From 7fd688d21dae2814ffcadc09f7ef6a94be4a427b Mon Sep 17 00:00:00 2001 From: Aurelien Geron Date: Sun, 30 Apr 2017 10:21:27 +0200 Subject: [PATCH] Use tf.layers instead of tf.contrib.layers --- ...uction_to_artificial_neural_networks.ipynb | 1756 +++++++++-------- 11_deep_learning.ipynb | 524 ++--- 12_distributed_tensorflow.ipynb | 2 +- 13_convolutional_neural_networks.ipynb | 284 ++- 14_recurrent_neural_networks.ipynb | 1137 +++++------ 15_autoencoders.ipynb | 639 +++--- 16_reinforcement_learning.ipynb | 174 +- 7 files changed, 2317 insertions(+), 2199 deletions(-) diff --git a/10_introduction_to_artificial_neural_networks.ipynb b/10_introduction_to_artificial_neural_networks.ipynb index 0c87363..8617807 100644 --- a/10_introduction_to_artificial_neural_networks.ipynb +++ b/10_introduction_to_artificial_neural_networks.ipynb @@ -157,7 +157,7 @@ "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsgAAAEYCAYAAABBfQDEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -246,7 +246,7 @@ "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAxAAAAEYCAYAAADMNRC5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nUoAQQgghhBBCVNn/A/DkBetHy0ZRAAAAAElFTkSuQmCC\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -317,7 +317,7 @@ "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmYAAAEOCAYAAAAjY9sgAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrkJggg==\n", "text/plain": [ - "" + "" ] }, "metadata": {}, @@ -411,20 +411,20 @@ "name": "stdout", "output_type": "stream", "text": [ - "WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmphilui6nx\n", + "WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmp7zss569e\n", "INFO:tensorflow:Using default config.\n", - "INFO:tensorflow:Using config: {'_master': '', '_save_checkpoints_secs': 600, '_environment': 'local', '_is_chief': True, '_evaluation_master': '', '_save_summary_steps': 100, '_tf_config': gpu_options {\n", + "INFO:tensorflow:Using config: {'_evaluation_master': '', '_num_ps_replicas': 0, '_environment': 'local', '_master': '', '_save_checkpoints_secs': 600, '_is_chief': True, '_tf_config': gpu_options {\n", " per_process_gpu_memory_fraction: 1.0\n", "}\n", - ", '_task_id': 0, '_task_type': None, '_keep_checkpoint_every_n_hours': 10000, '_num_ps_replicas': 0, '_save_checkpoints_steps': None, '_tf_random_seed': None, '_keep_checkpoint_max': 5, '_cluster_spec': }\n", - "WARNING:tensorflow:From :6: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.\n", + ", '_keep_checkpoint_every_n_hours': 10000, '_cluster_spec': , '_save_checkpoints_steps': None, '_task_id': 0, '_keep_checkpoint_max': 5, '_task_type': None, '_tf_random_seed': None, '_save_summary_steps': 100}\n", + "WARNING:tensorflow:From :6: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.\n", "Instructions for updating:\n", "Estimator is decoupled from Scikit Learn interface by moving into\n", "separate class SKCompat. Arguments x, y and batch_size are only\n", "available in the SKCompat class, Estimator will only accept input_fn.\n", "Example conversion:\n", " est = Estimator(...) -> est = SKCompat(Estimator(...))\n", - "WARNING:tensorflow:From :6: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.\n", + "WARNING:tensorflow:From :6: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.\n", "Instructions for updating:\n", "Estimator is decoupled from Scikit Learn interface by moving into\n", "separate class SKCompat. Arguments x, y and batch_size are only\n", @@ -438,7 +438,7 @@ "available in the SKCompat class, Estimator will only accept input_fn.\n", "Example conversion:\n", " est = Estimator(...) -> est = SKCompat(Estimator(...))\n", - "WARNING:tensorflow:From /home/ageron/dev/py/envs/mltst/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:1362: scalar_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30.\n", + "WARNING:tensorflow:From /home/ageron/dev/py/envs/ml/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:1362: scalar_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30.\n", "Instructions for updating:\n", "Please switch to tf.summary.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.\n", "INFO:tensorflow:Create CheckpointSaverHook.\n" @@ -448,7 +448,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "/home/ageron/dev/py/envs/mltst/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.\n", + "/home/ageron/dev/py/envs/ml/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.\n", " equality = a == b\n" ] }, @@ -456,814 +456,814 @@ "name": "stdout", "output_type": "stream", "text": [ - "INFO:tensorflow:Saving checkpoints for 1 into /tmp/tmphilui6nx/model.ckpt.\n", - "INFO:tensorflow:step = 1, loss = 2.33583\n", - "INFO:tensorflow:global_step/sec: 258.583\n", - "INFO:tensorflow:step = 101, loss = 0.294522\n", - "INFO:tensorflow:global_step/sec: 262.729\n", - "INFO:tensorflow:step = 201, loss = 0.266201\n", - "INFO:tensorflow:global_step/sec: 265.044\n", - "INFO:tensorflow:step = 301, loss = 0.336991\n", - "INFO:tensorflow:global_step/sec: 264.135\n", - "INFO:tensorflow:step = 401, loss = 0.199312\n", - "INFO:tensorflow:global_step/sec: 262.027\n", - "INFO:tensorflow:step = 501, loss = 0.26225\n", - "INFO:tensorflow:global_step/sec: 264.196\n", - "INFO:tensorflow:step = 601, loss = 0.061271\n", - "INFO:tensorflow:global_step/sec: 264.339\n", - "INFO:tensorflow:step = 701, loss = 0.117645\n", - "INFO:tensorflow:global_step/sec: 264.631\n", - "INFO:tensorflow:step = 801, loss = 0.188891\n", - "INFO:tensorflow:global_step/sec: 263.036\n", - "INFO:tensorflow:step = 901, loss = 0.125975\n", - "INFO:tensorflow:global_step/sec: 262.293\n", - "INFO:tensorflow:step = 1001, loss = 0.191452\n", - "INFO:tensorflow:global_step/sec: 265.231\n", - "INFO:tensorflow:step = 1101, loss = 0.165268\n", - "INFO:tensorflow:global_step/sec: 263.441\n", - "INFO:tensorflow:step = 1201, loss = 0.15249\n", - "INFO:tensorflow:global_step/sec: 264.949\n", - "INFO:tensorflow:step = 1301, loss = 0.15392\n", - "INFO:tensorflow:global_step/sec: 261.824\n", - "INFO:tensorflow:step = 1401, loss = 0.060045\n", - "INFO:tensorflow:global_step/sec: 258.09\n", - "INFO:tensorflow:step = 1501, loss = 0.0843455\n", - "INFO:tensorflow:global_step/sec: 265.78\n", - "INFO:tensorflow:step = 1601, loss = 0.0917156\n", - "INFO:tensorflow:global_step/sec: 263.362\n", - "INFO:tensorflow:step = 1701, loss = 0.0443376\n", - "INFO:tensorflow:global_step/sec: 256.37\n", - "INFO:tensorflow:step = 1801, loss = 0.166449\n", - "INFO:tensorflow:global_step/sec: 264.067\n", - "INFO:tensorflow:step = 1901, loss = 0.0924655\n", - "INFO:tensorflow:global_step/sec: 261.329\n", - "INFO:tensorflow:step = 2001, loss = 0.0630006\n", - "INFO:tensorflow:global_step/sec: 262.04\n", - "INFO:tensorflow:step = 2101, loss = 0.0157954\n", - "INFO:tensorflow:global_step/sec: 262.729\n", - "INFO:tensorflow:step = 2201, loss = 0.0351585\n", - "INFO:tensorflow:global_step/sec: 260.452\n", - "INFO:tensorflow:step = 2301, loss = 0.0407206\n", - "INFO:tensorflow:global_step/sec: 261.333\n", - "INFO:tensorflow:step = 2401, loss = 0.0516131\n", - "INFO:tensorflow:global_step/sec: 262.191\n", - "INFO:tensorflow:step = 2501, loss = 0.0995485\n", - "INFO:tensorflow:global_step/sec: 265.165\n", - "INFO:tensorflow:step = 2601, loss = 0.0402033\n", - "INFO:tensorflow:global_step/sec: 265.729\n", - "INFO:tensorflow:step = 2701, loss = 0.00852274\n", - "INFO:tensorflow:global_step/sec: 263.466\n", - "INFO:tensorflow:step = 2801, loss = 0.06966\n", - "INFO:tensorflow:global_step/sec: 262.087\n", - "INFO:tensorflow:step = 2901, loss = 0.11404\n", - "INFO:tensorflow:global_step/sec: 253.174\n", - "INFO:tensorflow:step = 3001, loss = 0.0276311\n", - "INFO:tensorflow:global_step/sec: 268.014\n", - "INFO:tensorflow:step = 3101, loss = 0.054816\n", - "INFO:tensorflow:global_step/sec: 268.547\n", - "INFO:tensorflow:step = 3201, loss = 0.0102452\n", - "INFO:tensorflow:global_step/sec: 267.084\n", - "INFO:tensorflow:step = 3301, loss = 0.0257433\n", - "INFO:tensorflow:global_step/sec: 264.915\n", - "INFO:tensorflow:step = 3401, loss = 0.189313\n", - "INFO:tensorflow:global_step/sec: 266.16\n", - "INFO:tensorflow:step = 3501, loss = 0.0645021\n", - "INFO:tensorflow:global_step/sec: 265.347\n", - "INFO:tensorflow:step = 3601, loss = 0.167561\n", - "INFO:tensorflow:global_step/sec: 267.618\n", - "INFO:tensorflow:step = 3701, loss = 0.0273186\n", - "INFO:tensorflow:global_step/sec: 266.919\n", - "INFO:tensorflow:step = 3801, loss = 0.0110131\n", - "INFO:tensorflow:global_step/sec: 263.598\n", - "INFO:tensorflow:step = 3901, loss = 0.0723817\n", - "INFO:tensorflow:global_step/sec: 269.606\n", - "INFO:tensorflow:step = 4001, loss = 0.116048\n", - "INFO:tensorflow:global_step/sec: 268.314\n", - "INFO:tensorflow:step = 4101, loss = 0.0298984\n", - "INFO:tensorflow:global_step/sec: 265.744\n", - "INFO:tensorflow:step = 4201, loss = 0.0515774\n", - "INFO:tensorflow:global_step/sec: 264.673\n", - "INFO:tensorflow:step = 4301, loss = 0.157317\n", - "INFO:tensorflow:global_step/sec: 264.228\n", - "INFO:tensorflow:step = 4401, loss = 0.0839866\n", - "INFO:tensorflow:global_step/sec: 270.694\n", - "INFO:tensorflow:step = 4501, loss = 0.0153724\n", - "INFO:tensorflow:global_step/sec: 266.478\n", - "INFO:tensorflow:step = 4601, loss = 0.0214291\n", - "INFO:tensorflow:global_step/sec: 265.286\n", - "INFO:tensorflow:step = 4701, loss = 0.00992293\n", - "INFO:tensorflow:global_step/sec: 264.861\n", - "INFO:tensorflow:step = 4801, loss = 0.0130271\n", - "INFO:tensorflow:global_step/sec: 266.583\n", - "INFO:tensorflow:step = 4901, loss = 0.0750115\n", - "INFO:tensorflow:global_step/sec: 265.146\n", - "INFO:tensorflow:step = 5001, loss = 0.0654392\n", - "INFO:tensorflow:global_step/sec: 265.554\n", - "INFO:tensorflow:step = 5101, loss = 0.0122972\n", - "INFO:tensorflow:global_step/sec: 267.958\n", - "INFO:tensorflow:step = 5201, loss = 0.0230854\n", - "INFO:tensorflow:global_step/sec: 269.081\n", - "INFO:tensorflow:step = 5301, loss = 0.0413182\n", - "INFO:tensorflow:global_step/sec: 265.704\n", - "INFO:tensorflow:step = 5401, loss = 0.0367745\n", - "INFO:tensorflow:global_step/sec: 261.233\n", - "INFO:tensorflow:step = 5501, loss = 0.0407551\n", - "INFO:tensorflow:global_step/sec: 261.96\n", - "INFO:tensorflow:step = 5601, loss = 0.059933\n", - "INFO:tensorflow:global_step/sec: 266.29\n", - "INFO:tensorflow:step = 5701, loss = 0.0105129\n", - "INFO:tensorflow:global_step/sec: 267.622\n", - "INFO:tensorflow:step = 5801, loss = 0.00775855\n", - "INFO:tensorflow:global_step/sec: 264.971\n", - "INFO:tensorflow:step = 5901, loss = 0.0600619\n", - "INFO:tensorflow:global_step/sec: 267.956\n", - "INFO:tensorflow:step = 6001, loss = 0.137863\n", - "INFO:tensorflow:global_step/sec: 265.11\n", - "INFO:tensorflow:step = 6101, loss = 0.0100134\n", - "INFO:tensorflow:global_step/sec: 270.769\n", - "INFO:tensorflow:step = 6201, loss = 0.0170551\n", - "INFO:tensorflow:global_step/sec: 269.998\n", - "INFO:tensorflow:step = 6301, loss = 0.0741573\n", - "INFO:tensorflow:global_step/sec: 267.485\n", - "INFO:tensorflow:step = 6401, loss = 0.0196445\n", - "INFO:tensorflow:global_step/sec: 256.387\n", - "INFO:tensorflow:step = 6501, loss = 0.0100872\n", - "INFO:tensorflow:global_step/sec: 263.009\n", - "INFO:tensorflow:step = 6601, loss = 0.00834956\n", - "INFO:tensorflow:global_step/sec: 260.941\n", - "INFO:tensorflow:step = 6701, loss = 0.0113611\n", - "INFO:tensorflow:global_step/sec: 261.688\n", - "INFO:tensorflow:step = 6801, loss = 0.00559575\n", - "INFO:tensorflow:global_step/sec: 266.126\n", - "INFO:tensorflow:step = 6901, loss = 0.013403\n", - "INFO:tensorflow:global_step/sec: 265.606\n", - "INFO:tensorflow:step = 7001, loss = 0.0323094\n", - "INFO:tensorflow:global_step/sec: 263.16\n", - "INFO:tensorflow:step = 7101, loss = 0.0110709\n", - "INFO:tensorflow:global_step/sec: 245.675\n", - "INFO:tensorflow:step = 7201, loss = 0.0326521\n", - "INFO:tensorflow:global_step/sec: 263.859\n", - "INFO:tensorflow:step = 7301, loss = 0.00889494\n", - "INFO:tensorflow:global_step/sec: 265.057\n", - "INFO:tensorflow:step = 7401, loss = 0.0173639\n", - "INFO:tensorflow:global_step/sec: 266.844\n", - "INFO:tensorflow:step = 7501, loss = 0.00434639\n", - "INFO:tensorflow:global_step/sec: 264.902\n", - "INFO:tensorflow:step = 7601, loss = 0.035643\n", - "INFO:tensorflow:global_step/sec: 267.666\n", - "INFO:tensorflow:step = 7701, loss = 0.00853796\n", - "INFO:tensorflow:global_step/sec: 268.121\n", - "INFO:tensorflow:step = 7801, loss = 0.00428518\n", - "INFO:tensorflow:global_step/sec: 261.36\n", - "INFO:tensorflow:step = 7901, loss = 0.0232153\n", - "INFO:tensorflow:global_step/sec: 267.48\n", - "INFO:tensorflow:step = 8001, loss = 0.00182722\n", - "INFO:tensorflow:global_step/sec: 264.632\n", - "INFO:tensorflow:step = 8101, loss = 0.0302677\n", - "INFO:tensorflow:global_step/sec: 265.2\n", - "INFO:tensorflow:step = 8201, loss = 0.0134658\n", - "INFO:tensorflow:global_step/sec: 265.434\n", - "INFO:tensorflow:step = 8301, loss = 0.0458922\n", - "INFO:tensorflow:global_step/sec: 264.779\n", - "INFO:tensorflow:step = 8401, loss = 0.00551947\n", - "INFO:tensorflow:global_step/sec: 266.52\n", - "INFO:tensorflow:step = 8501, loss = 0.00715816\n", - "INFO:tensorflow:global_step/sec: 268.68\n", - "INFO:tensorflow:step = 8601, loss = 0.0024569\n", - "INFO:tensorflow:global_step/sec: 263.982\n", - "INFO:tensorflow:step = 8701, loss = 0.00357583\n", - "INFO:tensorflow:global_step/sec: 263.412\n", - "INFO:tensorflow:step = 8801, loss = 0.0145001\n", - "INFO:tensorflow:global_step/sec: 264.913\n", - "INFO:tensorflow:step = 8901, loss = 0.00273304\n", - "INFO:tensorflow:global_step/sec: 264.721\n", - "INFO:tensorflow:step = 9001, loss = 0.0154719\n", - "INFO:tensorflow:global_step/sec: 266.284\n", - "INFO:tensorflow:step = 9101, loss = 0.00689276\n", - "INFO:tensorflow:global_step/sec: 260.827\n", - "INFO:tensorflow:step = 9201, loss = 0.0055988\n", - "INFO:tensorflow:global_step/sec: 261.611\n", - "INFO:tensorflow:step = 9301, loss = 0.0120085\n", - "INFO:tensorflow:global_step/sec: 264.147\n", - "INFO:tensorflow:step = 9401, loss = 0.0305538\n", - "INFO:tensorflow:global_step/sec: 264.386\n", - "INFO:tensorflow:step = 9501, loss = 0.0047565\n", - "INFO:tensorflow:global_step/sec: 255.262\n", - "INFO:tensorflow:step = 9601, loss = 0.0167732\n", - "INFO:tensorflow:global_step/sec: 244.569\n", - "INFO:tensorflow:step = 9701, loss = 0.00320569\n", - "INFO:tensorflow:global_step/sec: 251.616\n", - "INFO:tensorflow:step = 9801, loss = 0.0166949\n", - "INFO:tensorflow:global_step/sec: 248.793\n", - "INFO:tensorflow:step = 9901, loss = 0.0126207\n", - "INFO:tensorflow:global_step/sec: 252.162\n", - "INFO:tensorflow:step = 10001, loss = 0.00503674\n", - "INFO:tensorflow:global_step/sec: 243.868\n", - "INFO:tensorflow:step = 10101, loss = 0.0135752\n", - "INFO:tensorflow:global_step/sec: 243.911\n", - "INFO:tensorflow:step = 10201, loss = 0.00947774\n", - "INFO:tensorflow:global_step/sec: 252.785\n", - "INFO:tensorflow:step = 10301, loss = 0.00903084\n", - "INFO:tensorflow:global_step/sec: 250.763\n", - "INFO:tensorflow:step = 10401, loss = 0.00326914\n", - "INFO:tensorflow:global_step/sec: 247.976\n", - "INFO:tensorflow:step = 10501, loss = 0.00418044\n", - "INFO:tensorflow:global_step/sec: 168.467\n", - "INFO:tensorflow:step = 10601, loss = 0.00981428\n", - "INFO:tensorflow:global_step/sec: 239.297\n", - "INFO:tensorflow:step = 10701, loss = 0.0198247\n", - "INFO:tensorflow:global_step/sec: 245.054\n", - "INFO:tensorflow:step = 10801, loss = 0.0123972\n", - "INFO:tensorflow:global_step/sec: 243.707\n", - "INFO:tensorflow:step = 10901, loss = 0.00193546\n", - "INFO:tensorflow:global_step/sec: 253.569\n", - "INFO:tensorflow:step = 11001, loss = 0.0192977\n", - "INFO:tensorflow:global_step/sec: 248.93\n", - "INFO:tensorflow:step = 11101, loss = 0.00524275\n", - "INFO:tensorflow:global_step/sec: 245.026\n", - "INFO:tensorflow:step = 11201, loss = 0.00167169\n", - "INFO:tensorflow:global_step/sec: 249.137\n", - "INFO:tensorflow:step = 11301, loss = 0.00450903\n", - "INFO:tensorflow:global_step/sec: 250.359\n", - "INFO:tensorflow:step = 11401, loss = 0.006075\n", - "INFO:tensorflow:global_step/sec: 252.84\n", - "INFO:tensorflow:step = 11501, loss = 0.014548\n", - "INFO:tensorflow:global_step/sec: 250.307\n", - "INFO:tensorflow:step = 11601, loss = 0.000971343\n", - "INFO:tensorflow:global_step/sec: 247.967\n", - "INFO:tensorflow:step = 11701, loss = 0.00491666\n", - "INFO:tensorflow:global_step/sec: 244.054\n", - "INFO:tensorflow:step = 11801, loss = 0.000402435\n", - "INFO:tensorflow:global_step/sec: 241.133\n", - "INFO:tensorflow:step = 11901, loss = 0.00428989\n", - "INFO:tensorflow:global_step/sec: 245.259\n", - "INFO:tensorflow:step = 12001, loss = 0.000430896\n", - "INFO:tensorflow:global_step/sec: 246.885\n", - "INFO:tensorflow:step = 12101, loss = 0.00598627\n", + "INFO:tensorflow:Saving checkpoints for 1 into /tmp/tmp7zss569e/model.ckpt.\n", + "INFO:tensorflow:loss = 2.33582, step = 1\n", + "INFO:tensorflow:global_step/sec: 232.736\n", + "INFO:tensorflow:loss = 0.27437, step = 101\n", + "INFO:tensorflow:global_step/sec: 241.055\n", + "INFO:tensorflow:loss = 0.269322, step = 201\n", + "INFO:tensorflow:global_step/sec: 226.091\n", + "INFO:tensorflow:loss = 0.38457, step = 301\n", + "INFO:tensorflow:global_step/sec: 208.719\n", + "INFO:tensorflow:loss = 0.260778, step = 401\n", + "INFO:tensorflow:global_step/sec: 214.101\n", + "INFO:tensorflow:loss = 0.248095, step = 501\n", + "INFO:tensorflow:global_step/sec: 183.667\n", + "INFO:tensorflow:loss = 0.0638462, step = 601\n", + "INFO:tensorflow:global_step/sec: 202.389\n", + "INFO:tensorflow:loss = 0.142341, step = 701\n", + "INFO:tensorflow:global_step/sec: 196.715\n", + "INFO:tensorflow:loss = 0.189448, step = 801\n", + "INFO:tensorflow:global_step/sec: 162.115\n", + "INFO:tensorflow:loss = 0.0936472, step = 901\n", + "INFO:tensorflow:global_step/sec: 179.778\n", + "INFO:tensorflow:loss = 0.219577, step = 1001\n", + "INFO:tensorflow:global_step/sec: 182.234\n", + "INFO:tensorflow:loss = 0.164676, step = 1101\n", + "INFO:tensorflow:global_step/sec: 244.283\n", + "INFO:tensorflow:loss = 0.168738, step = 1201\n", + "INFO:tensorflow:global_step/sec: 241.932\n", + "INFO:tensorflow:loss = 0.164561, step = 1301\n", + "INFO:tensorflow:global_step/sec: 194.53\n", + "INFO:tensorflow:loss = 0.0613272, step = 1401\n", + "INFO:tensorflow:global_step/sec: 185.759\n", + "INFO:tensorflow:loss = 0.120366, step = 1501\n", + "INFO:tensorflow:global_step/sec: 217.706\n", + "INFO:tensorflow:loss = 0.135398, step = 1601\n", + "INFO:tensorflow:global_step/sec: 196.067\n", + "INFO:tensorflow:loss = 0.0358065, step = 1701\n", + "INFO:tensorflow:global_step/sec: 206.017\n", + "INFO:tensorflow:loss = 0.143794, step = 1801\n", + "INFO:tensorflow:global_step/sec: 219.435\n", + "INFO:tensorflow:loss = 0.089612, step = 1901\n", + "INFO:tensorflow:global_step/sec: 222.212\n", + "INFO:tensorflow:loss = 0.102802, step = 2001\n", + "INFO:tensorflow:global_step/sec: 224.6\n", + "INFO:tensorflow:loss = 0.0238651, step = 2101\n", + "INFO:tensorflow:global_step/sec: 215.887\n", + "INFO:tensorflow:loss = 0.0385514, step = 2201\n", + "INFO:tensorflow:global_step/sec: 224.202\n", + "INFO:tensorflow:loss = 0.0744303, step = 2301\n", + "INFO:tensorflow:global_step/sec: 216.387\n", + "INFO:tensorflow:loss = 0.0479892, step = 2401\n", + "INFO:tensorflow:global_step/sec: 172.553\n", + "INFO:tensorflow:loss = 0.0908712, step = 2501\n", + "INFO:tensorflow:global_step/sec: 178.59\n", + "INFO:tensorflow:loss = 0.0467151, step = 2601\n", + "INFO:tensorflow:global_step/sec: 200.186\n", + "INFO:tensorflow:loss = 0.0115768, step = 2701\n", + "INFO:tensorflow:global_step/sec: 198.792\n", + "INFO:tensorflow:loss = 0.0435034, step = 2801\n", + "INFO:tensorflow:global_step/sec: 203.308\n", + "INFO:tensorflow:loss = 0.12453, step = 2901\n", + "INFO:tensorflow:global_step/sec: 198.026\n", + "INFO:tensorflow:loss = 0.0150253, step = 3001\n", + "INFO:tensorflow:global_step/sec: 200.059\n", + "INFO:tensorflow:loss = 0.0531305, step = 3101\n", + "INFO:tensorflow:global_step/sec: 205.495\n", + "INFO:tensorflow:loss = 0.0127235, step = 3201\n", + "INFO:tensorflow:global_step/sec: 188.812\n", + "INFO:tensorflow:loss = 0.022856, step = 3301\n", + "INFO:tensorflow:global_step/sec: 206.492\n", + "INFO:tensorflow:loss = 0.17245, step = 3401\n", + "INFO:tensorflow:global_step/sec: 221.094\n", + "INFO:tensorflow:loss = 0.113406, step = 3501\n", + "INFO:tensorflow:global_step/sec: 170.705\n", + "INFO:tensorflow:loss = 0.126381, step = 3601\n", + "INFO:tensorflow:global_step/sec: 184.293\n", + "INFO:tensorflow:loss = 0.0568855, step = 3701\n", + "INFO:tensorflow:global_step/sec: 216.495\n", + "INFO:tensorflow:loss = 0.0132421, step = 3801\n", + "INFO:tensorflow:global_step/sec: 228.173\n", + "INFO:tensorflow:loss = 0.102047, step = 3901\n", + "INFO:tensorflow:global_step/sec: 226.907\n", + "INFO:tensorflow:loss = 0.141461, step = 4001\n", + "INFO:tensorflow:global_step/sec: 225.195\n", + "INFO:tensorflow:loss = 0.0300985, step = 4101\n", + "INFO:tensorflow:global_step/sec: 227.254\n", + "INFO:tensorflow:loss = 0.042273, step = 4201\n", + "INFO:tensorflow:global_step/sec: 247.86\n", + "INFO:tensorflow:loss = 0.15238, step = 4301\n", + "INFO:tensorflow:global_step/sec: 248.962\n", + "INFO:tensorflow:loss = 0.0881295, step = 4401\n", + "INFO:tensorflow:global_step/sec: 246.632\n", + "INFO:tensorflow:loss = 0.0174146, step = 4501\n", + "INFO:tensorflow:global_step/sec: 177.153\n", + "INFO:tensorflow:loss = 0.0178437, step = 4601\n", + "INFO:tensorflow:global_step/sec: 234.802\n", + "INFO:tensorflow:loss = 0.0132971, step = 4701\n", + "INFO:tensorflow:global_step/sec: 246.051\n", + "INFO:tensorflow:loss = 0.0232754, step = 4801\n", + "INFO:tensorflow:global_step/sec: 244.843\n", + "INFO:tensorflow:loss = 0.0572909, step = 4901\n", + "INFO:tensorflow:global_step/sec: 227.631\n", + "INFO:tensorflow:loss = 0.0557351, step = 5001\n", + "INFO:tensorflow:global_step/sec: 196.75\n", + "INFO:tensorflow:loss = 0.0116517, step = 5101\n", + "INFO:tensorflow:global_step/sec: 222.078\n", + "INFO:tensorflow:loss = 0.0428042, step = 5201\n", + "INFO:tensorflow:global_step/sec: 187.775\n", + "INFO:tensorflow:loss = 0.0168372, step = 5301\n", + "INFO:tensorflow:global_step/sec: 201.735\n", + "INFO:tensorflow:loss = 0.0486017, step = 5401\n", + "INFO:tensorflow:global_step/sec: 224.78\n", + "INFO:tensorflow:loss = 0.0476393, step = 5501\n", + "INFO:tensorflow:global_step/sec: 222.074\n", + "INFO:tensorflow:loss = 0.0486749, step = 5601\n", + "INFO:tensorflow:global_step/sec: 220.022\n", + "INFO:tensorflow:loss = 0.0204452, step = 5701\n", + "INFO:tensorflow:global_step/sec: 195.329\n", + "INFO:tensorflow:loss = 0.0128521, step = 5801\n", + "INFO:tensorflow:global_step/sec: 173.434\n", + "INFO:tensorflow:loss = 0.092056, step = 5901\n", + "INFO:tensorflow:global_step/sec: 170.983\n", + "INFO:tensorflow:loss = 0.113198, step = 6001\n", + "INFO:tensorflow:global_step/sec: 170.622\n", + "INFO:tensorflow:loss = 0.0123016, step = 6101\n", + "INFO:tensorflow:global_step/sec: 177.83\n", + "INFO:tensorflow:loss = 0.0178882, step = 6201\n", + "INFO:tensorflow:global_step/sec: 169.424\n", + "INFO:tensorflow:loss = 0.0549205, step = 6301\n", + "INFO:tensorflow:global_step/sec: 166.949\n", + "INFO:tensorflow:loss = 0.0254723, step = 6401\n", + "INFO:tensorflow:global_step/sec: 187.405\n", + "INFO:tensorflow:loss = 0.0159722, step = 6501\n", + "INFO:tensorflow:global_step/sec: 199.493\n", + "INFO:tensorflow:loss = 0.005644, step = 6601\n", + "INFO:tensorflow:global_step/sec: 204.607\n", + "INFO:tensorflow:loss = 0.0149404, step = 6701\n", + "INFO:tensorflow:global_step/sec: 202.233\n", + "INFO:tensorflow:loss = 0.010484, step = 6801\n", + "INFO:tensorflow:global_step/sec: 198.638\n", + "INFO:tensorflow:loss = 0.0133455, step = 6901\n", + "INFO:tensorflow:global_step/sec: 201.837\n", + "INFO:tensorflow:loss = 0.0251883, step = 7001\n", + "INFO:tensorflow:global_step/sec: 204.075\n", + "INFO:tensorflow:loss = 0.00227061, step = 7101\n", + "INFO:tensorflow:global_step/sec: 206.319\n", + "INFO:tensorflow:loss = 0.0713634, step = 7201\n", + "INFO:tensorflow:global_step/sec: 203.238\n", + "INFO:tensorflow:loss = 0.00441089, step = 7301\n", + "INFO:tensorflow:global_step/sec: 204.605\n", + "INFO:tensorflow:loss = 0.00593142, step = 7401\n", + "INFO:tensorflow:global_step/sec: 204.406\n", + "INFO:tensorflow:loss = 0.00345275, step = 7501\n", + "INFO:tensorflow:global_step/sec: 202.258\n", + "INFO:tensorflow:loss = 0.013012, step = 7601\n", + "INFO:tensorflow:global_step/sec: 200.434\n", + "INFO:tensorflow:loss = 0.00894726, step = 7701\n", + "INFO:tensorflow:global_step/sec: 204.126\n", + "INFO:tensorflow:loss = 0.00337269, step = 7801\n", + "INFO:tensorflow:global_step/sec: 206.978\n", + "INFO:tensorflow:loss = 0.00881938, step = 7901\n", + "INFO:tensorflow:global_step/sec: 225.289\n", + "INFO:tensorflow:loss = 0.00304166, step = 8001\n", + "INFO:tensorflow:global_step/sec: 219.813\n", + "INFO:tensorflow:loss = 0.0224723, step = 8101\n", + "INFO:tensorflow:global_step/sec: 165.652\n", + "INFO:tensorflow:loss = 0.0193584, step = 8201\n", + "INFO:tensorflow:global_step/sec: 170.095\n", + "INFO:tensorflow:loss = 0.0556088, step = 8301\n", + "INFO:tensorflow:global_step/sec: 222.843\n", + "INFO:tensorflow:loss = 0.0104646, step = 8401\n", + "INFO:tensorflow:global_step/sec: 226.252\n", + "INFO:tensorflow:loss = 0.00550747, step = 8501\n", + "INFO:tensorflow:global_step/sec: 225.572\n", + "INFO:tensorflow:loss = 0.0020269, step = 8601\n", + "INFO:tensorflow:global_step/sec: 227.813\n", + "INFO:tensorflow:loss = 0.00409054, step = 8701\n", + "INFO:tensorflow:global_step/sec: 246.437\n", + "INFO:tensorflow:loss = 0.00901896, step = 8801\n", "INFO:tensorflow:global_step/sec: 249.994\n", - "INFO:tensorflow:step = 12201, loss = 0.00443125\n", - "INFO:tensorflow:global_step/sec: 244.643\n", - "INFO:tensorflow:step = 12301, loss = 0.00464918\n", - "INFO:tensorflow:global_step/sec: 243.309\n", - "INFO:tensorflow:step = 12401, loss = 0.000441867\n", - "INFO:tensorflow:global_step/sec: 250.808\n", - "INFO:tensorflow:step = 12501, loss = 0.00116503\n", - "INFO:tensorflow:global_step/sec: 246.728\n", - "INFO:tensorflow:step = 12601, loss = 0.00111193\n", - "INFO:tensorflow:global_step/sec: 248.218\n", - "INFO:tensorflow:step = 12701, loss = 0.00284948\n", - "INFO:tensorflow:global_step/sec: 249.957\n", - "INFO:tensorflow:step = 12801, loss = 0.00891217\n", - "INFO:tensorflow:global_step/sec: 248.482\n", - "INFO:tensorflow:step = 12901, loss = 0.00487016\n", - "INFO:tensorflow:global_step/sec: 249.405\n", - "INFO:tensorflow:step = 13001, loss = 0.00393647\n", - "INFO:tensorflow:global_step/sec: 236.455\n", - "INFO:tensorflow:step = 13101, loss = 0.00700558\n", - "INFO:tensorflow:global_step/sec: 246.88\n", - "INFO:tensorflow:step = 13201, loss = 0.00445399\n", - "INFO:tensorflow:global_step/sec: 244.8\n", - "INFO:tensorflow:step = 13301, loss = 0.00342426\n", - "INFO:tensorflow:global_step/sec: 247.414\n", - "INFO:tensorflow:step = 13401, loss = 0.0122895\n", - "INFO:tensorflow:global_step/sec: 251.312\n", - "INFO:tensorflow:step = 13501, loss = 0.00549989\n", - "INFO:tensorflow:global_step/sec: 248.626\n", - "INFO:tensorflow:step = 13601, loss = 0.00425534\n", - "INFO:tensorflow:global_step/sec: 247.163\n", - "INFO:tensorflow:step = 13701, loss = 0.00198492\n", - "INFO:tensorflow:global_step/sec: 250.463\n", - "INFO:tensorflow:step = 13801, loss = 0.00456028\n", - "INFO:tensorflow:global_step/sec: 247.789\n", - "INFO:tensorflow:step = 13901, loss = 0.00288654\n", - "INFO:tensorflow:global_step/sec: 248.548\n", - "INFO:tensorflow:step = 14001, loss = 0.00143443\n", - "INFO:tensorflow:global_step/sec: 240.287\n", - "INFO:tensorflow:step = 14101, loss = 0.00547716\n", - "INFO:tensorflow:global_step/sec: 242.846\n", - "INFO:tensorflow:step = 14201, loss = 0.00444594\n", - "INFO:tensorflow:global_step/sec: 235.527\n", - "INFO:tensorflow:step = 14301, loss = 0.00101852\n", - "INFO:tensorflow:global_step/sec: 236.087\n", - "INFO:tensorflow:step = 14401, loss = 0.000907388\n", - "INFO:tensorflow:global_step/sec: 250.224\n", - "INFO:tensorflow:step = 14501, loss = 0.000484752\n", - "INFO:tensorflow:global_step/sec: 243.983\n", - "INFO:tensorflow:step = 14601, loss = 0.00389277\n", - "INFO:tensorflow:global_step/sec: 244.299\n", - "INFO:tensorflow:step = 14701, loss = 0.00117707\n", - "INFO:tensorflow:global_step/sec: 247.275\n", - "INFO:tensorflow:step = 14801, loss = 0.000943235\n", - "INFO:tensorflow:global_step/sec: 246.136\n", - "INFO:tensorflow:step = 14901, loss = 0.0022002\n", - "INFO:tensorflow:global_step/sec: 252.242\n", - "INFO:tensorflow:step = 15001, loss = 0.000899703\n", - "INFO:tensorflow:global_step/sec: 248.166\n", - "INFO:tensorflow:step = 15101, loss = 0.00156591\n", - "INFO:tensorflow:global_step/sec: 252.96\n", - "INFO:tensorflow:step = 15201, loss = 0.0012625\n", - "INFO:tensorflow:global_step/sec: 248.383\n", - "INFO:tensorflow:step = 15301, loss = 0.00242751\n", - "INFO:tensorflow:global_step/sec: 243.749\n", - "INFO:tensorflow:step = 15401, loss = 0.00408677\n", - "INFO:tensorflow:global_step/sec: 238.935\n", - "INFO:tensorflow:step = 15501, loss = 0.00477146\n", - "INFO:tensorflow:global_step/sec: 249.892\n", - "INFO:tensorflow:step = 15601, loss = 0.00529571\n", - "INFO:tensorflow:global_step/sec: 249.813\n", - "INFO:tensorflow:step = 15701, loss = 0.00946869\n", - "INFO:tensorflow:global_step/sec: 248.988\n", - "INFO:tensorflow:step = 15801, loss = 0.000920816\n", - "INFO:tensorflow:global_step/sec: 250.56\n", - "INFO:tensorflow:step = 15901, loss = 0.000340587\n", - "INFO:tensorflow:global_step/sec: 251.236\n", - "INFO:tensorflow:step = 16001, loss = 0.00582687\n", - "INFO:tensorflow:global_step/sec: 245.505\n", - "INFO:tensorflow:step = 16101, loss = 0.00268699\n", - "INFO:tensorflow:global_step/sec: 251.138\n", - "INFO:tensorflow:step = 16201, loss = 5.72727e-05\n", - "INFO:tensorflow:global_step/sec: 244.844\n", - "INFO:tensorflow:step = 16301, loss = 0.00230679\n", - "INFO:tensorflow:global_step/sec: 249.935\n", - "INFO:tensorflow:step = 16401, loss = 0.00171192\n", - "INFO:tensorflow:global_step/sec: 248.462\n", - "INFO:tensorflow:step = 16501, loss = 0.0016867\n", - "INFO:tensorflow:global_step/sec: 248.387\n", - "INFO:tensorflow:step = 16601, loss = 0.0022899\n", - "INFO:tensorflow:global_step/sec: 245.245\n", - "INFO:tensorflow:step = 16701, loss = 0.00230502\n", - "INFO:tensorflow:global_step/sec: 241.63\n", - "INFO:tensorflow:step = 16801, loss = 0.00312321\n", - "INFO:tensorflow:global_step/sec: 248.868\n", - "INFO:tensorflow:step = 16901, loss = 0.00434566\n", - "INFO:tensorflow:global_step/sec: 247.993\n", - "INFO:tensorflow:step = 17001, loss = 0.0052677\n", - "INFO:tensorflow:global_step/sec: 244.877\n", - "INFO:tensorflow:step = 17101, loss = 0.00145811\n", - "INFO:tensorflow:global_step/sec: 248.081\n", - "INFO:tensorflow:step = 17201, loss = 0.00205843\n", - "INFO:tensorflow:global_step/sec: 244.37\n", - "INFO:tensorflow:step = 17301, loss = 0.00130019\n", - "INFO:tensorflow:global_step/sec: 250.473\n", - "INFO:tensorflow:step = 17401, loss = 0.00176198\n", - "INFO:tensorflow:global_step/sec: 239.867\n", - "INFO:tensorflow:step = 17501, loss = 0.00104172\n", - "INFO:tensorflow:global_step/sec: 246.066\n", - "INFO:tensorflow:step = 17601, loss = 0.0016109\n", - "INFO:tensorflow:global_step/sec: 240.935\n", - "INFO:tensorflow:step = 17701, loss = 0.000893278\n", - "INFO:tensorflow:global_step/sec: 242.978\n", - "INFO:tensorflow:step = 17801, loss = 0.000108865\n", - "INFO:tensorflow:global_step/sec: 250.211\n", - "INFO:tensorflow:step = 17901, loss = 0.00272813\n", - "INFO:tensorflow:global_step/sec: 245.557\n", - "INFO:tensorflow:step = 18001, loss = 0.000493953\n", - "INFO:tensorflow:global_step/sec: 244.553\n", - "INFO:tensorflow:step = 18101, loss = 0.00107321\n", - "INFO:tensorflow:global_step/sec: 244.391\n", - "INFO:tensorflow:step = 18201, loss = 0.00432032\n", - "INFO:tensorflow:global_step/sec: 248.068\n", - "INFO:tensorflow:step = 18301, loss = 0.00682757\n", - "INFO:tensorflow:global_step/sec: 244.677\n", - "INFO:tensorflow:step = 18401, loss = 0.00247597\n", - "INFO:tensorflow:global_step/sec: 251.405\n", - "INFO:tensorflow:step = 18501, loss = 0.00179731\n", - "INFO:tensorflow:global_step/sec: 244.564\n", - "INFO:tensorflow:step = 18601, loss = 0.00293765\n", - "INFO:tensorflow:global_step/sec: 242.328\n", - "INFO:tensorflow:step = 18701, loss = 0.00115208\n", - "INFO:tensorflow:global_step/sec: 246.41\n", - "INFO:tensorflow:step = 18801, loss = 0.00135701\n", - "INFO:tensorflow:global_step/sec: 245.431\n", - "INFO:tensorflow:step = 18901, loss = 0.00296331\n", - "INFO:tensorflow:global_step/sec: 248.573\n", - "INFO:tensorflow:step = 19001, loss = 0.00132945\n", - "INFO:tensorflow:global_step/sec: 244.966\n", - "INFO:tensorflow:step = 19101, loss = 0.00102776\n", - "INFO:tensorflow:global_step/sec: 250.039\n", - "INFO:tensorflow:step = 19201, loss = 0.000434285\n", - "INFO:tensorflow:global_step/sec: 243.803\n", - "INFO:tensorflow:step = 19301, loss = 0.00649516\n", - "INFO:tensorflow:global_step/sec: 249.789\n", - "INFO:tensorflow:step = 19401, loss = 0.00038595\n", - "INFO:tensorflow:global_step/sec: 244.687\n", - "INFO:tensorflow:step = 19501, loss = 0.00202882\n", - "INFO:tensorflow:global_step/sec: 248.51\n", - "INFO:tensorflow:step = 19601, loss = 0.000549477\n", - "INFO:tensorflow:global_step/sec: 248.725\n", - "INFO:tensorflow:step = 19701, loss = 0.000107742\n", - "INFO:tensorflow:global_step/sec: 247.741\n", - "INFO:tensorflow:step = 19801, loss = 0.00034557\n", - "INFO:tensorflow:global_step/sec: 245.082\n", - "INFO:tensorflow:step = 19901, loss = 0.00245132\n", - "INFO:tensorflow:global_step/sec: 248.156\n", - "INFO:tensorflow:step = 20001, loss = 0.00279147\n", - "INFO:tensorflow:global_step/sec: 247.549\n", - "INFO:tensorflow:step = 20101, loss = 0.000340105\n", - "INFO:tensorflow:global_step/sec: 247.083\n", - "INFO:tensorflow:step = 20201, loss = 0.0020789\n", - "INFO:tensorflow:global_step/sec: 243.219\n", - "INFO:tensorflow:step = 20301, loss = 0.000787494\n", - "INFO:tensorflow:global_step/sec: 246.564\n", - "INFO:tensorflow:step = 20401, loss = 0.000245126\n", - "INFO:tensorflow:global_step/sec: 246.811\n", - "INFO:tensorflow:step = 20501, loss = 0.00153776\n", - "INFO:tensorflow:global_step/sec: 243.331\n", - "INFO:tensorflow:step = 20601, loss = 0.00123978\n", - "INFO:tensorflow:global_step/sec: 250.265\n", - "INFO:tensorflow:step = 20701, loss = 0.000603144\n", - "INFO:tensorflow:global_step/sec: 242.539\n", - "INFO:tensorflow:step = 20801, loss = 0.00137458\n", - "INFO:tensorflow:global_step/sec: 248.389\n", - "INFO:tensorflow:step = 20901, loss = 0.000536628\n", - "INFO:tensorflow:global_step/sec: 238.879\n", - "INFO:tensorflow:step = 21001, loss = 0.0018328\n", - "INFO:tensorflow:global_step/sec: 246.09\n", - "INFO:tensorflow:step = 21101, loss = 0.00114942\n", - "INFO:tensorflow:global_step/sec: 250.408\n", - "INFO:tensorflow:step = 21201, loss = 0.00303938\n", - "INFO:tensorflow:global_step/sec: 248.31\n", - "INFO:tensorflow:step = 21301, loss = 0.00087698\n", - "INFO:tensorflow:global_step/sec: 247.719\n", - "INFO:tensorflow:step = 21401, loss = 0.00141594\n", - "INFO:tensorflow:global_step/sec: 248.786\n", - "INFO:tensorflow:step = 21501, loss = 0.000281237\n", - "INFO:tensorflow:global_step/sec: 246.171\n", - "INFO:tensorflow:step = 21601, loss = 0.000930675\n", - "INFO:tensorflow:global_step/sec: 247.673\n", - "INFO:tensorflow:step = 21701, loss = 0.000837973\n", - "INFO:tensorflow:global_step/sec: 240.075\n", - "INFO:tensorflow:step = 21801, loss = 0.000813459\n", - "INFO:tensorflow:global_step/sec: 249.037\n", - "INFO:tensorflow:step = 21901, loss = 0.000547416\n", - "INFO:tensorflow:global_step/sec: 241.514\n", - "INFO:tensorflow:step = 22001, loss = 0.000244948\n", - "INFO:tensorflow:global_step/sec: 241.263\n", - "INFO:tensorflow:step = 22101, loss = 0.000257258\n", - "INFO:tensorflow:global_step/sec: 248.895\n", - "INFO:tensorflow:step = 22201, loss = 0.00182091\n", - "INFO:tensorflow:global_step/sec: 245.009\n", - "INFO:tensorflow:step = 22301, loss = 0.00297279\n", - "INFO:tensorflow:global_step/sec: 249.41\n", - "INFO:tensorflow:step = 22401, loss = 0.00137926\n", - "INFO:tensorflow:global_step/sec: 242.765\n", - "INFO:tensorflow:step = 22501, loss = 0.00146514\n", - "INFO:tensorflow:global_step/sec: 244.716\n", - "INFO:tensorflow:step = 22601, loss = 0.00264534\n", - "INFO:tensorflow:global_step/sec: 245.338\n", - "INFO:tensorflow:step = 22701, loss = 0.00126739\n", - "INFO:tensorflow:global_step/sec: 242.604\n", - "INFO:tensorflow:step = 22801, loss = 0.000698428\n", - "INFO:tensorflow:global_step/sec: 241.746\n", - "INFO:tensorflow:step = 22901, loss = 0.0020562\n", - "INFO:tensorflow:global_step/sec: 249.885\n", - "INFO:tensorflow:step = 23001, loss = 0.000768296\n", - "INFO:tensorflow:global_step/sec: 245.624\n", - "INFO:tensorflow:step = 23101, loss = 0.00314021\n", - "INFO:tensorflow:global_step/sec: 239.568\n", - "INFO:tensorflow:step = 23201, loss = 0.00144092\n", - "INFO:tensorflow:global_step/sec: 245.193\n", - "INFO:tensorflow:step = 23301, loss = 0.00168657\n", - "INFO:tensorflow:global_step/sec: 248.96\n", - "INFO:tensorflow:step = 23401, loss = 0.000903284\n", - "INFO:tensorflow:global_step/sec: 245.839\n", - "INFO:tensorflow:step = 23501, loss = 0.0011984\n", - "INFO:tensorflow:global_step/sec: 240.538\n", - "INFO:tensorflow:step = 23601, loss = 0.000466293\n", - "INFO:tensorflow:global_step/sec: 193.05\n", - "INFO:tensorflow:step = 23701, loss = 0.000249591\n", - "INFO:tensorflow:global_step/sec: 200.657\n", - "INFO:tensorflow:step = 23801, loss = 0.00127097\n", - "INFO:tensorflow:global_step/sec: 232.626\n", - "INFO:tensorflow:step = 23901, loss = 0.0013907\n", - "INFO:tensorflow:global_step/sec: 228.232\n", - "INFO:tensorflow:step = 24001, loss = 0.000850245\n", - "INFO:tensorflow:global_step/sec: 248.237\n", - "INFO:tensorflow:step = 24101, loss = 0.00067008\n", - "INFO:tensorflow:global_step/sec: 242.352\n", - "INFO:tensorflow:step = 24201, loss = 0.00162798\n", - "INFO:tensorflow:global_step/sec: 249.913\n", - "INFO:tensorflow:step = 24301, loss = 0.000157957\n", - "INFO:tensorflow:global_step/sec: 238.959\n", - "INFO:tensorflow:step = 24401, loss = 0.00172181\n", - "INFO:tensorflow:global_step/sec: 237.534\n", - "INFO:tensorflow:step = 24501, loss = 0.000770766\n", - "INFO:tensorflow:global_step/sec: 246.949\n", - "INFO:tensorflow:step = 24601, loss = 0.000254101\n", - "INFO:tensorflow:global_step/sec: 242.319\n", - "INFO:tensorflow:step = 24701, loss = 0.00130859\n", - "INFO:tensorflow:global_step/sec: 251.051\n", - "INFO:tensorflow:step = 24801, loss = 0.000816425\n", - "INFO:tensorflow:global_step/sec: 244.98\n", - "INFO:tensorflow:step = 24901, loss = 0.00153355\n", - "INFO:tensorflow:global_step/sec: 239.869\n", - "INFO:tensorflow:step = 25001, loss = 0.000311535\n", - "INFO:tensorflow:global_step/sec: 242.972\n", - "INFO:tensorflow:step = 25101, loss = 0.00109469\n", - "INFO:tensorflow:global_step/sec: 248.203\n", - "INFO:tensorflow:step = 25201, loss = 0.0020218\n", - "INFO:tensorflow:global_step/sec: 247.228\n", - "INFO:tensorflow:step = 25301, loss = 0.000132103\n", - "INFO:tensorflow:global_step/sec: 245.735\n", - "INFO:tensorflow:step = 25401, loss = 0.000610623\n", - "INFO:tensorflow:global_step/sec: 243.994\n", - "INFO:tensorflow:step = 25501, loss = 0.000781174\n", - "INFO:tensorflow:global_step/sec: 250.7\n", - "INFO:tensorflow:step = 25601, loss = 0.0013282\n", - "INFO:tensorflow:global_step/sec: 241.05\n", - "INFO:tensorflow:step = 25701, loss = 0.000808145\n", - "INFO:tensorflow:global_step/sec: 180.549\n", - "INFO:tensorflow:step = 25801, loss = 0.00108103\n", - "INFO:tensorflow:global_step/sec: 215.426\n", - "INFO:tensorflow:step = 25901, loss = 0.00230078\n", - "INFO:tensorflow:global_step/sec: 232.696\n", - "INFO:tensorflow:step = 26001, loss = 6.1131e-05\n", - "INFO:tensorflow:global_step/sec: 246.028\n", - "INFO:tensorflow:step = 26101, loss = 0.000970652\n", - "INFO:tensorflow:global_step/sec: 250.106\n", - "INFO:tensorflow:step = 26201, loss = 0.00072212\n", - "INFO:tensorflow:global_step/sec: 245.033\n", - "INFO:tensorflow:step = 26301, loss = 0.00085699\n", - "INFO:tensorflow:global_step/sec: 237.904\n", - "INFO:tensorflow:step = 26401, loss = 0.00150846\n", - "INFO:tensorflow:global_step/sec: 246.991\n", - "INFO:tensorflow:step = 26501, loss = 0.000699469\n", - "INFO:tensorflow:global_step/sec: 238.237\n", - "INFO:tensorflow:step = 26601, loss = 0.000750032\n", - "INFO:tensorflow:global_step/sec: 244.544\n", - "INFO:tensorflow:step = 26701, loss = 6.04618e-05\n", - "INFO:tensorflow:global_step/sec: 237.949\n", - "INFO:tensorflow:step = 26801, loss = 0.000458257\n", - "INFO:tensorflow:global_step/sec: 246.305\n", - "INFO:tensorflow:step = 26901, loss = 0.000821386\n", - "INFO:tensorflow:global_step/sec: 246.827\n", - "INFO:tensorflow:step = 27001, loss = 0.000517322\n", - "INFO:tensorflow:global_step/sec: 246.614\n", - "INFO:tensorflow:step = 27101, loss = 0.000386259\n", - "INFO:tensorflow:global_step/sec: 240.337\n", - "INFO:tensorflow:step = 27201, loss = 0.000272117\n", - "INFO:tensorflow:global_step/sec: 246.184\n", - "INFO:tensorflow:step = 27301, loss = 0.00166003\n", - "INFO:tensorflow:global_step/sec: 243.104\n", - "INFO:tensorflow:step = 27401, loss = 9.18467e-05\n", - "INFO:tensorflow:global_step/sec: 246.577\n", - "INFO:tensorflow:step = 27501, loss = 0.00151844\n", - "INFO:tensorflow:global_step/sec: 242.473\n", - "INFO:tensorflow:step = 27601, loss = 0.00109749\n", - "INFO:tensorflow:global_step/sec: 247.051\n", - "INFO:tensorflow:step = 27701, loss = 0.000505122\n", - "INFO:tensorflow:global_step/sec: 245.559\n", - "INFO:tensorflow:step = 27801, loss = 0.000277064\n", - "INFO:tensorflow:global_step/sec: 246.535\n", - "INFO:tensorflow:step = 27901, loss = 0.00047921\n", - "INFO:tensorflow:global_step/sec: 243.796\n", - "INFO:tensorflow:step = 28001, loss = 0.00115689\n", - "INFO:tensorflow:global_step/sec: 246.335\n", - "INFO:tensorflow:step = 28101, loss = 0.000566811\n", - "INFO:tensorflow:global_step/sec: 241.759\n", - "INFO:tensorflow:step = 28201, loss = 0.000805723\n", - "INFO:tensorflow:global_step/sec: 233.823\n", - "INFO:tensorflow:step = 28301, loss = 0.00087746\n", - "INFO:tensorflow:global_step/sec: 249.316\n", - "INFO:tensorflow:step = 28401, loss = 0.000773794\n", - "INFO:tensorflow:global_step/sec: 239.551\n", - "INFO:tensorflow:step = 28501, loss = 0.000328233\n", - "INFO:tensorflow:global_step/sec: 226.029\n", - "INFO:tensorflow:step = 28601, loss = 0.000284878\n", - "INFO:tensorflow:global_step/sec: 231.103\n", - "INFO:tensorflow:step = 28701, loss = 0.00101513\n", - "INFO:tensorflow:global_step/sec: 242.639\n", - "INFO:tensorflow:step = 28801, loss = 0.00114092\n", - "INFO:tensorflow:global_step/sec: 241.219\n", - "INFO:tensorflow:step = 28901, loss = 0.000341943\n", - "INFO:tensorflow:global_step/sec: 245.56\n", - "INFO:tensorflow:step = 29001, loss = 0.00153582\n", - "INFO:tensorflow:global_step/sec: 233.615\n", - "INFO:tensorflow:step = 29101, loss = 0.00119408\n", - "INFO:tensorflow:global_step/sec: 239.244\n", - "INFO:tensorflow:step = 29201, loss = 0.00144968\n", - "INFO:tensorflow:global_step/sec: 233.955\n", - "INFO:tensorflow:step = 29301, loss = 0.00131137\n", - "INFO:tensorflow:global_step/sec: 240.867\n", - "INFO:tensorflow:step = 29401, loss = 0.000922557\n", - "INFO:tensorflow:global_step/sec: 240.281\n", - "INFO:tensorflow:step = 29501, loss = 0.00124206\n", - "INFO:tensorflow:global_step/sec: 246.735\n", - "INFO:tensorflow:step = 29601, loss = 0.00045622\n", - "INFO:tensorflow:global_step/sec: 237.12\n", - "INFO:tensorflow:step = 29701, loss = 0.000168732\n", - "INFO:tensorflow:global_step/sec: 247.14\n", - "INFO:tensorflow:step = 29801, loss = 0.000520009\n", - "INFO:tensorflow:global_step/sec: 236.225\n", - "INFO:tensorflow:step = 29901, loss = 0.000940927\n", - "INFO:tensorflow:global_step/sec: 235.781\n", - "INFO:tensorflow:step = 30001, loss = 6.55183e-05\n", - "INFO:tensorflow:global_step/sec: 245.948\n", - "INFO:tensorflow:step = 30101, loss = 0.00114673\n", - "INFO:tensorflow:global_step/sec: 245.856\n", - "INFO:tensorflow:step = 30201, loss = 0.000330221\n", - "INFO:tensorflow:global_step/sec: 244.257\n", - "INFO:tensorflow:step = 30301, loss = 0.00113722\n", - "INFO:tensorflow:global_step/sec: 241.908\n", - "INFO:tensorflow:step = 30401, loss = 0.00145566\n", - "INFO:tensorflow:global_step/sec: 244.53\n", - "INFO:tensorflow:step = 30501, loss = 0.000797784\n", - "INFO:tensorflow:global_step/sec: 248.507\n", - "INFO:tensorflow:step = 30601, loss = 0.0008587\n", - "INFO:tensorflow:global_step/sec: 236.005\n", - "INFO:tensorflow:step = 30701, loss = 0.000842631\n", - "INFO:tensorflow:global_step/sec: 242.622\n", - "INFO:tensorflow:step = 30801, loss = 0.000945636\n", - "INFO:tensorflow:global_step/sec: 244.147\n", - "INFO:tensorflow:step = 30901, loss = 0.00131948\n", - "INFO:tensorflow:global_step/sec: 241.163\n", - "INFO:tensorflow:step = 31001, loss = 0.000880524\n", - "INFO:tensorflow:global_step/sec: 245.765\n", - "INFO:tensorflow:step = 31101, loss = 0.00116646\n", - "INFO:tensorflow:global_step/sec: 240.579\n", - "INFO:tensorflow:step = 31201, loss = 0.000565536\n", - "INFO:tensorflow:global_step/sec: 249.164\n", - "INFO:tensorflow:step = 31301, loss = 0.000322631\n", - "INFO:tensorflow:global_step/sec: 238.37\n", - "INFO:tensorflow:step = 31401, loss = 0.000807407\n", - "INFO:tensorflow:global_step/sec: 239.273\n", - "INFO:tensorflow:step = 31501, loss = 0.000204689\n", - "INFO:tensorflow:global_step/sec: 245.192\n", - "INFO:tensorflow:step = 31601, loss = 0.000169035\n", - "INFO:tensorflow:global_step/sec: 241.263\n", - "INFO:tensorflow:step = 31701, loss = 0.000707169\n", - "INFO:tensorflow:global_step/sec: 235.987\n", - "INFO:tensorflow:step = 31801, loss = 0.000105213\n", - "INFO:tensorflow:global_step/sec: 247.337\n", - "INFO:tensorflow:step = 31901, loss = 0.00102748\n", - "INFO:tensorflow:global_step/sec: 243.728\n", - "INFO:tensorflow:step = 32001, loss = 0.000195816\n", - "INFO:tensorflow:global_step/sec: 247.961\n", - "INFO:tensorflow:step = 32101, loss = 0.000221564\n", - "INFO:tensorflow:global_step/sec: 242.705\n", - "INFO:tensorflow:step = 32201, loss = 0.00137419\n", - "INFO:tensorflow:global_step/sec: 246.86\n", - "INFO:tensorflow:step = 32301, loss = 0.000418382\n", - "INFO:tensorflow:global_step/sec: 240.749\n", - "INFO:tensorflow:step = 32401, loss = 0.000154195\n", - "INFO:tensorflow:global_step/sec: 238.659\n", - "INFO:tensorflow:step = 32501, loss = 0.000584929\n", - "INFO:tensorflow:global_step/sec: 238.608\n", - "INFO:tensorflow:step = 32601, loss = 0.000108147\n", - "INFO:tensorflow:global_step/sec: 241.1\n", - "INFO:tensorflow:step = 32701, loss = 0.00088507\n", - "INFO:tensorflow:global_step/sec: 245.823\n", - "INFO:tensorflow:step = 32801, loss = 0.000875408\n", - "INFO:tensorflow:global_step/sec: 244.955\n", - "INFO:tensorflow:step = 32901, loss = 0.000654719\n", - "INFO:tensorflow:global_step/sec: 243.455\n", - "INFO:tensorflow:step = 33001, loss = 0.00065554\n", - "INFO:tensorflow:global_step/sec: 243.72\n", - "INFO:tensorflow:step = 33101, loss = 0.00170502\n", - "INFO:tensorflow:global_step/sec: 238.345\n", - "INFO:tensorflow:step = 33201, loss = 0.000959129\n", - "INFO:tensorflow:global_step/sec: 241.443\n", - "INFO:tensorflow:step = 33301, loss = 0.000135101\n", - "INFO:tensorflow:global_step/sec: 244.596\n", - "INFO:tensorflow:step = 33401, loss = 0.000821542\n", - "INFO:tensorflow:global_step/sec: 234.834\n", - "INFO:tensorflow:step = 33501, loss = 0.000344222\n", - "INFO:tensorflow:global_step/sec: 245.863\n", - "INFO:tensorflow:step = 33601, loss = 0.000636476\n", - "INFO:tensorflow:global_step/sec: 244.153\n", - "INFO:tensorflow:step = 33701, loss = 0.000885468\n", - "INFO:tensorflow:global_step/sec: 243.042\n", - "INFO:tensorflow:step = 33801, loss = 0.000874726\n", - "INFO:tensorflow:global_step/sec: 238.381\n", - "INFO:tensorflow:step = 33901, loss = 0.00105782\n", - "INFO:tensorflow:global_step/sec: 246.85\n", - "INFO:tensorflow:step = 34001, loss = 0.000729783\n", - "INFO:tensorflow:global_step/sec: 233.716\n", - "INFO:tensorflow:step = 34101, loss = 0.000687763\n", - "INFO:tensorflow:global_step/sec: 244.4\n", - "INFO:tensorflow:step = 34201, loss = 0.00104149\n", - "INFO:tensorflow:global_step/sec: 245.652\n", - "INFO:tensorflow:step = 34301, loss = 0.000168195\n", - "INFO:tensorflow:global_step/sec: 241.618\n", - "INFO:tensorflow:step = 34401, loss = 0.0002834\n", - "INFO:tensorflow:global_step/sec: 246.09\n", - "INFO:tensorflow:step = 34501, loss = 0.000569185\n", - "INFO:tensorflow:global_step/sec: 243.869\n", - "INFO:tensorflow:step = 34601, loss = 0.000454339\n", - "INFO:tensorflow:global_step/sec: 235.775\n", - "INFO:tensorflow:step = 34701, loss = 0.00153568\n", - "INFO:tensorflow:global_step/sec: 235.412\n", - "INFO:tensorflow:step = 34801, loss = 0.000622719\n", - "INFO:tensorflow:global_step/sec: 242.846\n", - "INFO:tensorflow:step = 34901, loss = 0.00054165\n", - "INFO:tensorflow:global_step/sec: 247.712\n", - "INFO:tensorflow:step = 35001, loss = 0.000450491\n", - "INFO:tensorflow:global_step/sec: 243.01\n", - "INFO:tensorflow:step = 35101, loss = 0.000623572\n", - "INFO:tensorflow:global_step/sec: 246.548\n", - "INFO:tensorflow:step = 35201, loss = 0.000144089\n", - "INFO:tensorflow:global_step/sec: 242.952\n", - "INFO:tensorflow:step = 35301, loss = 7.78079e-05\n", - "INFO:tensorflow:global_step/sec: 243.807\n", - "INFO:tensorflow:step = 35401, loss = 0.00105005\n", - "INFO:tensorflow:global_step/sec: 247.184\n", - "INFO:tensorflow:step = 35501, loss = 0.00014352\n", - "INFO:tensorflow:global_step/sec: 241.864\n", - "INFO:tensorflow:step = 35601, loss = 0.000269061\n", - "INFO:tensorflow:global_step/sec: 244.81\n", - "INFO:tensorflow:step = 35701, loss = 0.00115224\n", - "INFO:tensorflow:global_step/sec: 244.936\n", - "INFO:tensorflow:step = 35801, loss = 0.000905719\n", - "INFO:tensorflow:global_step/sec: 240.111\n", - "INFO:tensorflow:step = 35901, loss = 0.000680426\n", - "INFO:tensorflow:global_step/sec: 247.451\n", - "INFO:tensorflow:step = 36001, loss = 0.000322845\n", - "INFO:tensorflow:global_step/sec: 242.096\n", - "INFO:tensorflow:step = 36101, loss = 0.00124711\n", - "INFO:tensorflow:global_step/sec: 245.293\n", - "INFO:tensorflow:step = 36201, loss = 0.000507463\n", - "INFO:tensorflow:global_step/sec: 241.615\n", - "INFO:tensorflow:step = 36301, loss = 0.000235807\n", - "INFO:tensorflow:global_step/sec: 244.294\n", - "INFO:tensorflow:step = 36401, loss = 0.00077797\n", - "INFO:tensorflow:global_step/sec: 236.347\n", - "INFO:tensorflow:step = 36501, loss = 0.00020462\n", - "INFO:tensorflow:global_step/sec: 227.267\n", - "INFO:tensorflow:step = 36601, loss = 0.000275301\n", - "INFO:tensorflow:global_step/sec: 242.004\n", - "INFO:tensorflow:step = 36701, loss = 0.00020321\n", - "INFO:tensorflow:global_step/sec: 241.99\n", - "INFO:tensorflow:step = 36801, loss = 0.000844449\n", - "INFO:tensorflow:global_step/sec: 234.881\n", - "INFO:tensorflow:step = 36901, loss = 0.000557124\n", - "INFO:tensorflow:global_step/sec: 245.162\n", - "INFO:tensorflow:step = 37001, loss = 0.000396684\n", - "INFO:tensorflow:global_step/sec: 238.864\n", - "INFO:tensorflow:step = 37101, loss = 0.00016357\n", - "INFO:tensorflow:global_step/sec: 244.372\n", - "INFO:tensorflow:step = 37201, loss = 0.000212332\n", - "INFO:tensorflow:global_step/sec: 242.111\n", - "INFO:tensorflow:step = 37301, loss = 0.000865044\n", - "INFO:tensorflow:global_step/sec: 245.475\n", - "INFO:tensorflow:step = 37401, loss = 0.000353255\n", - "INFO:tensorflow:global_step/sec: 243.818\n", - "INFO:tensorflow:step = 37501, loss = 0.000183781\n", - "INFO:tensorflow:global_step/sec: 240.41\n", - "INFO:tensorflow:step = 37601, loss = 0.000351368\n", - "INFO:tensorflow:global_step/sec: 245.559\n", - "INFO:tensorflow:step = 37701, loss = 0.000124169\n", - "INFO:tensorflow:global_step/sec: 241.597\n", - "INFO:tensorflow:step = 37801, loss = 0.000490647\n", - "INFO:tensorflow:global_step/sec: 243.379\n", - "INFO:tensorflow:step = 37901, loss = 0.00138029\n", - "INFO:tensorflow:global_step/sec: 244.721\n", - "INFO:tensorflow:step = 38001, loss = 0.000172892\n", - "INFO:tensorflow:global_step/sec: 243.427\n", - "INFO:tensorflow:step = 38101, loss = 0.000794774\n", - "INFO:tensorflow:global_step/sec: 242.264\n", - "INFO:tensorflow:step = 38201, loss = 0.00051292\n", - "INFO:tensorflow:global_step/sec: 242.455\n", - "INFO:tensorflow:step = 38301, loss = 8.52539e-05\n", - "INFO:tensorflow:global_step/sec: 239.979\n", - "INFO:tensorflow:step = 38401, loss = 0.000246268\n", - "INFO:tensorflow:global_step/sec: 241.008\n", - "INFO:tensorflow:step = 38501, loss = 0.000642512\n", - "INFO:tensorflow:global_step/sec: 244.412\n", - "INFO:tensorflow:step = 38601, loss = 0.000691297\n", - "INFO:tensorflow:global_step/sec: 233.413\n", - "INFO:tensorflow:step = 38701, loss = 0.00052233\n", - "INFO:tensorflow:global_step/sec: 235.453\n", - "INFO:tensorflow:step = 38801, loss = 0.000105408\n", - "INFO:tensorflow:global_step/sec: 244.125\n", - "INFO:tensorflow:step = 38901, loss = 0.00126448\n", - "INFO:tensorflow:global_step/sec: 238.689\n", - "INFO:tensorflow:step = 39001, loss = 0.000308452\n", - "INFO:tensorflow:global_step/sec: 244.176\n", - "INFO:tensorflow:step = 39101, loss = 0.000773441\n", - "INFO:tensorflow:global_step/sec: 240.856\n", - "INFO:tensorflow:step = 39201, loss = 0.000307987\n", - "INFO:tensorflow:global_step/sec: 244.67\n", - "INFO:tensorflow:step = 39301, loss = 0.000205293\n", - "INFO:tensorflow:global_step/sec: 245.733\n", - "INFO:tensorflow:step = 39401, loss = 0.000667318\n", - "INFO:tensorflow:global_step/sec: 236.613\n", - "INFO:tensorflow:step = 39501, loss = 0.000110089\n", - "INFO:tensorflow:global_step/sec: 241.411\n", - "INFO:tensorflow:step = 39601, loss = 0.000498979\n", - "INFO:tensorflow:global_step/sec: 243.139\n", - "INFO:tensorflow:step = 39701, loss = 0.000127125\n", - "INFO:tensorflow:global_step/sec: 245.656\n", - "INFO:tensorflow:step = 39801, loss = 0.000936548\n", - "INFO:tensorflow:global_step/sec: 233.223\n", - "INFO:tensorflow:step = 39901, loss = 0.000996868\n", - "INFO:tensorflow:Saving checkpoints for 40000 into /tmp/tmphilui6nx/model.ckpt.\n", - "INFO:tensorflow:Loss for final step: 0.000420265.\n" + "INFO:tensorflow:loss = 0.00243773, step = 8901\n", + "INFO:tensorflow:global_step/sec: 249.966\n", + "INFO:tensorflow:loss = 0.00704045, step = 9001\n", + "INFO:tensorflow:global_step/sec: 248.39\n", + "INFO:tensorflow:loss = 0.00667741, step = 9101\n", + "INFO:tensorflow:global_step/sec: 247.03\n", + "INFO:tensorflow:loss = 0.00851065, step = 9201\n", + "INFO:tensorflow:global_step/sec: 249.13\n", + "INFO:tensorflow:loss = 0.00764919, step = 9301\n", + "INFO:tensorflow:global_step/sec: 247.127\n", + "INFO:tensorflow:loss = 0.0320206, step = 9401\n", + "INFO:tensorflow:global_step/sec: 252.933\n", + "INFO:tensorflow:loss = 0.00869709, step = 9501\n", + "INFO:tensorflow:global_step/sec: 250.09\n", + "INFO:tensorflow:loss = 0.00985262, step = 9601\n", + "INFO:tensorflow:global_step/sec: 250.711\n", + "INFO:tensorflow:loss = 0.0031784, step = 9701\n", + "INFO:tensorflow:global_step/sec: 178.246\n", + "INFO:tensorflow:loss = 0.00425218, step = 9801\n", + "INFO:tensorflow:global_step/sec: 155.539\n", + "INFO:tensorflow:loss = 0.00946152, step = 9901\n", + "INFO:tensorflow:global_step/sec: 225.532\n", + "INFO:tensorflow:loss = 0.0200995, step = 10001\n", + "INFO:tensorflow:global_step/sec: 226.505\n", + "INFO:tensorflow:loss = 0.00739148, step = 10101\n", + "INFO:tensorflow:global_step/sec: 241.791\n", + "INFO:tensorflow:loss = 0.0152016, step = 10201\n", + "INFO:tensorflow:global_step/sec: 241.861\n", + "INFO:tensorflow:loss = 0.005831, step = 10301\n", + "INFO:tensorflow:global_step/sec: 252.924\n", + "INFO:tensorflow:loss = 0.00450662, step = 10401\n", + "INFO:tensorflow:global_step/sec: 244.221\n", + "INFO:tensorflow:loss = 0.00301706, step = 10501\n", + "INFO:tensorflow:global_step/sec: 244.852\n", + "INFO:tensorflow:loss = 0.0107337, step = 10601\n", + "INFO:tensorflow:global_step/sec: 250.175\n", + "INFO:tensorflow:loss = 0.0145845, step = 10701\n", + "INFO:tensorflow:global_step/sec: 245.781\n", + "INFO:tensorflow:loss = 0.008441, step = 10801\n", + "INFO:tensorflow:global_step/sec: 248.631\n", + "INFO:tensorflow:loss = 0.000870229, step = 10901\n", + "INFO:tensorflow:global_step/sec: 250.852\n", + "INFO:tensorflow:loss = 0.0385219, step = 11001\n", + "INFO:tensorflow:global_step/sec: 247.528\n", + "INFO:tensorflow:loss = 0.0114916, step = 11101\n", + "INFO:tensorflow:global_step/sec: 250.542\n", + "INFO:tensorflow:loss = 0.000968566, step = 11201\n", + "INFO:tensorflow:global_step/sec: 241.787\n", + "INFO:tensorflow:loss = 0.0043037, step = 11301\n", + "INFO:tensorflow:global_step/sec: 248.603\n", + "INFO:tensorflow:loss = 0.0115999, step = 11401\n", + "INFO:tensorflow:global_step/sec: 233.728\n", + "INFO:tensorflow:loss = 0.0150273, step = 11501\n", + "INFO:tensorflow:global_step/sec: 223.48\n", + "INFO:tensorflow:loss = 0.000502977, step = 11601\n", + "INFO:tensorflow:global_step/sec: 224.879\n", + "INFO:tensorflow:loss = 0.00806901, step = 11701\n", + "INFO:tensorflow:global_step/sec: 224.185\n", + "INFO:tensorflow:loss = 0.000386931, step = 11801\n", + "INFO:tensorflow:global_step/sec: 222.32\n", + "INFO:tensorflow:loss = 0.00565369, step = 11901\n", + "INFO:tensorflow:global_step/sec: 219.261\n", + "INFO:tensorflow:loss = 0.000363288, step = 12001\n", + "INFO:tensorflow:global_step/sec: 218.833\n", + "INFO:tensorflow:loss = 0.00157113, step = 12101\n", + "INFO:tensorflow:global_step/sec: 216.566\n", + "INFO:tensorflow:loss = 0.00435414, step = 12201\n", + "INFO:tensorflow:global_step/sec: 219.818\n", + "INFO:tensorflow:loss = 0.00612552, step = 12301\n", + "INFO:tensorflow:global_step/sec: 222.551\n", + "INFO:tensorflow:loss = 0.000404168, step = 12401\n", + "INFO:tensorflow:global_step/sec: 221.108\n", + "INFO:tensorflow:loss = 0.0043108, step = 12501\n", + "INFO:tensorflow:global_step/sec: 228.263\n", + "INFO:tensorflow:loss = 0.00240749, step = 12601\n", + "INFO:tensorflow:global_step/sec: 219.129\n", + "INFO:tensorflow:loss = 0.00484132, step = 12701\n", + "INFO:tensorflow:global_step/sec: 220.544\n", + "INFO:tensorflow:loss = 0.0127916, step = 12801\n", + "INFO:tensorflow:global_step/sec: 218.076\n", + "INFO:tensorflow:loss = 0.00223205, step = 12901\n", + "INFO:tensorflow:global_step/sec: 224.567\n", + "INFO:tensorflow:loss = 0.0039482, step = 13001\n", + "INFO:tensorflow:global_step/sec: 218.085\n", + "INFO:tensorflow:loss = 0.00321868, step = 13101\n", + "INFO:tensorflow:global_step/sec: 220.348\n", + "INFO:tensorflow:loss = 0.00371133, step = 13201\n", + "INFO:tensorflow:global_step/sec: 212.185\n", + "INFO:tensorflow:loss = 0.00603448, step = 13301\n", + "INFO:tensorflow:global_step/sec: 219.132\n", + "INFO:tensorflow:loss = 0.0144509, step = 13401\n", + "INFO:tensorflow:global_step/sec: 222.004\n", + "INFO:tensorflow:loss = 0.0059841, step = 13501\n", + "INFO:tensorflow:global_step/sec: 224.662\n", + "INFO:tensorflow:loss = 0.00675491, step = 13601\n", + "INFO:tensorflow:global_step/sec: 197.622\n", + "INFO:tensorflow:loss = 0.0027232, step = 13701\n", + "INFO:tensorflow:global_step/sec: 173.053\n", + "INFO:tensorflow:loss = 0.00599961, step = 13801\n", + "INFO:tensorflow:global_step/sec: 173.466\n", + "INFO:tensorflow:loss = 0.00239148, step = 13901\n", + "INFO:tensorflow:global_step/sec: 171.589\n", + "INFO:tensorflow:loss = 0.00144705, step = 14001\n", + "INFO:tensorflow:global_step/sec: 197.774\n", + "INFO:tensorflow:loss = 0.00947546, step = 14101\n", + "INFO:tensorflow:global_step/sec: 198.875\n", + "INFO:tensorflow:loss = 0.00801135, step = 14201\n", + "INFO:tensorflow:global_step/sec: 199.875\n", + "INFO:tensorflow:loss = 0.00108079, step = 14301\n", + "INFO:tensorflow:global_step/sec: 203.297\n", + "INFO:tensorflow:loss = 0.00081179, step = 14401\n", + "INFO:tensorflow:global_step/sec: 202.201\n", + "INFO:tensorflow:loss = 0.000734463, step = 14501\n", + "INFO:tensorflow:global_step/sec: 201.753\n", + "INFO:tensorflow:loss = 0.00964704, step = 14601\n", + "INFO:tensorflow:global_step/sec: 196.616\n", + "INFO:tensorflow:loss = 0.000924671, step = 14701\n", + "INFO:tensorflow:global_step/sec: 202.897\n", + "INFO:tensorflow:loss = 0.000975085, step = 14801\n", + "INFO:tensorflow:global_step/sec: 197.398\n", + "INFO:tensorflow:loss = 0.00225048, step = 14901\n", + "INFO:tensorflow:global_step/sec: 199.475\n", + "INFO:tensorflow:loss = 0.000493091, step = 15001\n", + "INFO:tensorflow:global_step/sec: 203.727\n", + "INFO:tensorflow:loss = 0.00273843, step = 15101\n", + "INFO:tensorflow:global_step/sec: 202.021\n", + "INFO:tensorflow:loss = 0.00102185, step = 15201\n", + "INFO:tensorflow:global_step/sec: 203.306\n", + "INFO:tensorflow:loss = 0.00109643, step = 15301\n", + "INFO:tensorflow:global_step/sec: 218.769\n", + "INFO:tensorflow:loss = 0.00099506, step = 15401\n", + "INFO:tensorflow:global_step/sec: 221.231\n", + "INFO:tensorflow:loss = 0.00527221, step = 15501\n", + "INFO:tensorflow:global_step/sec: 225.913\n", + "INFO:tensorflow:loss = 0.00468541, step = 15601\n", + "INFO:tensorflow:global_step/sec: 222.539\n", + "INFO:tensorflow:loss = 0.0115757, step = 15701\n", + "INFO:tensorflow:global_step/sec: 214.032\n", + "INFO:tensorflow:loss = 0.000994101, step = 15801\n", + "INFO:tensorflow:global_step/sec: 227.299\n", + "INFO:tensorflow:loss = 0.000663049, step = 15901\n", + "INFO:tensorflow:global_step/sec: 221.371\n", + "INFO:tensorflow:loss = 0.00550774, step = 16001\n", + "INFO:tensorflow:global_step/sec: 221.877\n", + "INFO:tensorflow:loss = 0.00454118, step = 16101\n", + "INFO:tensorflow:global_step/sec: 222.341\n", + "INFO:tensorflow:loss = 6.5705e-05, step = 16201\n", + "INFO:tensorflow:global_step/sec: 250.887\n", + "INFO:tensorflow:loss = 0.00299656, step = 16301\n", + "INFO:tensorflow:global_step/sec: 245.627\n", + "INFO:tensorflow:loss = 0.00176672, step = 16401\n", + "INFO:tensorflow:global_step/sec: 248.53\n", + "INFO:tensorflow:loss = 0.00186204, step = 16501\n", + "INFO:tensorflow:global_step/sec: 250.174\n", + "INFO:tensorflow:loss = 0.00217391, step = 16601\n", + "INFO:tensorflow:global_step/sec: 240.957\n", + "INFO:tensorflow:loss = 0.00271636, step = 16701\n", + "INFO:tensorflow:global_step/sec: 247.992\n", + "INFO:tensorflow:loss = 0.00198975, step = 16801\n", + "INFO:tensorflow:global_step/sec: 245.091\n", + "INFO:tensorflow:loss = 0.00237977, step = 16901\n", + "INFO:tensorflow:global_step/sec: 249.102\n", + "INFO:tensorflow:loss = 0.00455543, step = 17001\n", + "INFO:tensorflow:global_step/sec: 253.652\n", + "INFO:tensorflow:loss = 0.000879103, step = 17101\n", + "INFO:tensorflow:global_step/sec: 239.679\n", + "INFO:tensorflow:loss = 0.00226957, step = 17201\n", + "INFO:tensorflow:global_step/sec: 226.454\n", + "INFO:tensorflow:loss = 0.00136685, step = 17301\n", + "INFO:tensorflow:global_step/sec: 222.099\n", + "INFO:tensorflow:loss = 0.00146913, step = 17401\n", + "INFO:tensorflow:global_step/sec: 219.209\n", + "INFO:tensorflow:loss = 0.00118623, step = 17501\n", + "INFO:tensorflow:global_step/sec: 223.162\n", + "INFO:tensorflow:loss = 0.000321646, step = 17601\n", + "INFO:tensorflow:global_step/sec: 223.696\n", + "INFO:tensorflow:loss = 0.00103467, step = 17701\n", + "INFO:tensorflow:global_step/sec: 222.309\n", + "INFO:tensorflow:loss = 0.000512657, step = 17801\n", + "INFO:tensorflow:global_step/sec: 222.265\n", + "INFO:tensorflow:loss = 0.00254291, step = 17901\n", + "INFO:tensorflow:global_step/sec: 222.621\n", + "INFO:tensorflow:loss = 0.000439994, step = 18001\n", + "INFO:tensorflow:global_step/sec: 213.274\n", + "INFO:tensorflow:loss = 0.00133925, step = 18101\n", + "INFO:tensorflow:global_step/sec: 225.978\n", + "INFO:tensorflow:loss = 0.00390742, step = 18201\n", + "INFO:tensorflow:global_step/sec: 221.529\n", + "INFO:tensorflow:loss = 0.0088991, step = 18301\n", + "INFO:tensorflow:global_step/sec: 225.213\n", + "INFO:tensorflow:loss = 0.00297377, step = 18401\n", + "INFO:tensorflow:global_step/sec: 219.55\n", + "INFO:tensorflow:loss = 0.00228189, step = 18501\n", + "INFO:tensorflow:global_step/sec: 213.269\n", + "INFO:tensorflow:loss = 0.00385677, step = 18601\n", + "INFO:tensorflow:global_step/sec: 219.882\n", + "INFO:tensorflow:loss = 0.0015286, step = 18701\n", + "INFO:tensorflow:global_step/sec: 209.596\n", + "INFO:tensorflow:loss = 0.00284093, step = 18801\n", + "INFO:tensorflow:global_step/sec: 212.419\n", + "INFO:tensorflow:loss = 0.00266602, step = 18901\n", + "INFO:tensorflow:global_step/sec: 227.252\n", + "INFO:tensorflow:loss = 0.000786861, step = 19001\n", + "INFO:tensorflow:global_step/sec: 246.067\n", + "INFO:tensorflow:loss = 0.000335497, step = 19101\n", + "INFO:tensorflow:global_step/sec: 232.593\n", + "INFO:tensorflow:loss = 0.000921562, step = 19201\n", + "INFO:tensorflow:global_step/sec: 164.406\n", + "INFO:tensorflow:loss = 0.007462, step = 19301\n", + "INFO:tensorflow:global_step/sec: 201.899\n", + "INFO:tensorflow:loss = 0.000464647, step = 19401\n", + "INFO:tensorflow:global_step/sec: 192.669\n", + "INFO:tensorflow:loss = 0.0026026, step = 19501\n", + "INFO:tensorflow:global_step/sec: 173.811\n", + "INFO:tensorflow:loss = 0.0003197, step = 19601\n", + "INFO:tensorflow:global_step/sec: 192.081\n", + "INFO:tensorflow:loss = 8.24519e-05, step = 19701\n", + "INFO:tensorflow:global_step/sec: 212.942\n", + "INFO:tensorflow:loss = 0.000531701, step = 19801\n", + "INFO:tensorflow:global_step/sec: 224.567\n", + "INFO:tensorflow:loss = 0.00136314, step = 19901\n", + "INFO:tensorflow:global_step/sec: 133.936\n", + "INFO:tensorflow:loss = 0.00202061, step = 20001\n", + "INFO:tensorflow:global_step/sec: 130.557\n", + "INFO:tensorflow:loss = 0.000579102, step = 20101\n", + "INFO:tensorflow:global_step/sec: 125.301\n", + "INFO:tensorflow:loss = 0.00300941, step = 20201\n", + "INFO:tensorflow:global_step/sec: 115.551\n", + "INFO:tensorflow:loss = 0.00112481, step = 20301\n", + "INFO:tensorflow:global_step/sec: 131.251\n", + "INFO:tensorflow:loss = 0.000193757, step = 20401\n", + "INFO:tensorflow:global_step/sec: 132.814\n", + "INFO:tensorflow:loss = 0.000290382, step = 20501\n", + "INFO:tensorflow:global_step/sec: 123.171\n", + "INFO:tensorflow:loss = 0.00121122, step = 20601\n", + "INFO:tensorflow:global_step/sec: 175.92\n", + "INFO:tensorflow:loss = 0.00088932, step = 20701\n", + "INFO:tensorflow:global_step/sec: 167.949\n", + "INFO:tensorflow:loss = 0.00140518, step = 20801\n", + "INFO:tensorflow:global_step/sec: 196.227\n", + "INFO:tensorflow:loss = 0.000813194, step = 20901\n", + "INFO:tensorflow:global_step/sec: 202.38\n", + "INFO:tensorflow:loss = 0.00233443, step = 21001\n", + "INFO:tensorflow:global_step/sec: 202.112\n", + "INFO:tensorflow:loss = 0.0012099, step = 21101\n", + "INFO:tensorflow:global_step/sec: 219.88\n", + "INFO:tensorflow:loss = 0.00447898, step = 21201\n", + "INFO:tensorflow:global_step/sec: 203.289\n", + "INFO:tensorflow:loss = 0.00124133, step = 21301\n", + "INFO:tensorflow:global_step/sec: 219.2\n", + "INFO:tensorflow:loss = 0.00191285, step = 21401\n", + "INFO:tensorflow:global_step/sec: 220.707\n", + "INFO:tensorflow:loss = 0.000466406, step = 21501\n", + "INFO:tensorflow:global_step/sec: 222.47\n", + "INFO:tensorflow:loss = 0.000663659, step = 21601\n", + "INFO:tensorflow:global_step/sec: 224.897\n", + "INFO:tensorflow:loss = 0.000965006, step = 21701\n", + "INFO:tensorflow:global_step/sec: 217.626\n", + "INFO:tensorflow:loss = 0.000571798, step = 21801\n", + "INFO:tensorflow:global_step/sec: 225.879\n", + "INFO:tensorflow:loss = 0.000650687, step = 21901\n", + "INFO:tensorflow:global_step/sec: 217.328\n", + "INFO:tensorflow:loss = 0.000145654, step = 22001\n", + "INFO:tensorflow:global_step/sec: 226.469\n", + "INFO:tensorflow:loss = 0.000195093, step = 22101\n", + "INFO:tensorflow:global_step/sec: 221.064\n", + "INFO:tensorflow:loss = 0.00157508, step = 22201\n", + "INFO:tensorflow:global_step/sec: 194.716\n", + "INFO:tensorflow:loss = 0.00294935, step = 22301\n", + "INFO:tensorflow:global_step/sec: 195.736\n", + "INFO:tensorflow:loss = 0.001912, step = 22401\n", + "INFO:tensorflow:global_step/sec: 195.879\n", + "INFO:tensorflow:loss = 0.000832729, step = 22501\n", + "INFO:tensorflow:global_step/sec: 169.578\n", + "INFO:tensorflow:loss = 0.00274704, step = 22601\n", + "INFO:tensorflow:global_step/sec: 150.659\n", + "INFO:tensorflow:loss = 0.00081313, step = 22701\n", + "INFO:tensorflow:global_step/sec: 143.218\n", + "INFO:tensorflow:loss = 0.000624607, step = 22801\n", + "INFO:tensorflow:global_step/sec: 140.29\n", + "INFO:tensorflow:loss = 0.00217949, step = 22901\n", + "INFO:tensorflow:global_step/sec: 151.139\n", + "INFO:tensorflow:loss = 0.000891173, step = 23001\n", + "INFO:tensorflow:global_step/sec: 241.921\n", + "INFO:tensorflow:loss = 0.00390463, step = 23101\n", + "INFO:tensorflow:global_step/sec: 193.533\n", + "INFO:tensorflow:loss = 0.00274365, step = 23201\n", + "INFO:tensorflow:global_step/sec: 139.673\n", + "INFO:tensorflow:loss = 0.00244988, step = 23301\n", + "INFO:tensorflow:global_step/sec: 127.433\n", + "INFO:tensorflow:loss = 0.000624292, step = 23401\n", + "INFO:tensorflow:global_step/sec: 167.768\n", + "INFO:tensorflow:loss = 0.000631158, step = 23501\n", + "INFO:tensorflow:global_step/sec: 212.679\n", + "INFO:tensorflow:loss = 0.00055499, step = 23601\n", + "INFO:tensorflow:global_step/sec: 215.224\n", + "INFO:tensorflow:loss = 0.000339098, step = 23701\n", + "INFO:tensorflow:global_step/sec: 216.112\n", + "INFO:tensorflow:loss = 0.00114711, step = 23801\n", + "INFO:tensorflow:global_step/sec: 202.485\n", + "INFO:tensorflow:loss = 0.0016139, step = 23901\n", + "INFO:tensorflow:global_step/sec: 217.558\n", + "INFO:tensorflow:loss = 0.000408336, step = 24001\n", + "INFO:tensorflow:global_step/sec: 212.719\n", + "INFO:tensorflow:loss = 0.000898319, step = 24101\n", + "INFO:tensorflow:global_step/sec: 215.823\n", + "INFO:tensorflow:loss = 0.00175749, step = 24201\n", + "INFO:tensorflow:global_step/sec: 220.661\n", + "INFO:tensorflow:loss = 0.00015739, step = 24301\n", + "INFO:tensorflow:global_step/sec: 209.216\n", + "INFO:tensorflow:loss = 0.00259422, step = 24401\n", + "INFO:tensorflow:global_step/sec: 213.822\n", + "INFO:tensorflow:loss = 0.00096173, step = 24501\n", + "INFO:tensorflow:global_step/sec: 186.595\n", + "INFO:tensorflow:loss = 0.00063238, step = 24601\n", + "INFO:tensorflow:global_step/sec: 144.669\n", + "INFO:tensorflow:loss = 0.00057392, step = 24701\n", + "INFO:tensorflow:global_step/sec: 152.366\n", + "INFO:tensorflow:loss = 0.00121459, step = 24801\n", + "INFO:tensorflow:global_step/sec: 174.895\n", + "INFO:tensorflow:loss = 0.00128009, step = 24901\n", + "INFO:tensorflow:global_step/sec: 174.756\n", + "INFO:tensorflow:loss = 0.000494892, step = 25001\n", + "INFO:tensorflow:global_step/sec: 172.246\n", + "INFO:tensorflow:loss = 0.000652375, step = 25101\n", + "INFO:tensorflow:global_step/sec: 175.405\n", + "INFO:tensorflow:loss = 0.00142389, step = 25201\n", + "INFO:tensorflow:global_step/sec: 177.185\n", + "INFO:tensorflow:loss = 0.000164492, step = 25301\n", + "INFO:tensorflow:global_step/sec: 206.164\n", + "INFO:tensorflow:loss = 0.000561076, step = 25401\n", + "INFO:tensorflow:global_step/sec: 196.853\n", + "INFO:tensorflow:loss = 0.000957897, step = 25501\n", + "INFO:tensorflow:global_step/sec: 207.245\n", + "INFO:tensorflow:loss = 0.000952798, step = 25601\n", + "INFO:tensorflow:global_step/sec: 175.923\n", + "INFO:tensorflow:loss = 0.000784664, step = 25701\n", + "INFO:tensorflow:global_step/sec: 163.915\n", + "INFO:tensorflow:loss = 0.000907174, step = 25801\n", + "INFO:tensorflow:global_step/sec: 202.086\n", + "INFO:tensorflow:loss = 0.00168781, step = 25901\n", + "INFO:tensorflow:global_step/sec: 203.587\n", + "INFO:tensorflow:loss = 0.000104824, step = 26001\n", + "INFO:tensorflow:global_step/sec: 209.885\n", + "INFO:tensorflow:loss = 0.000690419, step = 26101\n", + "INFO:tensorflow:global_step/sec: 226.35\n", + "INFO:tensorflow:loss = 0.00103272, step = 26201\n", + "INFO:tensorflow:global_step/sec: 224.379\n", + "INFO:tensorflow:loss = 0.000976912, step = 26301\n", + "INFO:tensorflow:global_step/sec: 228.713\n", + "INFO:tensorflow:loss = 0.00152238, step = 26401\n", + "INFO:tensorflow:global_step/sec: 226.491\n", + "INFO:tensorflow:loss = 0.00039652, step = 26501\n", + "INFO:tensorflow:global_step/sec: 220.675\n", + "INFO:tensorflow:loss = 0.000678569, step = 26601\n", + "INFO:tensorflow:global_step/sec: 217.117\n", + "INFO:tensorflow:loss = 4.83376e-05, step = 26701\n", + "INFO:tensorflow:global_step/sec: 229.967\n", + "INFO:tensorflow:loss = 0.000343526, step = 26801\n", + "INFO:tensorflow:global_step/sec: 225.69\n", + "INFO:tensorflow:loss = 0.000502717, step = 26901\n", + "INFO:tensorflow:global_step/sec: 193.85\n", + "INFO:tensorflow:loss = 0.000601708, step = 27001\n", + "INFO:tensorflow:global_step/sec: 229.012\n", + "INFO:tensorflow:loss = 0.000526853, step = 27101\n", + "INFO:tensorflow:global_step/sec: 213.665\n", + "INFO:tensorflow:loss = 0.000572055, step = 27201\n", + "INFO:tensorflow:global_step/sec: 209.167\n", + "INFO:tensorflow:loss = 0.00139602, step = 27301\n", + "INFO:tensorflow:global_step/sec: 219.407\n", + "INFO:tensorflow:loss = 0.000124362, step = 27401\n", + "INFO:tensorflow:global_step/sec: 228.511\n", + "INFO:tensorflow:loss = 0.00109078, step = 27501\n", + "INFO:tensorflow:global_step/sec: 213.144\n", + "INFO:tensorflow:loss = 0.000855066, step = 27601\n", + "INFO:tensorflow:global_step/sec: 218.503\n", + "INFO:tensorflow:loss = 0.000256398, step = 27701\n", + "INFO:tensorflow:global_step/sec: 219.416\n", + "INFO:tensorflow:loss = 0.000580438, step = 27801\n", + "INFO:tensorflow:global_step/sec: 226.393\n", + "INFO:tensorflow:loss = 0.000888619, step = 27901\n", + "INFO:tensorflow:global_step/sec: 253.367\n", + "INFO:tensorflow:loss = 0.00165073, step = 28001\n", + "INFO:tensorflow:global_step/sec: 251.191\n", + "INFO:tensorflow:loss = 0.00077614, step = 28101\n", + "INFO:tensorflow:global_step/sec: 242.37\n", + "INFO:tensorflow:loss = 0.000606156, step = 28201\n", + "INFO:tensorflow:global_step/sec: 248.664\n", + "INFO:tensorflow:loss = 0.000895309, step = 28301\n", + "INFO:tensorflow:global_step/sec: 255.741\n", + "INFO:tensorflow:loss = 0.000701728, step = 28401\n", + "INFO:tensorflow:global_step/sec: 236.818\n", + "INFO:tensorflow:loss = 0.000128898, step = 28501\n", + "INFO:tensorflow:global_step/sec: 247.318\n", + "INFO:tensorflow:loss = 0.0001886, step = 28601\n", + "INFO:tensorflow:global_step/sec: 250.678\n", + "INFO:tensorflow:loss = 0.00096269, step = 28701\n", + "INFO:tensorflow:global_step/sec: 245.647\n", + "INFO:tensorflow:loss = 0.00105206, step = 28801\n", + "INFO:tensorflow:global_step/sec: 221.274\n", + "INFO:tensorflow:loss = 0.000268267, step = 28901\n", + "INFO:tensorflow:global_step/sec: 227.845\n", + "INFO:tensorflow:loss = 0.00168694, step = 29001\n", + "INFO:tensorflow:global_step/sec: 223.859\n", + "INFO:tensorflow:loss = 0.00110313, step = 29101\n", + "INFO:tensorflow:global_step/sec: 221.472\n", + "INFO:tensorflow:loss = 0.00159099, step = 29201\n", + "INFO:tensorflow:global_step/sec: 222.633\n", + "INFO:tensorflow:loss = 0.00158097, step = 29301\n", + "INFO:tensorflow:global_step/sec: 222.882\n", + "INFO:tensorflow:loss = 0.00154527, step = 29401\n", + "INFO:tensorflow:global_step/sec: 203.567\n", + "INFO:tensorflow:loss = 0.00123796, step = 29501\n", + "INFO:tensorflow:global_step/sec: 203.555\n", + "INFO:tensorflow:loss = 0.000219997, step = 29601\n", + "INFO:tensorflow:global_step/sec: 222.119\n", + "INFO:tensorflow:loss = 9.3096e-05, step = 29701\n", + "INFO:tensorflow:global_step/sec: 222.823\n", + "INFO:tensorflow:loss = 0.000455586, step = 29801\n", + "INFO:tensorflow:global_step/sec: 223.143\n", + "INFO:tensorflow:loss = 0.000910388, step = 29901\n", + "INFO:tensorflow:global_step/sec: 222.494\n", + "INFO:tensorflow:loss = 0.000136834, step = 30001\n", + "INFO:tensorflow:global_step/sec: 206.077\n", + "INFO:tensorflow:loss = 0.00103797, step = 30101\n", + "INFO:tensorflow:global_step/sec: 216.847\n", + "INFO:tensorflow:loss = 0.000433273, step = 30201\n", + "INFO:tensorflow:global_step/sec: 228.443\n", + "INFO:tensorflow:loss = 0.000948461, step = 30301\n", + "INFO:tensorflow:global_step/sec: 184.656\n", + "INFO:tensorflow:loss = 0.00149153, step = 30401\n", + "INFO:tensorflow:global_step/sec: 172.113\n", + "INFO:tensorflow:loss = 0.00108908, step = 30501\n", + "INFO:tensorflow:global_step/sec: 174.156\n", + "INFO:tensorflow:loss = 0.00132978, step = 30601\n", + "INFO:tensorflow:global_step/sec: 175.028\n", + "INFO:tensorflow:loss = 0.00101348, step = 30701\n", + "INFO:tensorflow:global_step/sec: 176.614\n", + "INFO:tensorflow:loss = 0.000972399, step = 30801\n", + "INFO:tensorflow:global_step/sec: 166.519\n", + "INFO:tensorflow:loss = 0.00108417, step = 30901\n", + "INFO:tensorflow:global_step/sec: 176.128\n", + "INFO:tensorflow:loss = 0.00116226, step = 31001\n", + "INFO:tensorflow:global_step/sec: 192.185\n", + "INFO:tensorflow:loss = 0.00123486, step = 31101\n", + "INFO:tensorflow:global_step/sec: 204.961\n", + "INFO:tensorflow:loss = 0.000454989, step = 31201\n", + "INFO:tensorflow:global_step/sec: 196.908\n", + "INFO:tensorflow:loss = 0.00047457, step = 31301\n", + "INFO:tensorflow:global_step/sec: 202.095\n", + "INFO:tensorflow:loss = 0.00092365, step = 31401\n", + "INFO:tensorflow:global_step/sec: 207.113\n", + "INFO:tensorflow:loss = 0.000283516, step = 31501\n", + "INFO:tensorflow:global_step/sec: 206.36\n", + "INFO:tensorflow:loss = 8.1612e-05, step = 31601\n", + "INFO:tensorflow:global_step/sec: 202.344\n", + "INFO:tensorflow:loss = 0.000638481, step = 31701\n", + "INFO:tensorflow:global_step/sec: 197.21\n", + "INFO:tensorflow:loss = 0.000208251, step = 31801\n", + "INFO:tensorflow:global_step/sec: 217.532\n", + "INFO:tensorflow:loss = 0.000799432, step = 31901\n", + "INFO:tensorflow:global_step/sec: 210.115\n", + "INFO:tensorflow:loss = 0.000196637, step = 32001\n", + "INFO:tensorflow:global_step/sec: 217.303\n", + "INFO:tensorflow:loss = 0.000395417, step = 32101\n", + "INFO:tensorflow:global_step/sec: 229.732\n", + "INFO:tensorflow:loss = 0.00127422, step = 32201\n", + "INFO:tensorflow:global_step/sec: 214.444\n", + "INFO:tensorflow:loss = 0.000320352, step = 32301\n", + "INFO:tensorflow:global_step/sec: 220.418\n", + "INFO:tensorflow:loss = 0.000127237, step = 32401\n", + "INFO:tensorflow:global_step/sec: 228.064\n", + "INFO:tensorflow:loss = 0.000640732, step = 32501\n", + "INFO:tensorflow:global_step/sec: 221.788\n", + "INFO:tensorflow:loss = 0.000122039, step = 32601\n", + "INFO:tensorflow:global_step/sec: 225.677\n", + "INFO:tensorflow:loss = 0.000924701, step = 32701\n", + "INFO:tensorflow:global_step/sec: 234.225\n", + "INFO:tensorflow:loss = 0.000954173, step = 32801\n", + "INFO:tensorflow:global_step/sec: 253.279\n", + "INFO:tensorflow:loss = 0.000642773, step = 32901\n", + "INFO:tensorflow:global_step/sec: 252.763\n", + "INFO:tensorflow:loss = 0.000546381, step = 33001\n", + "INFO:tensorflow:global_step/sec: 259.948\n", + "INFO:tensorflow:loss = 0.00167006, step = 33101\n", + "INFO:tensorflow:global_step/sec: 256.835\n", + "INFO:tensorflow:loss = 0.000996035, step = 33201\n", + "INFO:tensorflow:global_step/sec: 252.823\n", + "INFO:tensorflow:loss = 0.000129591, step = 33301\n", + "INFO:tensorflow:global_step/sec: 256.189\n", + "INFO:tensorflow:loss = 0.000786503, step = 33401\n", + "INFO:tensorflow:global_step/sec: 256.643\n", + "INFO:tensorflow:loss = 0.00016885, step = 33501\n", + "INFO:tensorflow:global_step/sec: 249.535\n", + "INFO:tensorflow:loss = 0.000828449, step = 33601\n", + "INFO:tensorflow:global_step/sec: 255.976\n", + "INFO:tensorflow:loss = 0.000697898, step = 33701\n", + "INFO:tensorflow:global_step/sec: 259.514\n", + "INFO:tensorflow:loss = 0.000795015, step = 33801\n", + "INFO:tensorflow:global_step/sec: 241.978\n", + "INFO:tensorflow:loss = 0.00110586, step = 33901\n", + "INFO:tensorflow:global_step/sec: 258.384\n", + "INFO:tensorflow:loss = 0.000736455, step = 34001\n", + "INFO:tensorflow:global_step/sec: 249.197\n", + "INFO:tensorflow:loss = 0.000609881, step = 34101\n", + "INFO:tensorflow:global_step/sec: 208.475\n", + "INFO:tensorflow:loss = 0.00112126, step = 34201\n", + "INFO:tensorflow:global_step/sec: 218.013\n", + "INFO:tensorflow:loss = 0.000172698, step = 34301\n", + "INFO:tensorflow:global_step/sec: 228.062\n", + "INFO:tensorflow:loss = 0.000639106, step = 34401\n", + "INFO:tensorflow:global_step/sec: 224.503\n", + "INFO:tensorflow:loss = 0.000682767, step = 34501\n", + "INFO:tensorflow:global_step/sec: 221.874\n", + "INFO:tensorflow:loss = 0.000590395, step = 34601\n", + "INFO:tensorflow:global_step/sec: 220.975\n", + "INFO:tensorflow:loss = 0.00183083, step = 34701\n", + "INFO:tensorflow:global_step/sec: 211.296\n", + "INFO:tensorflow:loss = 0.00064613, step = 34801\n", + "INFO:tensorflow:global_step/sec: 219.584\n", + "INFO:tensorflow:loss = 0.000506961, step = 34901\n", + "INFO:tensorflow:global_step/sec: 202.945\n", + "INFO:tensorflow:loss = 0.000376796, step = 35001\n", + "INFO:tensorflow:global_step/sec: 161.128\n", + "INFO:tensorflow:loss = 0.000649564, step = 35101\n", + "INFO:tensorflow:global_step/sec: 170.543\n", + "INFO:tensorflow:loss = 0.000365507, step = 35201\n", + "INFO:tensorflow:global_step/sec: 187.648\n", + "INFO:tensorflow:loss = 0.000325794, step = 35301\n", + "INFO:tensorflow:global_step/sec: 208.011\n", + "INFO:tensorflow:loss = 0.00102065, step = 35401\n", + "INFO:tensorflow:global_step/sec: 201.43\n", + "INFO:tensorflow:loss = 0.000226456, step = 35501\n", + "INFO:tensorflow:global_step/sec: 202.46\n", + "INFO:tensorflow:loss = 0.000174838, step = 35601\n", + "INFO:tensorflow:global_step/sec: 201.411\n", + "INFO:tensorflow:loss = 0.000776101, step = 35701\n", + "INFO:tensorflow:global_step/sec: 205.301\n", + "INFO:tensorflow:loss = 0.000510848, step = 35801\n", + "INFO:tensorflow:global_step/sec: 201.897\n", + "INFO:tensorflow:loss = 0.000446139, step = 35901\n", + "INFO:tensorflow:global_step/sec: 203.072\n", + "INFO:tensorflow:loss = 0.000303391, step = 36001\n", + "INFO:tensorflow:global_step/sec: 210.629\n", + "INFO:tensorflow:loss = 0.00122339, step = 36101\n", + "INFO:tensorflow:global_step/sec: 221.421\n", + "INFO:tensorflow:loss = 0.000596962, step = 36201\n", + "INFO:tensorflow:global_step/sec: 219.066\n", + "INFO:tensorflow:loss = 0.000169634, step = 36301\n", + "INFO:tensorflow:global_step/sec: 222.964\n", + "INFO:tensorflow:loss = 0.000808914, step = 36401\n", + "INFO:tensorflow:global_step/sec: 221.649\n", + "INFO:tensorflow:loss = 0.0001687, step = 36501\n", + "INFO:tensorflow:global_step/sec: 214.763\n", + "INFO:tensorflow:loss = 0.000135252, step = 36601\n", + "INFO:tensorflow:global_step/sec: 225.411\n", + "INFO:tensorflow:loss = 0.000231627, step = 36701\n", + "INFO:tensorflow:global_step/sec: 222.832\n", + "INFO:tensorflow:loss = 0.000907288, step = 36801\n", + "INFO:tensorflow:global_step/sec: 224.827\n", + "INFO:tensorflow:loss = 0.00058429, step = 36901\n", + "INFO:tensorflow:global_step/sec: 244.201\n", + "INFO:tensorflow:loss = 0.000721054, step = 37001\n", + "INFO:tensorflow:global_step/sec: 238.205\n", + "INFO:tensorflow:loss = 0.000285423, step = 37101\n", + "INFO:tensorflow:global_step/sec: 222.531\n", + "INFO:tensorflow:loss = 0.000330493, step = 37201\n", + "INFO:tensorflow:global_step/sec: 221.661\n", + "INFO:tensorflow:loss = 0.000599393, step = 37301\n", + "INFO:tensorflow:global_step/sec: 220.455\n", + "INFO:tensorflow:loss = 0.000201867, step = 37401\n", + "INFO:tensorflow:global_step/sec: 224.484\n", + "INFO:tensorflow:loss = 0.00018047, step = 37501\n", + "INFO:tensorflow:global_step/sec: 221.584\n", + "INFO:tensorflow:loss = 0.000454654, step = 37601\n", + "INFO:tensorflow:global_step/sec: 223.15\n", + "INFO:tensorflow:loss = 0.00014325, step = 37701\n", + "INFO:tensorflow:global_step/sec: 221.338\n", + "INFO:tensorflow:loss = 0.000284938, step = 37801\n", + "INFO:tensorflow:global_step/sec: 219.213\n", + "INFO:tensorflow:loss = 0.000899544, step = 37901\n", + "INFO:tensorflow:global_step/sec: 222.322\n", + "INFO:tensorflow:loss = 0.000259325, step = 38001\n", + "INFO:tensorflow:global_step/sec: 219.983\n", + "INFO:tensorflow:loss = 0.000650089, step = 38101\n", + "INFO:tensorflow:global_step/sec: 223.19\n", + "INFO:tensorflow:loss = 0.000674867, step = 38201\n", + "INFO:tensorflow:global_step/sec: 222.408\n", + "INFO:tensorflow:loss = 0.000212536, step = 38301\n", + "INFO:tensorflow:global_step/sec: 226.471\n", + "INFO:tensorflow:loss = 0.000212651, step = 38401\n", + "INFO:tensorflow:global_step/sec: 204.517\n", + "INFO:tensorflow:loss = 0.000693711, step = 38501\n", + "INFO:tensorflow:global_step/sec: 176.364\n", + "INFO:tensorflow:loss = 0.000641259, step = 38601\n", + "INFO:tensorflow:global_step/sec: 172.888\n", + "INFO:tensorflow:loss = 0.000500807, step = 38701\n", + "INFO:tensorflow:global_step/sec: 172.28\n", + "INFO:tensorflow:loss = 0.000238236, step = 38801\n", + "INFO:tensorflow:global_step/sec: 174.695\n", + "INFO:tensorflow:loss = 0.00117353, step = 38901\n", + "INFO:tensorflow:global_step/sec: 162.459\n", + "INFO:tensorflow:loss = 0.000101205, step = 39001\n", + "INFO:tensorflow:global_step/sec: 172.143\n", + "INFO:tensorflow:loss = 0.00106715, step = 39101\n", + "INFO:tensorflow:global_step/sec: 180.468\n", + "INFO:tensorflow:loss = 0.000345391, step = 39201\n", + "INFO:tensorflow:global_step/sec: 195.353\n", + "INFO:tensorflow:loss = 0.000169909, step = 39301\n", + "INFO:tensorflow:global_step/sec: 205.431\n", + "INFO:tensorflow:loss = 0.000561044, step = 39401\n", + "INFO:tensorflow:global_step/sec: 208.582\n", + "INFO:tensorflow:loss = 0.000116529, step = 39501\n", + "INFO:tensorflow:global_step/sec: 203.156\n", + "INFO:tensorflow:loss = 0.000750057, step = 39601\n", + "INFO:tensorflow:global_step/sec: 203.551\n", + "INFO:tensorflow:loss = 0.000109314, step = 39701\n", + "INFO:tensorflow:global_step/sec: 201.477\n", + "INFO:tensorflow:loss = 0.00102298, step = 39801\n", + "INFO:tensorflow:global_step/sec: 205.444\n", + "INFO:tensorflow:loss = 0.000732327, step = 39901\n", + "INFO:tensorflow:Saving checkpoints for 40000 into /tmp/tmp7zss569e/model.ckpt.\n", + "INFO:tensorflow:Loss for final step: 0.000484666.\n" ] }, { "data": { "text/plain": [ - "DNNClassifier(params={'optimizer': None, 'input_layer_min_slice_size': None, 'embedding_lr_multipliers': None, 'hidden_units': [300, 100], 'dropout': None, 'feature_columns': (_RealValuedColumn(column_name='', dimension=784, default_value=None, dtype=tf.float32, normalizer=None),), 'activation_fn': , 'head': , 'gradient_clip_norm': None})" + "DNNClassifier(params={'feature_columns': (_RealValuedColumn(column_name='', dimension=784, default_value=None, dtype=tf.float32, normalizer=None),), 'embedding_lr_multipliers': None, 'hidden_units': [300, 100], 'head': , 'dropout': None, 'activation_fn': , 'optimizer': None, 'input_layer_min_slice_size': None, 'gradient_clip_norm': None})" ] }, "execution_count": 10, @@ -1293,7 +1293,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "WARNING:tensorflow:From /home/ageron/dev/py/envs/mltst/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/dnn.py:374: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.\n", + "WARNING:tensorflow:From /home/ageron/dev/py/envs/ml/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/dnn.py:374: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.\n", "Instructions for updating:\n", "Estimator is decoupled from Scikit Learn interface by moving into\n", "separate class SKCompat. Arguments x, y and batch_size are only\n", @@ -1306,14 +1306,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "/home/ageron/dev/py/envs/mltst/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.\n", + "/home/ageron/dev/py/envs/ml/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.\n", " equality = a == b\n" ] }, { "data": { "text/plain": [ - "0.98250000000000004" + "0.98329999999999995" ] }, "execution_count": 11, @@ -1342,7 +1342,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "WARNING:tensorflow:From /home/ageron/dev/py/envs/mltst/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/dnn.py:409: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.\n", + "WARNING:tensorflow:From /home/ageron/dev/py/envs/ml/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/dnn.py:409: calling BaseEstimator.predict (from tensorflow.contrib.learn.python.learn.estimators.estimator) with x is deprecated and will be removed after 2016-12-01.\n", "Instructions for updating:\n", "Estimator is decoupled from Scikit Learn interface by moving into\n", "separate class SKCompat. Arguments x, y and batch_size are only\n", @@ -1355,14 +1355,14 @@ "name": "stderr", "output_type": "stream", "text": [ - "/home/ageron/dev/py/envs/mltst/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.\n", + "/home/ageron/dev/py/envs/ml/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.\n", " equality = a == b\n" ] }, { "data": { "text/plain": [ - "0.067936991468389801" + "0.071601274010499413" ] }, "execution_count": 12, @@ -1404,17 +1404,16 @@ "available in the SKCompat class, Estimator will only accept input_fn.\n", "Example conversion:\n", " est = Estimator(...) -> est = SKCompat(Estimator(...))\n", - "WARNING:tensorflow:From /home/ageron/dev/py/envs/mltst/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:1362: scalar_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30.\n", + "WARNING:tensorflow:From /home/ageron/dev/py/envs/ml/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/head.py:1362: scalar_summary (from tensorflow.python.ops.logging_ops) is deprecated and will be removed after 2016-11-30.\n", "Instructions for updating:\n", - "Please switch to tf.summary.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.\n", - "INFO:tensorflow:Starting evaluation at 2017-02-15-16:32:24\n" + "Please switch to tf.summary.scalar. Note that tf.summary.scalar uses the node name instead of the tag. This means that TensorFlow will automatically de-duplicate summary names based on the scope they are created in. Also, passing a tensor or list of tags to a scalar summary op is no longer supported.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ - "/home/ageron/dev/py/envs/mltst/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.\n", + "/home/ageron/dev/py/envs/ml/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.\n", " equality = a == b\n" ] }, @@ -1422,18 +1421,19 @@ "name": "stdout", "output_type": "stream", "text": [ - "INFO:tensorflow:Finished evaluation at 2017-02-15-16:32:25\n", - "INFO:tensorflow:Saving dict for global step 40000: accuracy = 0.9825, auc = 0.998039, global_step = 40000, loss = 0.0679368\n", + "INFO:tensorflow:Starting evaluation at 2017-04-28-07:20:59\n", + "INFO:tensorflow:Finished evaluation at 2017-04-28-07:21:00\n", + "INFO:tensorflow:Saving dict for global step 40000: accuracy = 0.9833, auc = 0.997642, global_step = 40000, loss = 0.0716011\n", "WARNING:tensorflow:Skipping summary for global_step, must be a float or np.float32.\n" ] }, { "data": { "text/plain": [ - "{'accuracy': 0.98250002,\n", - " 'auc': 0.99803877,\n", + "{'accuracy': 0.98329997,\n", + " 'auc': 0.99764204,\n", " 'global_step': 40000,\n", - " 'loss': 0.06793683}" + " 'loss': 0.071601115}" ] }, "execution_count": 13, @@ -1537,26 +1537,26 @@ "name": "stdout", "output_type": "stream", "text": [ - "0 Train accuracy: 0.96 Test accuracy: 0.8802\n", - "1 Train accuracy: 0.88 Test accuracy: 0.9094\n", - "2 Train accuracy: 0.92 Test accuracy: 0.9207\n", - "3 Train accuracy: 0.9 Test accuracy: 0.9283\n", - "4 Train accuracy: 0.96 Test accuracy: 0.933\n", - "5 Train accuracy: 0.92 Test accuracy: 0.9389\n", - "6 Train accuracy: 0.94 Test accuracy: 0.9413\n", - "7 Train accuracy: 0.96 Test accuracy: 0.9452\n", - "8 Train accuracy: 0.96 Test accuracy: 0.949\n", - "9 Train accuracy: 0.9 Test accuracy: 0.9531\n", - "10 Train accuracy: 0.94 Test accuracy: 0.9553\n", - "11 Train accuracy: 0.96 Test accuracy: 0.9564\n", - "12 Train accuracy: 0.9 Test accuracy: 0.9586\n", - "13 Train accuracy: 1.0 Test accuracy: 0.9604\n", - "14 Train accuracy: 0.9 Test accuracy: 0.9607\n", - "15 Train accuracy: 0.98 Test accuracy: 0.9635\n", - "16 Train accuracy: 1.0 Test accuracy: 0.9644\n", - "17 Train accuracy: 0.98 Test accuracy: 0.9659\n", - "18 Train accuracy: 0.98 Test accuracy: 0.9658\n", - "19 Train accuracy: 1.0 Test accuracy: 0.967\n" + "0 Train accuracy: 0.96 Test accuracy: 0.8803\n", + "1 Train accuracy: 0.88 Test accuracy: 0.908\n", + "2 Train accuracy: 0.92 Test accuracy: 0.9187\n", + "3 Train accuracy: 0.9 Test accuracy: 0.925\n", + "4 Train accuracy: 0.96 Test accuracy: 0.9314\n", + "5 Train accuracy: 0.92 Test accuracy: 0.937\n", + "6 Train accuracy: 0.94 Test accuracy: 0.9403\n", + "7 Train accuracy: 0.94 Test accuracy: 0.9453\n", + "8 Train accuracy: 0.94 Test accuracy: 0.9488\n", + "9 Train accuracy: 0.9 Test accuracy: 0.9517\n", + "10 Train accuracy: 0.96 Test accuracy: 0.9541\n", + "11 Train accuracy: 0.98 Test accuracy: 0.9554\n", + "12 Train accuracy: 0.92 Test accuracy: 0.9596\n", + "13 Train accuracy: 0.98 Test accuracy: 0.9607\n", + "14 Train accuracy: 0.92 Test accuracy: 0.9624\n", + "15 Train accuracy: 1.0 Test accuracy: 0.964\n", + "16 Train accuracy: 1.0 Test accuracy: 0.9656\n", + "17 Train accuracy: 0.98 Test accuracy: 0.9656\n", + "18 Train accuracy: 0.96 Test accuracy: 0.9664\n", + "19 Train accuracy: 1.0 Test accuracy: 0.9684\n" ] } ], @@ -1697,7 +1697,17 @@ "editable": true }, "source": [ - "## Using `fully_connected` instead of `neuron_layer()`" + "## Using `dense()` instead of `neuron_layer()`" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Note: the book uses `tensorflow.contrib.layers.fully_connected()` rather than `tf.layers.dense()` (which did not exist when this chapter was written). It is now preferable to use `tf.layers.dense()`, because anything in the contrib module may change or be deleted without notice. The `dense()` function is almost identical to the `fully_connected()` function, except for a few minor differences:\n", + "* several parameters are renamed: `scope` becomes `name`, `activation_fn` becomes `activation` (and similarly the `_fn` suffix is removed from other parameters such as `normalizer_fn`), `weights_initializer` becomes `kernel_initializer`, etc.\n", + "* the default `activation` is now `None` rather than `tf.nn.relu`.\n", + "* a few more differences are presented in chapter 11." ] }, { @@ -1712,8 +1722,6 @@ "source": [ "tf.reset_default_graph()\n", "\n", - "from tensorflow.contrib.layers import fully_connected\n", - "\n", "n_inputs = 28*28 # MNIST\n", "n_hidden1 = 300\n", "n_hidden2 = 100\n", @@ -1724,9 +1732,9 @@ "y = tf.placeholder(tf.int64, shape=(None), name=\"y\")\n", "\n", "with tf.name_scope(\"dnn\"):\n", - " hidden1 = fully_connected(X, n_hidden1, scope=\"hidden1\")\n", - " hidden2 = fully_connected(hidden1, n_hidden2, scope=\"hidden2\")\n", - " logits = fully_connected(hidden2, n_outputs, activation_fn=None, scope=\"outputs\")\n", + " hidden1 = tf.layers.dense(X, n_hidden1, name=\"hidden1\", activation=tf.nn.relu)\n", + " hidden2 = tf.layers.dense(hidden1, n_hidden2, name=\"hidden2\", activation=tf.nn.relu)\n", + " logits = tf.layers.dense(hidden2, n_outputs, name=\"outputs\")\n", "\n", "with tf.name_scope(\"loss\"):\n", " xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)\n", @@ -1757,26 +1765,26 @@ "name": "stdout", "output_type": "stream", "text": [ - "0 Train accuracy: 0.92 Test accuracy: 0.9001\n", - "1 Train accuracy: 0.92 Test accuracy: 0.9203\n", - "2 Train accuracy: 0.96 Test accuracy: 0.9286\n", - "3 Train accuracy: 0.96 Test accuracy: 0.9367\n", - "4 Train accuracy: 0.96 Test accuracy: 0.941\n", - "5 Train accuracy: 0.98 Test accuracy: 0.9471\n", - "6 Train accuracy: 0.96 Test accuracy: 0.9502\n", - "7 Train accuracy: 0.96 Test accuracy: 0.9529\n", - "8 Train accuracy: 1.0 Test accuracy: 0.9566\n", - "9 Train accuracy: 0.94 Test accuracy: 0.9591\n", - "10 Train accuracy: 0.96 Test accuracy: 0.9602\n", - "11 Train accuracy: 1.0 Test accuracy: 0.9635\n", - "12 Train accuracy: 0.98 Test accuracy: 0.9637\n", + "0 Train accuracy: 0.96 Test accuracy: 0.9054\n", + "1 Train accuracy: 0.92 Test accuracy: 0.9219\n", + "2 Train accuracy: 0.92 Test accuracy: 0.9298\n", + "3 Train accuracy: 0.98 Test accuracy: 0.9365\n", + "4 Train accuracy: 0.92 Test accuracy: 0.9401\n", + "5 Train accuracy: 0.98 Test accuracy: 0.9459\n", + "6 Train accuracy: 0.96 Test accuracy: 0.9503\n", + "7 Train accuracy: 0.98 Test accuracy: 0.9536\n", + "8 Train accuracy: 1.0 Test accuracy: 0.9567\n", + "9 Train accuracy: 0.94 Test accuracy: 0.9577\n", + "10 Train accuracy: 0.98 Test accuracy: 0.9599\n", + "11 Train accuracy: 1.0 Test accuracy: 0.9632\n", + "12 Train accuracy: 1.0 Test accuracy: 0.9638\n", "13 Train accuracy: 1.0 Test accuracy: 0.9656\n", - "14 Train accuracy: 1.0 Test accuracy: 0.9659\n", - "15 Train accuracy: 0.96 Test accuracy: 0.9684\n", - "16 Train accuracy: 1.0 Test accuracy: 0.9681\n", - "17 Train accuracy: 1.0 Test accuracy: 0.9698\n", - "18 Train accuracy: 0.96 Test accuracy: 0.971\n", - "19 Train accuracy: 0.96 Test accuracy: 0.9718\n" + "14 Train accuracy: 0.98 Test accuracy: 0.9666\n", + "15 Train accuracy: 0.98 Test accuracy: 0.9667\n", + "16 Train accuracy: 1.0 Test accuracy: 0.9679\n", + "17 Train accuracy: 1.0 Test accuracy: 0.9678\n", + "18 Train accuracy: 0.94 Test accuracy: 0.9699\n", + "19 Train accuracy: 0.98 Test accuracy: 0.9712\n" ] } ], @@ -1813,7 +1821,7 @@ "