add code about hyperparameter tuner of sagemaker

aws-sagemaker/hyperparameter_tuner/clip06_hyperparameter_tuning.ipynb

@@ -0,0 +1,240 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0d4fe723-1c13-4679-b415-e1554c5ca1a4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "!{sys.executable} -m pip install --upgrade pip\n",
+    "!{sys.executable} -m pip install --upgrade boto3\n",
+    "!{sys.executable} -m pip install --upgrade sagemaker\n",
+    "!{sys.executable} -m pip install --upgrade tensorflow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "01b0b892-37ba-4d74-9a17-65b1295c50de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import json\n",
+    "\n",
+    "import sagemaker\n",
+    "from sagemaker.tensorflow import TensorFlow\n",
+    "from sagemaker import get_execution_role\n",
+    "\n",
+    "sess = sagemaker.Session()\n",
+    "region = sess.boto_region_name\n",
+    "role = get_execution_role()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9b84ddf1-573d-48b7-8e98-4c265cd2e225",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 데이터 다운로드 받는 코드\n",
+    "# Data download from http://yann.lecun.com/exdb/mnist/\n",
+    "\n",
+    "import logging\n",
+    "import boto3\n",
+    "from botocore.exceptions import ClientError\n",
+    "\n",
+    "public_bucket = f\"sagemaker-example-files-prod-{region}\"\n",
+    "local_data_dir = \"/tmp/data\"\n",
+    "\n",
+    "\n",
+    "# Download training and testing data from a public S3 bucket\n",
+    "def download_from_s3(data_dir=\"/tmp/data\", train=True):\n",
+    "    \"\"\"Download MNIST dataset and convert it to numpy array\n",
+    "\n",
+    "    Args:\n",
+    "        data_dir (str): directory to save the data\n",
+    "        train (bool): download training set\n",
+    "\n",
+    "    Returns:\n",
+    "        None\n",
+    "    \"\"\"\n",
+    "    # project root\n",
+    "    if not os.path.exists(data_dir):\n",
+    "        os.makedirs(data_dir)\n",
+    "\n",
+    "    if train:\n",
+    "        images_file = \"train-images-idx3-ubyte.gz\"\n",
+    "        labels_file = \"train-labels-idx1-ubyte.gz\"\n",
+    "    else:\n",
+    "        images_file = \"t10k-images-idx3-ubyte.gz\"\n",
+    "        labels_file = \"t10k-labels-idx1-ubyte.gz\"\n",
+    "\n",
+    "    # download objects\n",
+    "    s3 = boto3.client(\"s3\")\n",
+    "    bucket = public_bucket\n",
+    "    for obj in [images_file, labels_file]:\n",
+    "        key = os.path.join(\"datasets/image/MNIST\", obj)\n",
+    "        dest = os.path.join(data_dir, obj)\n",
+    "        if not os.path.exists(dest):\n",
+    "            s3.download_file(bucket, key, dest)\n",
+    "    return\n",
+    "\n",
+    "\n",
+    "download_from_s3(local_data_dir, True)\n",
+    "download_from_s3(local_data_dir, False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "370ca19f-6f75-4ab5-aba1-23f8c494898f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# TensorFlow Estimator 생성\n",
+    "est = TensorFlow(\n",
+    "    entry_point=\"train.py\",  # train.py: 학습에 사용할 코드. 이 코드는 code 폴더에 저장되어 있음\n",
+    "    source_dir=\"code\",\n",
+    "    role=role,\n",
+    "    framework_version=\"2.3.1\",\n",
+    "    # model_dir: remote에 있는 instance, 즉 sagemaker instance에 저장되는 model artifact가 저장되는 디렉토리\n",
+    "    model_dir=\"/opt/ml/model\",\n",
+    "    py_version=\"py37\",\n",
+    "    instance_type=\"ml.m5.xlarge\",\n",
+    "    instance_count=1,\n",
+    "    volume_size=250,  # volue size 지정: 250GB\n",
+    "    hyperparameters={\n",
+    "        \"batch-size\": 512,\n",
+    "        \"epochs\": 4,\n",
+    "    },\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "630e65fa-034e-4efb-bb2c-e1e9fb57c222",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prefix = \"mnist\"\n",
+    "bucket = sess.default_bucket()\n",
+    "\n",
+    "\"\"\"\n",
+    "Uploads data from the local directory to an S3 bucket.\n",
+    "\n",
+    "Args:\n",
+    "  local_data_dir (str): The local directory path where the data is located.\n",
+    "\n",
+    "Returns:\n",
+    "  dict: A dictionary containing the S3 bucket location for the training and testing data.\n",
+    "\n",
+    "\"\"\"\n",
+    "loc = sess.upload_data(path=local_data_dir, bucket=bucket, key_prefix=prefix)\n",
+    "\n",
+    "channels = {\"training\": loc, \"testing\": loc}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "753a86df-8ddd-422e-955a-7e6899ad3fe9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Hyperparameter Tuning\n",
+    "# Hyperparameter tuning을 위한 parameter range 설정\n",
+    "from sagemaker.tuner import ContinuousParameter, HyperparameterTuner\n",
+    "\n",
+    "# learning rate를 1e-4 ~ 1e-3 사이의 값으로 설정\n",
+    "hyperparameter_range = {\"learning-rate\": ContinuousParameter(1e-4, 1e-3)}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c10a6615-84ba-45d2-8f8c-749d7a9ebeec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "objective_metric_name = \"average test loss\"\n",
+    "# metic을 어떤 정책을 기반으로 최적화 할 것인지 설정\n",
+    "objective_type = \"Minimize\"  # 만약 average test loss를 높이고 싶으면 Maximize로 설정\n",
+    "\n",
+    "metric_definitions = [\n",
+    "    {\n",
+    "        \"Name\": \"average test loss\",\n",
+    "        \"Regex\": \"Test Loss: ([0-9\\\\.]+)\",\n",
+    "    }\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55a5a9b8-0ffb-41f4-aa3f-de5f6e32dcf4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tuner = HyperparameterTuner(\n",
+    "    est,\n",
+    "    objective_metric_name,\n",
+    "    hyperparameter_range,\n",
+    "    metric_definitions,\n",
+    "    max_jobs=3,\n",
+    "    max_parallel_jobs=3,\n",
+    "    objective_type=objective_type\n",
+    ")\n",
+    "\n",
+    "tuner.fit(inputs=channels)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e359fb4a-ad25-4a22-8058-d594397b6a1d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Deploy model using SageMaker Endpoint SDK\n",
+    "\n",
+    "from sagemaker import Model\n",
+    "\n",
+    "model = Model(model_data='s3://your-s3-bucket/path/to/model.tar.gz',\n",
+    "              # e.g., '763104351884.dkr.ecr.us-west-2.amazonaws.com/tensorflow-inference:2.3.1-cpu'\n",
+    "              image_uri='your-container-image-url',\n",
+    "              role='arn:aws:iam::account-id:role/role-name')\n",
+    "\n",
+    "predictor = model.deploy(initial_instance_count=1,\n",
+    "                         instance_type='ml.m4.xlarge')\n",
+    "result = predictor.predict(input_data)\n",
+    "predictor.delete_endpoint()  # 이렇게 실습을 진행한 뒤에는 꼭 endpoint를 삭제해서 과금을 막아야 한다."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}