_column_a,
+                       categorical_feature_a_x_categorical_feature_b],
+      optimizer=lambda: tf.train.FtrlOptimizer(
+          learning_rate=tf.exponential_decay(
+              learning_rate=0.1,
+              global_step=tf.get_global_step(),
+              decay_steps=10000,
+              decay_rate=0.96))
+
   # Or estimator using the FTRL optimizer with regularization.
   estimator = LinearEstimator(
       head=tf.contrib.estimator.multi_label_head(n_classes=3),
@@ -99,8 +111,9 @@ class LinearEstimator(estimator.Estimator):
       model_dir: Directory to save model parameters, graph and etc. This can
         also be used to load checkpoints from the directory into a estimator
         to continue training a previously saved model.
-      optimizer: An instance of `tf.Optimizer` used to train the model. Defaults
-        to FTRL optimizer.
+      optimizer: An instance of `tf.Optimizer` used to train the model. Can also
+        be a string (one of 'Adagrad', 'Adam', 'Ftrl', 'RMSProp', 'SGD'), or
+        callable. Defaults to FTRL optimizer.
       config: `RunConfig` object to configure the runtime settings.
       partitioner: Optional. Partitioner for input layer.
     """
diff --git a/tensorflow/contrib/lite/java/demo/app/build.gradle b/tensorflow/contrib/lite/java/demo/app/build.gradle
index 44ea2dcd90..192162cfce 100644
--- a/tensorflow/contrib/lite/java/demo/app/build.gradle
+++ b/tensorflow/contrib/lite/java/demo/app/build.gradle
@@ -5,7 +5,8 @@ android {
     buildToolsVersion "26.0.1"
     defaultConfig {
         applicationId "android.example.com.tflitecamerademo"
-        minSdkVersion 15
+        // Required by Camera2 API.
+        minSdkVersion 21
         targetSdkVersion 26
         versionCode 1
         versionName "1.0"
diff --git a/tensorflow/contrib/lite/python/lite.py b/tensorflow/contrib/lite/python/lite.py
index 69a2f638af..a4229f91f5 100644
--- a/tensorflow/contrib/lite/python/lite.py
+++ b/tensorflow/contrib/lite/python/lite.py
@@ -50,6 +50,7 @@ from tensorflow.contrib.lite.python.interpreter import Interpreter  # pylint: di
 from tensorflow.contrib.lite.python.op_hint import convert_op_hints_to_stubs  # pylint: disable=unused-import
 from tensorflow.contrib.lite.python.op_hint import OpHint  # pylint: disable=unused-import
 from tensorflow.core.framework import graph_pb2 as _graph_pb2
+from tensorflow.python import keras as _keras
 from tensorflow.python.client import session as _session
 from tensorflow.python.framework import graph_util as tf_graph_util
 from tensorflow.python.framework.importer import import_graph_def
@@ -269,6 +270,48 @@ class TocoConverter(object):
     return cls(
         graph_def=result[0], input_tensors=result[1], output_tensors=result[2])
 
+  @classmethod
+  def from_keras_model_file(cls,
+                            model_file,
+                            input_arrays=None,
+                            input_shapes=None,
+                            output_arrays=None):
+    """Creates a TocoConverter class from a tf.keras model file.
+
+    Args:
+      model_file: Full filepath of HDF5 file containing the tf.keras model.
+      input_arrays: List of input tensors to freeze graph with. Uses input
+        arrays from SignatureDef when none are provided. (default None)
+      input_shapes: Dict of strings representing input tensor names to list of
+        integers representing input shapes (e.g., {"foo" : [1, 16, 16, 3]}).
+        Automatically determined when input shapes is None (e.g., {"foo" :
+        None}). (default None)
+      output_arrays: List of output tensors to freeze graph with. Uses output
+        arrays from SignatureDef when none are provided. (default None)
+
+    Returns:
+      TocoConverter class.
+    """
+    _keras.backend.clear_session()
+    _keras.backend.set_learning_phase(False)
+    keras_model = _keras.models.load_model(model_file)
+    sess = _keras.backend.get_session()
+
+    # Get input and output tensors.
+    if input_arrays:
+      input_tensors = get_tensors_from_tensor_names(sess.graph, input_arrays)
+    else:
+      input_tensors = keras_model.inputs
+
+    if output_arrays:
+      output_tensors = get_tensors_from_tensor_names(sess.graph, output_arrays)
+    else:
+      output_tensors = keras_model.outputs
+    set_tensor_shapes(input_tensors, input_shapes)
+
+    graph_def = _freeze_graph(sess, output_tensors)
+    return cls(graph_def, input_tensors, output_tensors)
+
   def convert(self):
     """Converts a TensorFlow GraphDef based on instance variables.
 
@@ -366,7 +409,7 @@ def _is_frozen_graph(sess):
     Bool.
   """
   for op in sess.graph.get_operations():
-    if op.type.startswith("Variable"):
+    if op.type.startswith("Variable") or op.type.endswith("VariableOp"):
       return False
   return True
 
diff --git a/tensorflow/contrib/lite/python/lite_test.py b/tensorflow/contrib/lite/python/lite_test.py
index a9475de474..ca2af5aaed 100644
--- a/tensorflow/contrib/lite/python/lite_test.py
+++ b/tensorflow/contrib/lite/python/lite_test.py
@@ -19,11 +19,13 @@ from __future__ import division
 from __future__ import print_function
 
 import os
+import tempfile
 import numpy as np
 
 from tensorflow.contrib.lite.python import lite
 from tensorflow.contrib.lite.python import lite_constants
 from tensorflow.contrib.lite.python.interpreter import Interpreter
+from tensorflow.python import keras
 from tensorflow.python.client import session
 from tensorflow.python.framework import constant_op
 from tensorflow.python.framework import dtypes
@@ -618,5 +620,279 @@ class FromSavedModelTest(test_util.TensorFlowTestCase):
     self.assertTrue(tflite_model)
 
 
+class FromKerasFile(test_util.TensorFlowTestCase):
+
+  def setUp(self):
+    keras.backend.clear_session()
+
+  def _getSequentialModel(self):
+    model = keras.models.Sequential()
+    model.add(keras.layers.Dense(2, input_shape=(3,)))
+    model.add(keras.layers.RepeatVector(3))
+    model.add(keras.layers.TimeDistributed(keras.layers.Dense(3)))
+    model.compile(
+        loss=keras.losses.MSE,
+        optimizer=keras.optimizers.RMSprop(),
+        metrics=[keras.metrics.categorical_accuracy],
+        sample_weight_mode='temporal')
+    x = np.random.random((1, 3))
+    y = np.random.random((1, 3, 3))
+    model.train_on_batch(x, y)
+    model.predict(x)
+
+    try:
+      fd, keras_file = tempfile.mkstemp('.h5')
+      keras.models.save_model(model, keras_file)
+    finally:
+      os.close(fd)
+    return keras_file
+
+  def testSequentialModel(self):
+    """Test a Sequential tf.keras model with default inputs."""
+    keras_file = self._getSequentialModel()
+
+    converter = lite.TocoConverter.from_keras_model_file(keras_file)
+    tflite_model = converter.convert()
+    self.assertTrue(tflite_model)
+
+    os.remove(keras_file)
+
+    # Check values from converted model.
+    interpreter = Interpreter(model_content=tflite_model)
+    interpreter.allocate_tensors()
+
+    input_details = interpreter.get_input_details()
+    self.assertEqual(1, len(input_details))
+    self.assertEqual('dense_input', input_details[0]['name'])
+    self.assertEqual(np.float32, input_details[0]['dtype'])
+    self.assertTrue(([1, 3] == input_details[0]['shape']).all())
+    self.assertEqual((0., 0.), input_details[0]['quantization'])
+
+    output_details = interpreter.get_output_details()
+    self.assertEqual(1, len(output_details))
+    self.assertEqual('time_distributed/Reshape_1', output_details[0]['name'])
+    self.assertEqual(np.float32, output_details[0]['dtype'])
+    self.assertTrue(([1, 3, 3] == output_details[0]['shape']).all())
+    self.assertEqual((0., 0.), output_details[0]['quantization'])
+
+  def testSequentialModelInputArray(self):
+    """Test a Sequential tf.keras model testing input arrays argument."""
+    keras_file = self._getSequentialModel()
+
+    # Invalid input array raises error.
+    with self.assertRaises(ValueError) as error:
+      lite.TocoConverter.from_keras_model_file(
+          keras_file, input_arrays=['invalid-input'])
+    self.assertEqual("Invalid tensors 'invalid-input' were found.",
+                     str(error.exception))
+
+    # Valid input array.
+    converter = lite.TocoConverter.from_keras_model_file(
+        keras_file, input_arrays=['dense_input'])
+    tflite_model = converter.convert()
+    os.remove(keras_file)
+    self.assertTrue(tflite_model)
+
+  def testSequentialModelInputShape(self):
+    """Test a Sequential tf.keras model testing input shapes argument."""
+    keras_file = self._getSequentialModel()
+
+    # Passing in shape of invalid input array has no impact as long as all input
+    # arrays have a shape.
+    converter = lite.TocoConverter.from_keras_model_file(
+        keras_file, input_shapes={'invalid-input': [2, 3]})
+    tflite_model = converter.convert()
+    self.assertTrue(tflite_model)
+
+    # Passing in shape of valid input array.
+    converter = lite.TocoConverter.from_keras_model_file(
+        keras_file, input_shapes={'dense_input': [2, 3]})
+    tflite_model = converter.convert()
+    os.remove(keras_file)
+    self.assertTrue(tflite_model)
+
+    # Check input shape from converted model.
+    interpreter = Interpreter(model_content=tflite_model)
+    interpreter.allocate_tensors()
+
+    input_details = interpreter.get_input_details()
+    self.assertEqual(1, len(input_details))
+    self.assertEqual('dense_input', input_details[0]['name'])
+    self.assertTrue(([2, 3] == input_details[0]['shape']).all())
+
+  def testSequentialModelOutputArray(self):
+    """Test a Sequential tf.keras model testing output arrays argument."""
+    keras_file = self._getSequentialModel()
+
+    # Invalid output array raises error.
+    with self.assertRaises(ValueError) as error:
+      lite.TocoConverter.from_keras_model_file(
+          keras_file, output_arrays=['invalid-output'])
+    self.assertEqual("Invalid tensors 'invalid-output' were found.",
+                     str(error.exception))
+
+    # Valid output array.
+    converter = lite.TocoConverter.from_keras_model_file(
+        keras_file, output_arrays=['time_distributed/Reshape_1'])
+    tflite_model = converter.convert()
+    os.remove(keras_file)
+    self.assertTrue(tflite_model)
+
+  def testFunctionalModel(self):
+    """Test a Functional tf.keras model with default inputs."""
+    inputs = keras.layers.Input(shape=(3,), name='input')
+    x = keras.layers.Dense(2)(inputs)
+    output = keras.layers.Dense(3)(x)
+
+    model = keras.models.Model(inputs, output)
+    model.compile(
+        loss=keras.losses.MSE,
+        optimizer=keras.optimizers.RMSprop(),
+        metrics=[keras.metrics.categorical_accuracy])
+    x = np.random.random((1, 3))
+    y = np.random.random((1, 3))
+    model.train_on_batch(x, y)
+
+    model.predict(x)
+    fd, keras_file = tempfile.mkstemp('.h5')
+    keras.models.save_model(model, keras_file)
+
+    # Convert to TFLite model.
+    converter = lite.TocoConverter.from_keras_model_file(keras_file)
+    tflite_model = converter.convert()
+    self.assertTrue(tflite_model)
+
+    os.close(fd)
+    os.remove(keras_file)
+
+    # Check values from converted model.
+    interpreter = Interpreter(model_content=tflite_model)
+    interpreter.allocate_tensors()
+
+    input_details = interpreter.get_input_details()
+    self.assertEqual(1, len(input_details))
+    self.assertEqual('input', input_details[0]['name'])
+    self.assertEqual(np.float32, input_details[0]['dtype'])
+    self.assertTrue(([1, 3] == input_details[0]['shape']).all())
+    self.assertEqual((0., 0.), input_details[0]['quantization'])
+
+    output_details = interpreter.get_output_details()
+    self.assertEqual(1, len(output_details))
+    self.assertEqual('dense_1/BiasAdd', output_details[0]['name'])
+    self.assertEqual(np.float32, output_details[0]['dtype'])
+    self.assertTrue(([1, 3] == output_details[0]['shape']).all())
+    self.assertEqual((0., 0.), output_details[0]['quantization'])
+
+  def testFunctionalModelMultipleInputs(self):
+    """Test a Functional tf.keras model with multiple inputs and outputs."""
+    a = keras.layers.Input(shape=(3,), name='input_a')
+    b = keras.layers.Input(shape=(3,), name='input_b')
+    dense = keras.layers.Dense(4, name='dense')
+    c = dense(a)
+    d = dense(b)
+    e = keras.layers.Dropout(0.5, name='dropout')(c)
+
+    model = keras.models.Model([a, b], [d, e])
+    model.compile(
+        loss=keras.losses.MSE,
+        optimizer=keras.optimizers.RMSprop(),
+        metrics=[keras.metrics.mae],
+        loss_weights=[1., 0.5])
+
+    input_a_np = np.random.random((10, 3))
+    input_b_np = np.random.random((10, 3))
+    output_d_np = np.random.random((10, 4))
+    output_e_np = np.random.random((10, 4))
+    model.train_on_batch([input_a_np, input_b_np], [output_d_np, output_e_np])
+
+    model.predict([input_a_np, input_b_np], batch_size=5)
+    fd, keras_file = tempfile.mkstemp('.h5')
+    keras.models.save_model(model, keras_file)
+
+    # Convert to TFLite model.
+    converter = lite.TocoConverter.from_keras_model_file(keras_file)
+    tflite_model = converter.convert()
+    self.assertTrue(tflite_model)
+
+    os.close(fd)
+    os.remove(keras_file)
+
+    # Check values from converted model.
+    interpreter = Interpreter(model_content=tflite_model)
+    interpreter.allocate_tensors()
+
+    input_details = interpreter.get_input_details()
+    self.assertEqual(2, len(input_details))
+    self.assertEqual('input_a', input_details[0]['name'])
+    self.assertEqual(np.float32, input_details[0]['dtype'])
+    self.assertTrue(([1, 3] == input_details[0]['shape']).all())
+    self.assertEqual((0., 0.), input_details[0]['quantization'])
+
+    self.assertEqual('input_b', input_details[1]['name'])
+    self.assertEqual(np.float32, input_details[1]['dtype'])
+    self.assertTrue(([1, 3] == input_details[1]['shape']).all())
+    self.assertEqual((0., 0.), input_details[1]['quantization'])
+
+    output_details = interpreter.get_output_details()
+    self.assertEqual(2, len(output_details))
+    self.assertEqual('dense_1/BiasAdd', output_details[0]['name'])
+    self.assertEqual(np.float32, output_details[0]['dtype'])
+    self.assertTrue(([1, 4] == output_details[0]['shape']).all())
+    self.assertEqual((0., 0.), output_details[0]['quantization'])
+
+    self.assertEqual('dropout/Identity', output_details[1]['name'])
+    self.assertEqual(np.float32, output_details[1]['dtype'])
+    self.assertTrue(([1, 4] == output_details[1]['shape']).all())
+    self.assertEqual((0., 0.), output_details[1]['quantization'])
+
+  def testFunctionalSequentialModel(self):
+    """Test a Functional tf.keras model containing a Sequential model."""
+    model = keras.models.Sequential()
+    model.add(keras.layers.Dense(2, input_shape=(3,)))
+    model.add(keras.layers.RepeatVector(3))
+    model.add(keras.layers.TimeDistributed(keras.layers.Dense(3)))
+    model = keras.models.Model(model.input, model.output)
+
+    model.compile(
+        loss=keras.losses.MSE,
+        optimizer=keras.optimizers.RMSprop(),
+        metrics=[keras.metrics.categorical_accuracy],
+        sample_weight_mode='temporal')
+    x = np.random.random((1, 3))
+    y = np.random.random((1, 3, 3))
+    model.train_on_batch(x, y)
+    model.predict(x)
+
+    model.predict(x)
+    fd, keras_file = tempfile.mkstemp('.h5')
+    keras.models.save_model(model, keras_file)
+
+    # Convert to TFLite model.
+    converter = lite.TocoConverter.from_keras_model_file(keras_file)
+    tflite_model = converter.convert()
+    self.assertTrue(tflite_model)
+
+    os.close(fd)
+    os.remove(keras_file)
+
+    # Check values from converted model.
+    interpreter = Interpreter(model_content=tflite_model)
+    interpreter.allocate_tensors()
+
+    input_details = interpreter.get_input_details()
+    self.assertEqual(1, len(input_details))
+    self.assertEqual('dense_input', input_details[0]['name'])
+    self.assertEqual(np.float32, input_details[0]['dtype'])
+    self.assertTrue(([1, 3] == input_details[0]['shape']).all())
+    self.assertEqual((0., 0.), input_details[0]['quantization'])
+
+    output_details = interpreter.get_output_details()
+    self.assertEqual(1, len(output_details))
+    self.assertEqual('time_distributed/Reshape_1', output_details[0]['name'])
+    self.assertEqual(np.float32, output_details[0]['dtype'])
+    self.assertTrue(([1, 3, 3] == output_details[0]['shape']).all())
+    self.assertEqual((0., 0.), output_details[0]['quantization'])
+
+
 if __name__ == '__main__':
   test.main()
diff --git a/tensorflow/contrib/lite/python/tflite_convert.py b/tensorflow/contrib/lite/python/tflite_convert.py
index d18a29834b..249b940f92 100644
--- a/tensorflow/contrib/lite/python/tflite_convert.py
+++ b/tensorflow/contrib/lite/python/tflite_convert.py
@@ -74,6 +74,9 @@ def _get_toco_converter(flags):
     converter_kwargs["saved_model_dir"] = flags.saved_model_dir
     converter_kwargs["tag_set"] = _parse_set(flags.saved_model_tag_set)
     converter_kwargs["signature_key"] = flags.saved_model_signature_key
+  elif flags.keras_model_file:
+    converter_fn = lite.TocoConverter.from_keras_model_file
+    converter_kwargs["model_file"] = flags.keras_model_file
 
   return converter_fn(**converter_kwargs)
 
@@ -227,6 +230,10 @@ def run_main(_):
       "--saved_model_dir",
       type=str,
       help="Full filepath of directory containing the SavedModel.")
+  input_file_group.add_argument(
+      "--keras_model_file",
+      type=str,
+      help="Full filepath of HDF5 file containing tf.Keras model.")
 
   # Model format flags.
   parser.add_argument(
diff --git a/tensorflow/contrib/lite/toco/g3doc/python_api.md b/tensorflow/contrib/lite/toco/g3doc/python_api.md
index afa6fd6957..b04d166f89 100644
--- a/tensorflow/contrib/lite/toco/g3doc/python_api.md
+++ b/tensorflow/contrib/lite/toco/g3doc/python_api.md
@@ -15,6 +15,7 @@ Table of contents:
     *   [Exporting a GraphDef from tf.Session](#basic-graphdef-sess)
     *   [Exporting a GraphDef from file](#basic-graphdef-file)
     *   [Exporting a SavedModel](#basic-savedmodel)
+    *   [Exporting a tf.keras File](#basic-keras-file)
 *   [Complex examples](#complex)
     *   [Exporting a quantized GraphDef](#complex-quant)
 *   [TensorFlow Lite Python interpreter](#interpreter)
@@ -114,6 +115,51 @@ For more complex SavedModels, the optional parameters that can be passed into
 `output_arrays`, `tag_set` and `signature_key`. Details of each parameter are
 available by running `help(tf.contrib.lite.TocoConverter)`.
 
+### Exporting a tf.keras File <a name="basic-keras-file"></a>
+
+The following example shows how to convert a tf.keras model into a TensorFlow
+Lite FlatBuffer.
+
+```python
+import tensorflow as tf
+
+converter = tf.contrib.lite.TocoConverter.from_keras_model_file("keras_model.h5")
+tflite_model = converter.convert()
+open("converted_model.tflite", "wb").write(tflite_model)
+```
+
+The tf.keras file must contain both the model and the weights. A comprehensive
+example including model construction can be seen below.
+
+```python
+import numpy as np
+import tensorflow as tf
+
+# Generate tf.keras model.
+model = tf.keras.models.Sequential()
+model.add(tf.keras.layers.Dense(2, input_shape=(3,)))
+model.add(tf.keras.layers.RepeatVector(3))
+model.add(tf.keras.layers.TimeDistributed(tf.keras.layers.Dense(3)))
+model.compile(loss=tf.keras.losses.MSE,
+              optimizer=tf.keras.optimizers.RMSprop(lr=0.0001),
+              metrics=[tf.keras.metrics.categorical_accuracy],
+              sample_weight_mode='temporal')
+
+x = np.random.random((1, 3))
+y = np.random.random((1, 3, 3))
+model.train_on_batch(x, y)
+model.predict(x)
+
+# Save tf.keras model in HDF5 format.
+keras_file = "keras_model.h5"
+tf.keras.models.save_model(model, keras_file)
+
+# Convert to TensorFlow Lite model.
+converter = tf.contrib.lite.TocoConverter.from_keras_model_file(keras_file)
+tflite_model = converter.convert()
+open("converted_model.tflite", "wb").write(tflite_model)
+```
+
 ## Complex examples <a name="complex"></a>
 
 For models where the default value of the attributes is not sufficient, the
diff --git a/tensorflow/contrib/lite/toco/import_tensorflow.cc b/tensorflow/contrib/lite/toco/import_tensorflow.cc
index da7e5add7e..485e853e25 100644
--- a/tensorflow/contrib/lite/toco/import_tensorflow.cc
+++ b/tensorflow/contrib/lite/toco/import_tensorflow.cc
@@ -378,7 +378,7 @@ tensorflow::Status ImportBoolArray(const TensorProto& input_tensor,
     for (int i = 0; i < input_flat_size; i++) {
       output_bool_data[i] = input_tensor.bool_val(0);
     }
-  } else if (input_tensor.int_val_size() == input_flat_size) {
+  } else if (input_tensor.bool_val_size() == input_flat_size) {
     for (int i = 0; i < input_tensor.bool_val_size(); i++) {
       output_bool_data[i] = input_tensor.bool_val(i);
     }
diff --git a/tensorflow/contrib/summary/summary_ops_test.py b/tensorflow/contrib/summary/summary_ops_test.py
index f1ef218e74..3e41e3d0b4 100644
--- a/tensorflow/contrib/summary/summary_ops_test.py
+++ b/tensorflow/contrib/summary/summary_ops_test.py
@@ -81,6 +81,19 @@ class EagerFileTest(test_util.TensorFlowTestCase):
       # test here that we're calling them correctly.
       self.assertTrue(gfile.Exists(logdir))
 
+  @test_util.assert_no_new_pyobjects_executing_eagerly
+  def testEagerMemory(self):
+    training_util.get_or_create_global_step()
+    logdir = self.get_temp_dir()
+    with summary_ops.create_file_writer(
+        logdir, max_queue=0,
+        name='t0').as_default(), summary_ops.always_record_summaries():
+      summary_ops.generic('tensor', 1, '')
+      summary_ops.scalar('scalar', 2.0)
+      summary_ops.histogram('histogram', [1.0])
+      summary_ops.image('image', [[[[1.0]]]])
+      summary_ops.audio('audio', [[1.0]], 1.0, 1)
+
   def testDefunSummarys(self):
     training_util.get_or_create_global_step()
     logdir = tempfile.mkdtemp()