notebooks/tf.estimator_dataset.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.0.0'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "tf.__version__"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# THIS NOTEBOOK IS CURRENTLY BROKEN - use tf.estimator.ipynb instead (using numpy arrays of tf.data.Dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<TensorSliceDataset shapes: ((28, 28), ()), types: (tf.float64, tf.uint8)>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train, _ = tf.keras.datasets.fashion_mnist.load_data()\n",
    "images, labels = train\n",
    "images = images/255\n",
    "\n",
    "dataset = tf.data.Dataset.from_tensor_slices((images, labels))\n",
    "dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<tf.Tensor: id=29, shape=(), dtype=uint8, numpy=9>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iter(dataset).next()[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [],
   "source": [
    "def pre_process(image_tensor, label_tensor):\n",
    "    #flatten\n",
    "    image_tensor = tf.reshape(image_tensor,(28**2,))\n",
    "    \n",
    "    #tensor to tensordict\n",
    "    tensor_dict = dict()\n",
    "    for feature_idx in range(784):\n",
    "        key = str(feature_idx)\n",
    "        value = tf.slice(image_tensor,[feature_idx],[1])\n",
    "        tensor_dict.update({key:value})\n",
    "        \n",
    "    #one hot encode labels, cast to int32\n",
    "    label_tensor = tf.one_hot(label_tensor,10,dtype=tf.int32)\n",
    "    \n",
    "    #reshape\n",
    "    #label_tensor = tf.reshape(label_tensor,[1,10])\n",
    "    \n",
    "    return (tensor_dict,label_tensor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "features = []\n",
    "for feature_idx in range(784):\n",
    "    features.append(tf.feature_column.numeric_column(str(feature_idx)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Using default config.\n",
      "WARNING:tensorflow:Using temporary folder as model directory: /var/folders/95/7hxgmrh92z91hylbxw647jhr0000gn/T/tmph8hxm8fv\n",
      "INFO:tensorflow:Using config: {'_model_dir': '/var/folders/95/7hxgmrh92z91hylbxw647jhr0000gn/T/tmph8hxm8fv', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true\n",
      "graph_options {\n",
      "  rewrite_options {\n",
      "    meta_optimizer_iterations: ONE\n",
      "  }\n",
      "}\n",
      ", '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x5d23b38d0>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}\n"
     ]
    }
   ],
   "source": [
    "estimator = tf.estimator.DNNClassifier(feature_columns=features, hidden_units = [100], n_classes=10)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Calling model_fn.\n",
      "WARNING:tensorflow:Layer dnn is casting an input tensor from dtype float64 to the layer's dtype of float32, which is new behavior in TensorFlow 2.  The layer has dtype float32 because it's dtype defaults to floatx.\n",
      "\n",
      "If you intended to run this layer in float32, you can safely ignore this warning. If in doubt, this warning is likely only an issue if you are porting a TensorFlow 1.X model to TensorFlow 2.\n",
      "\n",
      "To change all layers to have dtype float64 by default, call `tf.keras.backend.set_floatx('float64')`. To change just this layer, pass dtype='float64' to the layer constructor. If you are the author of this layer, you can disable autocasting by passing autocast=False to the base Layer constructor.\n",
      "\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "Shape mismatch: The shape of labels (received (10,)) should equal the shape of logits except for the last dimension (received (1, 10)).",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-116-7c5db4f5621c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 8\u001b[0;31m \u001b[0mestimator\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_fn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mget_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msteps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m2000\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/estimator.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, input_fn, hooks, steps, max_steps, saving_listeners)\u001b[0m\n\u001b[1;32m    368\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    369\u001b[0m       \u001b[0msaving_listeners\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_check_listeners_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msaving_listeners\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 370\u001b[0;31m       \u001b[0mloss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_train_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_fn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhooks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msaving_listeners\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    371\u001b[0m       \u001b[0mlogging\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Loss for final step: %s.'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mloss\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    372\u001b[0m       \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/estimator.py\u001b[0m in \u001b[0;36m_train_model\u001b[0;34m(self, input_fn, hooks, saving_listeners)\u001b[0m\n\u001b[1;32m   1158\u001b[0m       \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_train_model_distributed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_fn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhooks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msaving_listeners\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1159\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1160\u001b[0;31m       \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_train_model_default\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_fn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhooks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msaving_listeners\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1161\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1162\u001b[0m   \u001b[0;32mdef\u001b[0m \u001b[0m_train_model_default\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput_fn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhooks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msaving_listeners\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/estimator.py\u001b[0m in \u001b[0;36m_train_model_default\u001b[0;34m(self, input_fn, hooks, saving_listeners)\u001b[0m\n\u001b[1;32m   1188\u001b[0m       \u001b[0mworker_hooks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_hooks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1189\u001b[0m       estimator_spec = self._call_model_fn(\n\u001b[0;32m-> 1190\u001b[0;31m           features, labels, ModeKeys.TRAIN, self.config)\n\u001b[0m\u001b[1;32m   1191\u001b[0m       \u001b[0mglobal_step_tensor\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtraining_util\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_global_step\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1192\u001b[0m       return self._train_with_estimator_spec(estimator_spec, worker_hooks,\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/estimator.py\u001b[0m in \u001b[0;36m_call_model_fn\u001b[0;34m(self, features, labels, mode, config)\u001b[0m\n\u001b[1;32m   1146\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1147\u001b[0m     \u001b[0mlogging\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Calling model_fn.'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1148\u001b[0;31m     \u001b[0mmodel_fn_results\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_model_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1149\u001b[0m     \u001b[0mlogging\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Done calling model_fn.'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1150\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/canned/dnn.py\u001b[0m in \u001b[0;36m_model_fn\u001b[0;34m(features, labels, mode, config)\u001b[0m\n\u001b[1;32m    762\u001b[0m           \u001b[0mdropout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdropout\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    763\u001b[0m           \u001b[0mconfig\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 764\u001b[0;31m           batch_norm=batch_norm)\n\u001b[0m\u001b[1;32m    765\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    766\u001b[0m     super(DNNClassifierV2, self).__init__(\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/canned/dnn.py\u001b[0m in \u001b[0;36mdnn_model_fn_v2\u001b[0;34m(***failed resolving arguments***)\u001b[0m\n\u001b[1;32m    593\u001b[0m       \u001b[0mlogits\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    594\u001b[0m       \u001b[0mtrainable_variables\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtrainable_variables\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 595\u001b[0;31m       update_ops=update_ops)\n\u001b[0m\u001b[1;32m    596\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    597\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/head/base_head.py\u001b[0m in \u001b[0;36mcreate_estimator_spec\u001b[0;34m(self, features, mode, logits, labels, optimizer, trainable_variables, train_op_fn, update_ops, regularization_losses)\u001b[0m\n\u001b[1;32m    274\u001b[0m               \u001b[0moptimizer\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0moptimizer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrainable_variables\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtrainable_variables\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    275\u001b[0m               \u001b[0mtrain_op_fn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtrain_op_fn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mupdate_ops\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mupdate_ops\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 276\u001b[0;31m               regularization_losses=regularization_losses))\n\u001b[0m\u001b[1;32m    277\u001b[0m       \u001b[0;32mreturn\u001b[0m \u001b[0mtpu_estimator_spec\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mas_estimator_spec\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    278\u001b[0m     \u001b[0;32mexcept\u001b[0m \u001b[0mNotImplementedError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/head/multi_class_head.py\u001b[0m in \u001b[0;36m_create_tpu_estimator_spec\u001b[0;34m(self, features, mode, logits, labels, optimizer, trainable_variables, train_op_fn, update_ops, regularization_losses)\u001b[0m\n\u001b[1;32m    420\u001b[0m       regularized_training_loss = self.loss(\n\u001b[1;32m    421\u001b[0m           \u001b[0mlogits\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlabels\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfeatures\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 422\u001b[0;31m           regularization_losses=regularization_losses)\n\u001b[0m\u001b[1;32m    423\u001b[0m       \u001b[0;31m# Eval.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    424\u001b[0m       \u001b[0;32mif\u001b[0m \u001b[0mmode\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mModeKeys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mEVAL\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/head/multi_class_head.py\u001b[0m in \u001b[0;36mloss\u001b[0;34m(***failed resolving arguments***)\u001b[0m\n\u001b[1;32m    254\u001b[0m       \u001b[0mlabel_ids\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_processed_labels\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    255\u001b[0m       unweighted_loss, weights = self._unweighted_loss_and_weights(\n\u001b[0;32m--> 256\u001b[0;31m           logits, label_ids, features)\n\u001b[0m\u001b[1;32m    257\u001b[0m       training_loss = losses_utils.compute_weighted_loss(\n\u001b[1;32m    258\u001b[0m           \u001b[0munweighted_loss\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/head/multi_class_head.py\u001b[0m in \u001b[0;36m_unweighted_loss_and_weights\u001b[0;34m(self, logits, label_ids, features)\u001b[0m\n\u001b[1;32m    236\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    237\u001b[0m       unweighted_loss = losses.sparse_softmax_cross_entropy(\n\u001b[0;32m--> 238\u001b[0;31m           labels=label_ids, logits=logits, reduction=losses.Reduction.NONE)\n\u001b[0m\u001b[1;32m    239\u001b[0m       \u001b[0;31m# Restore the squeezed dim, so unweighted_loss matches the weights shape.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    240\u001b[0m       \u001b[0munweighted_loss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0marray_ops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexpand_dims\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0munweighted_loss\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_core/python/ops/losses/losses_impl.py\u001b[0m in \u001b[0;36msparse_softmax_cross_entropy\u001b[0;34m(labels, logits, weights, scope, loss_collection, reduction)\u001b[0m\n\u001b[1;32m    886\u001b[0m     losses = nn.sparse_softmax_cross_entropy_with_logits(labels=labels,\n\u001b[1;32m    887\u001b[0m                                                          \u001b[0mlogits\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlogits\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 888\u001b[0;31m                                                          name=\"xentropy\")\n\u001b[0m\u001b[1;32m    889\u001b[0m     return compute_weighted_loss(\n\u001b[1;32m    890\u001b[0m         losses, weights, scope, loss_collection, reduction=reduction)\n",
      "\u001b[0;32m~/opt/anaconda3/envs/tf2.0/lib/python3.7/site-packages/tensorflow_core/python/ops/nn_ops.py\u001b[0m in \u001b[0;36msparse_softmax_cross_entropy_with_logits\u001b[0;34m(_sentinel, labels, logits, name)\u001b[0m\n\u001b[1;32m   3391\u001b[0m                        \u001b[0;34m\"should equal the shape of logits except for the last \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3392\u001b[0m                        \"dimension (received %s).\" % (labels_static_shape,\n\u001b[0;32m-> 3393\u001b[0;31m                                                      logits.get_shape()))\n\u001b[0m\u001b[1;32m   3394\u001b[0m     \u001b[0;31m# Check if no reshapes are required.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3395\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mlogits\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_shape\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndims\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: Shape mismatch: The shape of labels (received (10,)) should equal the shape of logits except for the last dimension (received (1, 10))."
     ]
    }
   ],
   "source": [
    "\n",
    "@tf.function\n",
    "def get_data():\n",
    "    dataset = tf.data.Dataset.from_tensor_slices((images, labels))\n",
    "    dataset_preprocessed = dataset.map(pre_process)\n",
    "    return dataset_preprocessed\n",
    "    \n",
    "\n",
    "estimator.train(input_fn=get_data, steps=2000)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}