train_and_deploy.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Image Classification with AWS Sagemaker\n",
    "\n",
    "This project will use a dog images dataset with 133 type of dogs. A CNN model will be used and trained on top of the ResNet50 Model using transfer learning. Then hyperparameter tuning is performed in an effort to try to look for the best parameter configuration possible. Then, the best model is deployed and some profiling and debugging metrics are obtained in order to check that the model was trained as expected. Finally, the model is deployed into an endpoint and queried to make some inferences."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "!pip install smdebug"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sagemaker\n",
    "import boto3\n",
    "import os"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Dataset\n",
    "The data set is downloaded from a s3 bucket and it is unziped into our local directoroy."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "jupyter": {
     "outputs_hidden": true
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Command to download and unzip data\n",
    "!wget https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/dogImages.zip\n",
    "!unzip dogImages.zip"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Then the dataset will be uplooaded into an s3 bucket so it can be used by different instances to train different models."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "\n",
    "bucket_name = 'sagemaker-us-east-1-272259209864'\n",
    "\n",
    "def upload_directory_to_s3(local_directory, s3_bucket, s3_prefix=''):\n",
    "    s3 = boto3.client('s3')\n",
    "    for root, dirs, files in os.walk(local_directory):\n",
    "        for file in files:\n",
    "            local_path = os.path.join(root, file)\n",
    "            relative_path = os.path.relpath(local_path, local_directory)\n",
    "            s3_path = os.path.join(s3_prefix, relative_path).replace(\"\\\\\", \"/\")\n",
    "            s3.upload_file(local_path, s3_bucket, s3_path)\n",
    "\n",
    "upload_directory_to_s3('dogImages', bucket_name,'dogImagesDS')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here we can visualize an image from the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "bucket_name = 'sagemaker-us-east-1-272259209864'\n",
    "img_s3_key = 'dogImagesDS/train/091.Japanese_chin/Japanese_chin_06190.jpg'\n",
    "local_path = '/tmp/Poodle_07899.jpg'\n",
    "\n",
    "s3 = boto3.client('s3')\n",
    "s3.download_file(bucket_name, img_s3_key, local_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.image as mpimg\n",
    "\n",
    "# Display the image\n",
    "img = mpimg.imread(local_path)\n",
    "plt.imshow(img)\n",
    "plt.axis('off')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "jupyter": {
     "outputs_hidden": true
    },
    "scrolled": true,
    "tags": []
   },
   "outputs": [],
   "source": [
    "!pip install torchvision"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Some transformations are applied to the different images in order to see how this transformations work. For instance, we can resize the images to 224x224 pixels and normalize them."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import torch.nn as nn\n",
    "import torch.optim as optim\n",
    "import torchvision.transforms as transforms\n",
    "from torchvision.datasets import ImageFolder\n",
    "from torch.utils.data import DataLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "\n",
    "data_dir='dogImages'\n",
    "\n",
    "# Define data transformations for training and validation\n",
    "transform = transforms.Compose([\n",
    "    transforms.Resize((224, 224)),\n",
    "    transforms.ToTensor(),\n",
    "    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])\n",
    "])\n",
    "\n",
    "#train_dataset = ImageFolder(root='s3://sagemaker-us-east-1-272259209864/dogImagesDS/train/', transform=transform)\n",
    "train_dataset = ImageFolder(root=data_dir + '/train', transform=transform)\n",
    "test_dataset = ImageFolder(root=data_dir + '/test', transform=transform)\n",
    "val_dataset = ImageFolder(root=data_dir + '/valid', transform=transform)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# image after transformation\n",
    "plt.imshow(train_dataset[30][0].permute(1, 2, 0))\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can also see how many classes we have (type of dogs)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "num_classes = len(train_dataset.classes)\n",
    "num_classes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Also we can see how many images we have for every class for the training dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "class_to_idx = train_dataset.class_to_idx\n",
    "class_names = train_dataset.classes\n",
    "\n",
    "class_counts = [0] * len(class_names)\n",
    "\n",
    "for _, label in train_dataset:\n",
    "    class_counts[label] += 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "plt.subplots(figsize=(20,5))\n",
    "plt.bar(class_names, class_counts , color ='maroon',\n",
    "        width = 0.3)\n",
    "\n",
    "plt.xticks(rotation=90,fontsize=8)\n",
    "plt.title(\"Number of images per class\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can see the type of dog called Alaskan Malamute has more images than the rest with 78 approx."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Test the hpo.py script\n",
    "\n",
    "This script will be used to perform parameter tuning. In order to check quickly if it is working properly, we can execute it with the following command:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "!python hpo.py \\\n",
    "    --batch_size 32 \\\n",
    "    --bucket_name sagemaker-us-east-1-272259209864 \\\n",
    "    --ds_path_s3 dogImages \\\n",
    "    --lr 0.001 \\\n",
    "    --momentum=0.9 \\\n",
    "    --epochs 1 \\\n",
    "    --path model.h5"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Hyperparameter Tuning\n",
    "\n",
    "In this part we will try to find the best parameters configuration for the model. For this purpose we will use `HyperparameterTuner."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sagemaker\n",
    "from sagemaker.tuner import (\n",
    "    IntegerParameter,\n",
    "    CategoricalParameter,\n",
    "    ContinuousParameter,\n",
    "    HyperparameterTuner,\n",
    ")\n",
    "from sagemaker.pytorch import PyTorch\n",
    "\n",
    "role = sagemaker.get_execution_role()\n",
    "\n",
    "hyperparameter_ranges = {\n",
    "    \"lr\": ContinuousParameter(0.001, 0.1),\n",
    "    \"batch_size\": CategoricalParameter([32, 64, 128]),\n",
    "    \"momentum\": CategoricalParameter([0.7,0.8,0.9])\n",
    "}\n",
    "\n",
    "objective_metric_name = \"Test Accuracy\"\n",
    "objective_type = \"Maximize\"\n",
    "metric_definitions = [{\"Name\": \"Test Accuracy\", \"Regex\": \"Test Accuracy: ([0-9\\\\.]+)\"}]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "training_path = 's3://sagemaker-us-east-1-272259209864/dogImagesDS'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "estimator = PyTorch(\n",
    "    entry_point=\"hpo.py\",\n",
    "    role=role,\n",
    "    py_version='py36',\n",
    "    framework_version='1.8',\n",
    "    instance_count=1,\n",
    "    instance_type='ml.g4dn.xlarge'\n",
    ")\n",
    "\n",
    "tuner = HyperparameterTuner(\n",
    "    estimator,\n",
    "    objective_metric_name,\n",
    "    hyperparameter_ranges,\n",
    "    metric_definitions,\n",
    "    max_jobs=4,\n",
    "    max_parallel_jobs=2,\n",
    "    objective_type=objective_type\n",
    ")\n",
    "\n",
    "tuner.fit({\"train\": training_path}, wait=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "best_estimator = tuner.best_estimator()\n",
    "\n",
    "#Get the hyperparameters of the best trained model\n",
    "best_estimator.hyperparameters()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model Profiling and Debugging\n",
    "Using the best hyperparameters, we will create and finetune a new model. We will use the `train_model.py` script to perform model profiling and debugging."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "rom sagemaker.debugger import Rule, ProfilerRule, rule_configs\n",
    "from sagemaker.debugger import DebuggerHookConfig, ProfilerConfig, FrameworkProfile, CollectionConfig\n",
    "import sagemaker\n",
    "from sagemaker.pytorch import PyTorch\n",
    "\n",
    "role = sagemaker.get_execution_role()\n",
    "rules = [\n",
    "    # debugger rules\n",
    "    Rule.sagemaker(rule_configs.loss_not_decreasing()),\n",
    "    Rule.sagemaker(rule_configs.vanishing_gradient()),\n",
    "    Rule.sagemaker(rule_configs.overfit()),\n",
    "    \n",
    "    # profiling rules\n",
    "    ProfilerRule.sagemaker(rule_configs.LowGPUUtilization()),\n",
    "    ProfilerRule.sagemaker(rule_configs.ProfilerReport())\n",
    "]\n",
    "\n",
    "collection_configs=[CollectionConfig(name=\"CrossEntropyLoss_output_0\",parameters={\n",
    "    \"include_regex\": \"CrossEntropyLoss_output_0\", \"train.save_interval\": \"10\",\"eval.save_interval\": \"1\"})]\n",
    "\n",
    "profiler_config = ProfilerConfig(\n",
    "    system_monitor_interval_millis=500, framework_profile_params=FrameworkProfile(num_steps=10)\n",
    ")\n",
    "debugger_hook_config = DebuggerHookConfig(collection_configs=collection_configs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os\n",
    "os.environ[\"SM_CHANNEL_TRAIN\"] = 'dogImages'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "!python train_model.py \\\n",
    "    --batch_size 32 \\\n",
    "    --ds_path_s3 dogImages \\\n",
    "    --lr 0.001 \\\n",
    "    --momentum=0.9 \\\n",
    "    --epochs 1 \\\n",
    "    --path model.h5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sagemaker.pytorch import PyTorch\n",
    "\n",
    "estimator = PyTorch(\n",
    "    role=sagemaker.get_execution_role(),\n",
    "    instance_count=1,\n",
    "    instance_type=\"ml.g4dn.xlarge\",\n",
    "    entry_point=\"train_model.py\",\n",
    "    framework_version=\"1.6\",\n",
    "    py_version=\"py36\",\n",
    "    output_path='s3://sagemaker-us-east-1-272259209864/output',\n",
    "    hyperparameters={\n",
    "        'batch_size': 128,\n",
    "        'lr': 0.05377,\n",
    "        'momentum': 0.7, # obtained from best model\n",
    "        'epochs': 5\n",
    "    },\n",
    "    profiler_config=profiler_config,\n",
    "    debugger_hook_config=debugger_config,\n",
    "    rules=rules\n",
    ")\n",
    "\n",
    "estimator.fit({\"train\": training_path}, wait=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from smdebug.trials import create_trial\n",
    "from smdebug.core.modes import ModeKeys\n",
    "import boto3\n",
    "from smdebug.profiler.analysis.notebook_utils.training_job import TrainingJob\n",
    "from smdebug.profiler.analysis.notebook_utils.timeline_charts import TimelineCharts\n",
    "\n",
    "session = boto3.session.Session()\n",
    "region = session.region_name\n",
    "\n",
    "training_job_name = estimator.latest_training_job.name\n",
    "print(f\"TRAINING JOB NAME: {training_job_name}\")\n",
    "print(f\"REGION: {region}\")\n",
    "\n",
    "trial = create_trial(estimator.latest_job_debugger_artifacts_path())\n",
    "\n",
    "print('TENSOR NAMES:',trial.tensor_names())\n",
    "print('TRAIN: CrossEntropyLoss_output_0',len(trial.tensor(\"CrossEntropyLoss_output_0\").steps(mode=ModeKeys.TRAIN)))\n",
    "print('TEST: CrossEntropyLoss_output_0',len(trial.tensor(\"CrossEntropyLoss_output_0\").steps(mode=ModeKeys.EVAL)))\n",
    "\n",
    "tj = TrainingJob(training_job_name, region)\n",
    "tj.wait_for_sys_profiling_data_to_be_available()\n",
    "\n",
    "system_metrics_reader = tj.get_systems_metrics_reader()\n",
    "system_metrics_reader.refresh_event_file_list()\n",
    "\n",
    "view_timeline_charts = TimelineCharts(\n",
    "    system_metrics_reader,\n",
    "    framework_metrics_reader=None,\n",
    "    select_dimensions=[\"CPU\", \"GPU\"],\n",
    "    select_events=[\"total\"],\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Visualize loss for train and eval. We can see how it decreases for both over time which is a good sign that our model is learning."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from mpl_toolkits.axes_grid1 import host_subplot\n",
    "\n",
    "def get_data(trial, tname, mode):\n",
    "    tensor = trial.tensor(tname)\n",
    "    steps = tensor.steps(mode=mode)\n",
    "    vals = []\n",
    "    for s in steps:\n",
    "        vals.append(tensor.value(s, mode=mode))\n",
    "    return steps, vals\n",
    "\n",
    "def plot_tensor(trial, tensor_name):\n",
    "    steps_train, vals_train = get_data(trial, tensor_name, mode=ModeKeys.TRAIN)\n",
    "    print(\"loaded TRAIN data\")\n",
    "    steps_eval, vals_eval = get_data(trial, tensor_name, mode=ModeKeys.EVAL)\n",
    "    print(\"loaded EVAL data\")\n",
    "\n",
    "    fig = plt.figure(figsize=(10, 7))\n",
    "    host = host_subplot(111)\n",
    "\n",
    "    par = host.twiny()\n",
    "\n",
    "    host.set_xlabel(\"Steps (TRAIN)\")\n",
    "    par.set_xlabel(\"Steps (EVAL)\")\n",
    "    host.set_ylabel(tensor_name)\n",
    "\n",
    "    (p1,) = host.plot(steps_train, vals_train, label=tensor_name)\n",
    "    print(\"completed TRAIN plot\")\n",
    "    (p2,) = par.plot(steps_eval, vals_eval, label=\"val_\" + tensor_name)\n",
    "    print(\"completed EVAL plot\")\n",
    "    leg = plt.legend()\n",
    "\n",
    "    host.xaxis.get_label().set_color(p1.get_color())\n",
    "    leg.texts[0].set_color(p1.get_color())\n",
    "\n",
    "    par.xaxis.get_label().set_color(p2.get_color())\n",
    "    leg.texts[1].set_color(p2.get_color())\n",
    "\n",
    "    plt.ylabel(tensor_name)\n",
    "\n",
    "    plt.show()\n",
    "\n",
    "plot_tensor(trial, \"CrossEntropyLoss_output_0\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "rule_output_path = estimator.output_path + estimator.latest_training_job.job_name + \"/rule-output\"\n",
    "print(f\"You will find the profiler report in {rule_output_path}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "! aws s3 ls {rule_output_path} --recursive\n",
    "! aws s3 cp {rule_output_path} ./ --recursive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "# get the autogenerated folder name of profiler report\n",
    "profiler_report_name = [\n",
    "    rule[\"RuleConfigurationName\"]\n",
    "    for rule in estimator.latest_training_job.rule_job_summary()\n",
    "    if \"Profiler\" in rule[\"RuleConfigurationName\"]][0]\n",
    "\n",
    "import IPython\n",
    "\n",
    "IPython.display.HTML(filename=profiler_report_name + \"/profiler-output/profiler-report.html\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model Deploying"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "estimator.model_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sagemaker.pytorch import PyTorchModel\n",
    "import sagemaker\n",
    "\n",
    "role = sagemaker.get_execution_role()\n",
    "\n",
    "pytorch_model = PyTorchModel(\n",
    "    model_data=estimator.model_data, \n",
    "    role=role, \n",
    "    entry_point='predictor.py',\n",
    "    py_version=\"py36\",\n",
    "    framework_version=\"1.6\"\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor = pytorch_model.deploy(initial_instance_count=1,\n",
    "                                 instance_type='ml.t2.medium')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model Inference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import io\n",
    "import torchvision.transforms as transforms\n",
    "from sagemaker.serializers import IdentitySerializer\n",
    "import numpy as np\n",
    "from PIL import Image\n",
    "\n",
    "predictor.serializer = IdentitySerializer(\"image/jpeg\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_prediction_to_endpoint(input_path, actual_label):\n",
    "    buf = io.BytesIO()\n",
    "    image = Image.open(input_path).save(buf, format='JPEG')\n",
    "    prediction = predictor.predict(buf.getvalue())\n",
    "    actual = actual_label\n",
    "    print('[LABELS INFO]   Predicted:', np.argmax(prediction)+1,'Actual:', actual) \n",
    "    print('Correct prediction?')\n",
    "    if (np.argmax(prediction)+1)==actual:  \n",
    "        print('Correct prediction?', 'yes')\n",
    "    else:\n",
    "        print('Correct prediction?', 'no :(')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "make_prediction_to_endpoint('test-images/French_bulldog_04764.jpg', 69) # FRENCH BULLDOG\n",
    "make_prediction_to_endpoint('test-images/Chihuahua_03459.jpg', 48) # CHIHUAHUA\n",
    "make_prediction_to_endpoint('test-images/187bb51c-fd77-444e-9797-895e54eb238b.JPG', 61) # English_cocker_spaniel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor.delete_endpoint()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "availableInstances": [
   {
    "_defaultOrder": 0,
    "_isFastLaunch": true,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 4,
    "name": "ml.t3.medium",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 1,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 8,
    "name": "ml.t3.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 2,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.t3.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 3,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.t3.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 4,
    "_isFastLaunch": true,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 8,
    "name": "ml.m5.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 5,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.m5.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 6,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.m5.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 7,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.m5.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 8,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.m5.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 9,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.m5.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 10,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.m5.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 11,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 384,
    "name": "ml.m5.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 12,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 8,
    "name": "ml.m5d.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 13,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.m5d.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 14,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.m5d.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 15,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.m5d.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 16,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.m5d.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 17,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.m5d.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 18,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.m5d.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 19,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 384,
    "name": "ml.m5d.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 20,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": true,
    "memoryGiB": 0,
    "name": "ml.geospatial.interactive",
    "supportedImageNames": [
     "sagemaker-geospatial-v1-0"
    ],
    "vcpuNum": 0
   },
   {
    "_defaultOrder": 21,
    "_isFastLaunch": true,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 4,
    "name": "ml.c5.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 22,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 8,
    "name": "ml.c5.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 23,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.c5.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 24,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.c5.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 25,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 72,
    "name": "ml.c5.9xlarge",
    "vcpuNum": 36
   },
   {
    "_defaultOrder": 26,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 96,
    "name": "ml.c5.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 27,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 144,
    "name": "ml.c5.18xlarge",
    "vcpuNum": 72
   },
   {
    "_defaultOrder": 28,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.c5.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 29,
    "_isFastLaunch": true,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.g4dn.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 30,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.g4dn.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 31,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.g4dn.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 32,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.g4dn.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 33,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 4,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.g4dn.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 34,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.g4dn.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 35,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 61,
    "name": "ml.p3.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 36,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 4,
    "hideHardwareSpecs": false,
    "memoryGiB": 244,
    "name": "ml.p3.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 37,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 488,
    "name": "ml.p3.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 38,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 768,
    "name": "ml.p3dn.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 39,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.r5.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 40,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.r5.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 41,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.r5.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 42,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.r5.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 43,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.r5.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 44,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 384,
    "name": "ml.r5.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 45,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 512,
    "name": "ml.r5.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 46,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 768,
    "name": "ml.r5.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 47,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.g5.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 48,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.g5.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 49,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.g5.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 50,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.g5.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 51,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.g5.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 52,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 4,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.g5.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 53,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 4,
    "hideHardwareSpecs": false,
    "memoryGiB": 384,
    "name": "ml.g5.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 54,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 768,
    "name": "ml.g5.48xlarge",
    "vcpuNum": 192
   },
   {
    "_defaultOrder": 55,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 1152,
    "name": "ml.p4d.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 56,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 1152,
    "name": "ml.p4de.24xlarge",
    "vcpuNum": 96
   }
  ],
  "instance_type": "ml.g4dn.xlarge",
  "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}