Regression API Test

regression_api_test.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Regress API Test\n",
    "===="
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import shutil\n",
    "import numpy as np\n",
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /Users/deploy/.pyenv/versions/3.7.6/envs/danke/lib/python3.7/site-packages/tensorflow/python/ops/init_ops.py:1251: calling VarianceScaling.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Call initializer instance with the dtype argument instead of passing it to the constructor\n",
      "WARNING:tensorflow:From /Users/deploy/.pyenv/versions/3.7.6/envs/danke/lib/python3.7/site-packages/tensorflow/python/ops/nn_impl.py:180: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Use tf.where in 2.0, which has the same broadcast rule as np.where\n",
      "Model: \"model\"\n",
      "__________________________________________________________________________________________________\n",
      "Layer (type)                    Output Shape         Param #     Connected to                     \n",
      "==================================================================================================\n",
      "x1 (InputLayer)                 [(None, 1)]          0                                            \n",
      "__________________________________________________________________________________________________\n",
      "x2 (InputLayer)                 [(None, 1)]          0                                            \n",
      "__________________________________________________________________________________________________\n",
      "concat (Concatenate)            (None, 2)            0           x1[0][0]                         \n",
      "                                                                 x2[0][0]                         \n",
      "__________________________________________________________________________________________________\n",
      "dense (Dense)                   (None, 10)           30          concat[0][0]                     \n",
      "__________________________________________________________________________________________________\n",
      "y (Dense)                       (None, 1)            11          dense[0][0]                      \n",
      "==================================================================================================\n",
      "Total params: 41\n",
      "Trainable params: 41\n",
      "Non-trainable params: 0\n",
      "__________________________________________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "inputs = {\n",
    "    'x1': tf.keras.layers.Input(shape=(1, ), name='x1', dtype='float32'),\n",
    "    'x2': tf.keras.layers.Input(shape=(1, ), name='x2', dtype='float32'),\n",
    "}\n",
    "concat = tf.keras.layers.Concatenate(name='concat')([inputs['x1'], inputs['x2']])\n",
    "dense = tf.keras.layers.Dense(10, use_bias=True, activation='relu', name='dense')(concat)\n",
    "outputs = tf.keras.layers.Dense(1, use_bias=True, activation='sigmoid', name='y')(dense)\n",
    "model = tf.keras.models.Model(inputs=inputs, outputs=outputs)\n",
    "model.compile(optimizer='SGD', loss='binary_crossentropy')\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000/10000 [==============================] - 0s 25us/sample - loss: 0.3056\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<tensorflow.python.keras.callbacks.History at 0x131192c90>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "num_exam = 10000\n",
    "model.fit({'x1': np.random.randn(num_exam), 'x2': np.random.rand(num_exam)}, np.random.randn(num_exam))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Save"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From <ipython-input-4-662274ec3ef5>:1: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info.\n",
      "inputs {\n",
      "  key: \"x1\"\n",
      "  value {\n",
      "    name: \"x1:0\"\n",
      "    dtype: DT_FLOAT\n",
      "    tensor_shape {\n",
      "      dim {\n",
      "        size: -1\n",
      "      }\n",
      "      dim {\n",
      "        size: 1\n",
      "      }\n",
      "    }\n",
      "  }\n",
      "}\n",
      "inputs {\n",
      "  key: \"x2\"\n",
      "  value {\n",
      "    name: \"x2:0\"\n",
      "    dtype: DT_FLOAT\n",
      "    tensor_shape {\n",
      "      dim {\n",
      "        size: -1\n",
      "      }\n",
      "      dim {\n",
      "        size: 1\n",
      "      }\n",
      "    }\n",
      "  }\n",
      "}\n",
      "outputs {\n",
      "  key: \"y\"\n",
      "  value {\n",
      "    name: \"y/Sigmoid:0\"\n",
      "    dtype: DT_FLOAT\n",
      "    tensor_shape {\n",
      "      dim {\n",
      "        size: -1\n",
      "      }\n",
      "      dim {\n",
      "        size: 1\n",
      "      }\n",
      "    }\n",
      "  }\n",
      "}\n",
      "method_name: \"tensorflow/serving/regress\"\n",
      "\n"
     ]
    }
   ],
   "source": [
    "input_infos = {name: tf.saved_model.build_tensor_info(tensor) for name, tensor in model.input.items()}\n",
    "output_infos = {'y': tf.saved_model.build_tensor_info(model.outputs[0])}\n",
    "signature = tf.saved_model.build_signature_def(\n",
    "    inputs=input_infos,\n",
    "    outputs=output_infos,\n",
    "    method_name=tf.saved_model.signature_constants.REGRESS_METHOD_NAME\n",
    ")\n",
    "print(signature)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:No assets to save.\n",
      "INFO:tensorflow:No assets to write.\n",
      "INFO:tensorflow:SavedModel written to: ./random_regression/1/saved_model.pb\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "b'./random_regression/1/saved_model.pb'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_dir = './random_regression/1'\n",
    "shutil.rmtree(model_dir, ignore_errors=True)\n",
    "model_builder = tf.saved_model.builder.SavedModelBuilder(model_dir)\n",
    "model_builder.add_meta_graph_and_variables(\n",
    "    tf.keras.backend.get_session(),\n",
    "    tags=[tf.saved_model.tag_constants.SERVING, ],\n",
    "    signature_def_map={tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: signature}\n",
    ")\n",
    "model_builder.save()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Show Saved Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:\n",
      "\n",
      "signature_def['serving_default']:\n",
      "  The given SavedModel SignatureDef contains the following input(s):\n",
      "    inputs['x1'] tensor_info:\n",
      "        dtype: DT_FLOAT\n",
      "        shape: (-1, 1)\n",
      "        name: x1:0\n",
      "    inputs['x2'] tensor_info:\n",
      "        dtype: DT_FLOAT\n",
      "        shape: (-1, 1)\n",
      "        name: x2:0\n",
      "  The given SavedModel SignatureDef contains the following output(s):\n",
      "    outputs['y'] tensor_info:\n",
      "        dtype: DT_FLOAT\n",
      "        shape: (-1, 1)\n",
      "        name: y/Sigmoid:0\n",
      "  Method name is: tensorflow/serving/regress\n"
     ]
    }
   ],
   "source": [
    "!saved_model_cli show --dir ./random_regression/1 --all"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### REST API Results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1) __regress__ API with \"examples\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{ \"error\": \"Expected one input Tensor.\" }"
     ]
    }
   ],
   "source": [
    "!curl -X POST -H \"Content-Type: application/json\" http://localhost:8501/v1/models/random_regression/versions/1:regress -d ' \\\n",
    "{ \\\n",
    "  \"examples\": [ \\\n",
    "    { \\\n",
    "      \"x1\": [0.1], \\\n",
    "      \"x2\": [0.2] \\\n",
    "    }, \\\n",
    "    { \\\n",
    "      \"x1\": [0.1], \\\n",
    "      \"x2\": [0.3] \\\n",
    "    } \\\n",
    "  ] \\\n",
    "}'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2) __predict__ API with \"instances\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\r\n",
      "    \"predictions\": [[0.143165469], [0.124352224]\r\n",
      "    ]\r\n",
      "}"
     ]
    }
   ],
   "source": [
    "!curl -X POST -H \"Content-Type: application/json\" http://localhost:8501/v1/models/random_regression/versions/1:predict -d ' \\\n",
    "{ \\\n",
    "  \"instances\": [ \\\n",
    "    { \\\n",
    "      \"x1\": [0.1], \\\n",
    "      \"x2\": [0.2] \\\n",
    "    }, \\\n",
    "    { \\\n",
    "      \"x1\": [0.1], \\\n",
    "      \"x2\": [0.3] \\\n",
    "    } \\\n",
    "  ] \\\n",
    "}'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3) __predict__ API with \"context\" and \"examples\" that I really want"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{ \"error\": \"Expected one input Tensor.\" }"
     ]
    }
   ],
   "source": [
    "!curl -X POST -H \"Content-Type: application/json\" http://localhost:8501/v1/models/random_regression/versions/1:regress -d ' \\\n",
    "{ \\\n",
    "  \"context\": { \\\n",
    "    \"x1\": [0.1] \\\n",
    "  }, \\\n",
    "  \"examples\": [ \\\n",
    "    { \\\n",
    "      \"x2\": [0.2] \\\n",
    "    }, \\\n",
    "    { \\\n",
    "      \"x2\": [0.3] \\\n",
    "    } \\\n",
    "  ] \\\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
}