re-train.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "from azureml.core import Experiment, Environment, Workspace, Datastore, Dataset, Model, ScriptRunConfig, Run\n",
        "import os\n",
        "import glob\n",
        "# get the current workspace\n",
        "ws = Workspace.from_config()"
      ],
      "outputs": [],
      "execution_count": 15,
      "metadata": {
        "gather": {
          "logged": 1684345750891
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%cd Satellite_ComputerVision\n",
        "!git pull\n",
        "%cd .."
      ],
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "Already up-to-date.\r\n/mnt/batch/tasks/shared/LS_root/mounts/clusters/test-compute-instance/code/Users/mevans\n"
        }
      ],
      "execution_count": 18,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# access our registered data share containing image data in this workspace\n",
        "datastore = Datastore.get(workspace = ws, datastore_name = 'solardatablob')\n",
        "\n",
        "cpk_train_path = (datastore, 'CPK_solar/data/training/')\n",
        "cpk_eval_path = (datastore, 'CPK_solar/data/eval/')\n",
        "\n",
        "nc_train_path = (datastore, 'NC_solar/data/training/')\n",
        "nc_eval_path = (datastore, 'NC_solar/data/eval/')\n",
        "\n",
        "test_path = (datastore, 'CPK_solar/data/predict/testpred5')\n",
        "\n",
        "# train_dataset = Dataset.File.from_files(path = [cpk_train_path])\n",
        "# eval_dataset = Dataset.File.from_files(path = [cpk_eval_path])\n",
        "\n",
        "# nc_train_dataset = Dataset.File.from_files(path = [nc_train_path])\n",
        "# nc_eval_dataset = Dataset.File.from_files(path = [nc_eval_path])\n",
        "\n",
        "# when we combine datasets the selected directories and relative paths to the datastore are brought in\n",
        "# mount folder\n",
        "# |-cddatafilestore\n",
        "# | |-GEE\n",
        "# | | |-training\n",
        "# | | |-eval\n",
        "# | |-Onera\n",
        "# | | |-training\n",
        "# | | |-eval\n",
        "\n",
        "train_dataset = Dataset.File.from_files(path = [cpk_train_path, nc_train_path])\n",
        "eval_dataset = Dataset.File.from_files(path = [cpk_eval_path, nc_eval_path])\n",
        "test_dataset = Dataset.File.from_files(path = [test_path])"
      ],
      "outputs": [],
      "execution_count": 16,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345752282
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# FInd the run corresponding to the model we want to register\n",
        "# run_id = 'solar-nc-cpk_1624989679_f59da7cf'\n",
        "run_id = 'solar-nc-cpk_1684259900_b71cc594'\n",
        "run = ws.get_run(run_id)"
      ],
      "outputs": [],
      "execution_count": 18,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345784093
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model_name = 'solar_May23'"
      ],
      "outputs": [],
      "execution_count": 17,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345762622
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model = run.register_model(model_name=model_name,\n",
        "                           tags=run.tags,\n",
        "                           description = 'UNET model delineating ground mounted solar arrays in S2 imagery. Trained on multi-season data from Chesapeake Bay and NC',\n",
        "                           model_path='outputs/',\n",
        "                           model_framework = 'Tensorflow',\n",
        "                           model_framework_version= '2.0',\n",
        "                           datasets = [('training', train_dataset), ('evaluation', eval_dataset), ('testing', test_dataset)])\n",
        "print(model.name, model.id, model.version, sep='\\t')"
      ],
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "solar_May23\tsolar_May23:2\t2\n"
        }
      ],
      "execution_count": 19,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345790955
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# use the azure folder as our script folder\n",
        "source = 'Satellite_ComputerVision'\n",
        "util_folder = 'utils'\n",
        "script_folder = f'{source}/azure'\n",
        "script_file = 'train_solar.py'"
      ],
      "outputs": [],
      "execution_count": 17,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1638378482125
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# define the compute target\n",
        "ws.compute_targets\n",
        "mevansGPU = ws.compute_targets['mevansGPU']"
      ],
      "outputs": [],
      "execution_count": 20,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345802021
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "experiment_name = 'solar-nc-cpk'\n",
        "exp = Experiment(workspace = ws, name = experiment_name)"
      ],
      "outputs": [],
      "execution_count": 22,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345807382
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "custom_env = Environment.from_docker_image(\r\n",
        "    name = 'tf_training',\r\n",
        "    image = 'mcr.microsoft.com/azureml/openmpi4.1.0-cuda11.2-cudnn8-ubuntu20.04:20221010.v1',\r\n",
        "    container_registry=None,\r\n",
        "    conda_specification='/mnt/batch/tasks/shared/LS_root/mounts/clusters/mevans1/code/Users/mevans/Solar_UNet/conda_env-copy.yml',\r\n",
        "    pip_requirements=None)"
      ],
      "outputs": [],
      "execution_count": 21,
      "metadata": {
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345805116
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "RESPONSE = 'landcover'\n",
        "args = [\n",
        "    '--train_data', train_dataset.as_mount(),\n",
        "    '--eval_data', eval_dataset.as_mount(),\n",
        "    '--test_data', test_dataset.as_mount(),\n",
        "    '--model_id', model_name,\n",
        "    '--weights', '[1.0, 1.0]',\n",
        "    '--bias', 0,\n",
        "    '-lr', 0.0005,\n",
        "    '--epochs', 200,\n",
        "    '--epoch_start', 150,\n",
        "    '--batch', 16,\n",
        "    '--size', 11020,\n",
        "    '--kernel_size', 256,\n",
        "    '--response', f'{RESPONSE}',\n",
        "    '--bands', '[\"B2\", \"B3\", \"B4\", \"B8\", \"B11\", \"B12\"]',\n",
        "    '--splits', '[0]']\n",
        "\n",
        "src = ScriptRunConfig(source_directory='azure',\n",
        "                      script='train_solar.py', \n",
        "                      arguments=args,\n",
        "                      compute_target=mevansGPU,\n",
        "                      environment=custom_env)"
      ],
      "outputs": [],
      "execution_count": 23,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345941382
        }
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#  run the training job\n",
        "run = exp.submit(config=src, tags = dict({'splits':'None', 'model':'Unet', 'dataset':'NC CPK S2', 'normalization':'S2 moments', 'epochs':'150-200'}))\n",
        "run"
      ],
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 24,
          "data": {
            "text/plain": "Run(Experiment: solar-nc-cpk,\nId: solar-nc-cpk_1684345980_10f4f4d2,\nType: azureml.scriptrun,\nStatus: Starting)",
            "text/html": "<table style=\"width:100%\"><tr><th>Experiment</th><th>Id</th><th>Type</th><th>Status</th><th>Details Page</th><th>Docs Page</th></tr><tr><td>solar-nc-cpk</td><td>solar-nc-cpk_1684345980_10f4f4d2</td><td>azureml.scriptrun</td><td>Starting</td><td><a href=\"https://ml.azure.com/runs/solar-nc-cpk_1684345980_10f4f4d2?wsid=/subscriptions/76630eb1-4c8e-4e5f-82c7-f8676ff25bf0/resourcegroups/cic_ai/workspaces/landcover-ai&amp;tid=2a55ee5f-4b13-43bb-b2d8-0c693229ec8a\" target=\"_blank\" rel=\"noopener\">Link to Azure Machine Learning studio</a></td><td><a href=\"https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.script_run.ScriptRun?view=azure-ml-py\" target=\"_blank\" rel=\"noopener\">Link to Documentation</a></td></tr></table>"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": "Bad pipe message: %s [b'8\\xde(\\xabdJN#r\\xf9\\x05\\xd7\\xe1h\\xee\\x83\\xac\\xda \\xe7\\x80\\x7fCu\\x10\\xe4\\xd9\\x94\\xc0\\xbdj\\xc4\\xd9\\xcb\\x18/\\xde\\x06M\\xfe\\xff\\xe6\\xd0\\x9a\\xf4m\\x08\\xcb\\x8f\\x93p\\x00\\x08\\x13\\x02\\x13\\x03\\x13\\x01\\x00\\xff\\x01\\x00\\x00\\x8f\\x00\\x00\\x00\\x0e\\x00\\x0c\\x00\\x00\\t127.0.0.1\\x00\\x0b\\x00\\x04\\x03\\x00\\x01\\x02\\x00\\n\\x00\\x0c\\x00\\n\\x00\\x1d\\x00\\x17\\x00\\x1e\\x00\\x19\\x00\\x18\\x00#\\x00\\x00\\x00\\x16\\x00\\x00\\x00\\x17\\x00\\x00\\x00\\r\\x00\\x1e\\x00\\x1c\\x04\\x03\\x05\\x03\\x06\\x03\\x08\\x07\\x08\\x08\\x08\\t\\x08\\n\\x08\\x0b\\x08\\x04\\x08\\x05\\x08\\x06\\x04\\x01\\x05\\x01\\x06\\x01\\x00+\\x00\\x03\\x02\\x03\\x04']\nBad pipe message: %s [b\"\\x86o~1o\\x1bu.\\xf9\\xdd\\xc4\\xde0\\x92\\xfd\\x18$\\x8d\\x00\\x00|\\xc0,\\xc00\\x00\\xa3\\x00\\x9f\\xcc\\xa9\\xcc\\xa8\\xcc\\xaa\\xc0\\xaf\\xc0\\xad\\xc0\\xa3\\xc0\\x9f\\xc0]\\xc0a\\xc0W\\xc0S\\xc0+\\xc0/\\x00\\xa2\\x00\\x9e\\xc0\\xae\\xc0\\xac\\xc0\\xa2\\xc0\\x9e\\xc0\\\\\\xc0`\\xc0V\\xc0R\\xc0$\\xc0(\\x00k\\x00j\\xc0#\\xc0'\\x00g\\x00@\\xc0\\n\\xc0\\x14\\x009\\x008\\xc0\\t\\xc0\\x13\\x003\\x002\\x00\\x9d\\xc0\\xa1\\xc0\\x9d\\xc0Q\\x00\\x9c\\xc0\\xa0\\xc0\\x9c\\xc0P\\x00=\\x00<\\x005\\x00/\\x00\\x9a\\x00\\x99\\xc0\\x07\\xc0\\x11\\x00\\x96\\x00\\x05\\x00\\xff\\x01\\x00\\x00j\\x00\\x00\\x00\\x0e\\x00\\x0c\\x00\\x00\\t127.0.0.1\\x00\\x0b\\x00\\x04\\x03\\x00\\x01\\x02\\x00\\n\\x00\\x0c\\x00\\n\\x00\\x1d\\x00\\x17\\x00\\x1e\\x00\\x19\\x00\\x18\\x00#\\x00\\x00\\x00\\x16\\x00\\x00\\x00\\x17\\x00\\x00\\x00\\r\\x000\\x00.\\x04\\x03\\x05\\x03\\x06\\x03\\x08\\x07\\x08\\x08\\x08\\t\\x08\\n\\x08\\x0b\\x08\\x04\\x08\\x05\\x08\\x06\\x04\\x01\\x05\\x01\\x06\\x01\\x03\\x03\\x02\"]\nBad pipe message: %s [b'\\x01\\x02', b'', b'\\x02']\nBad pipe message: %s [b'\\x05\\x02\\x06']\nBad pipe message: %s [b'My\\xef\\x0c\\xa9\\x9eQ\\xc4)d6t\\xc2pc[y\\xe3\\x00\\x00\\xa2\\xc0\\x14\\xc0\\n\\x009\\x008\\x007\\x006\\x00\\x88\\x00\\x87\\x00\\x86\\x00\\x85\\xc0\\x19\\x00:\\x00\\x89\\xc0\\x0f\\xc0\\x05\\x005\\x00\\x84\\xc0\\x13\\xc0\\t\\x003\\x002\\x001\\x000\\x00\\x9a\\x00\\x99\\x00\\x98\\x00\\x97\\x00E\\x00D\\x00C\\x00B\\xc0\\x18\\x004\\x00\\x9b\\x00F\\xc0\\x0e\\xc0\\x04\\x00/\\x00\\x96\\x00A\\x00\\x07\\xc0', b'\\x07\\xc0\\x16\\x00\\x18\\xc0\\x0c\\xc0\\x02\\x00\\x05\\x00\\x04\\xc0\\x12\\xc0']\nBad pipe message: %s [b'\\x16\\x00\\x13\\x00\\x10\\x00\\r']\nBad pipe message: %s [b'\\xe4\\x12,{\\x15\\x94\\xb4\\x11\\xc9\\x13\\xb1\\xc4\\xb9\\xfa4\\x1a\\xebf\\x00\\x00\\xa2\\xc0\\x14\\xc0\\n\\x009\\x008\\x007\\x006\\x00\\x88\\x00\\x87\\x00\\x86\\x00\\x85\\xc0\\x19\\x00:\\x00\\x89\\xc0\\x0f\\xc0\\x05\\x00']\nBad pipe message: %s [b'\\x84\\xc0\\x13\\xc0\\t\\x003\\x002\\x001\\x000\\x00\\x9a\\x00\\x99\\x00\\x98\\x00\\x97\\x00E\\x00D\\x00C\\x00B\\xc0\\x18\\x004\\x00\\x9b\\x00F\\xc0\\x0e\\xc0\\x04\\x00/\\x00\\x96\\x00A\\x00\\x07\\xc0\\x11\\xc0']\nBad pipe message: %s [b'\\x16\\x00\\x18\\xc0\\x0c\\xc0']\nBad pipe message: %s [b'\\x05']\nBad pipe message: %s [b\"\\xdbvN\\x0c\\xe8D{\\x910\\x1c\\xd0V$B2\\x8d\\xd0\\xc0\\x00\\x00\\x86\\xc00\\xc0,\\xc0(\\xc0$\\xc0\\x14\\xc0\\n\\x00\\xa5\\x00\\xa3\\x00\\xa1\\x00\\x9f\\x00k\\x00j\\x00i\\x00h\\x009\\x008\\x007\\x006\\xc02\\xc0.\\xc0*\\xc0&\\xc0\\x0f\\xc0\\x05\\x00\\x9d\\x00=\\x005\\xc0/\\xc0+\\xc0'\\xc0#\\xc0\\x13\\xc0\\t\\x00\\xa4\\x00\\xa2\\x00\\xa0\\x00\\x9e\\x00g\\x00@\\x00?\\x00>\\x003\\x002\\x001\\x000\\xc01\\xc0-\\xc0)\\xc0%\\xc0\\x0e\\xc0\\x04\\x00\\x9c\\x00<\\x00/\\x00\\x9a\\x00\\x99\\x00\\x98\\x00\\x97\\x00\\x96\\x00\\x07\\xc0\\x11\\xc0\\x07\\xc0\\x0c\\xc0\\x02\\x00\\x05\\x00\\x04\\x00\\xff\\x02\\x01\\x00\\x00g\\x00\\x00\\x00\\x0e\\x00\\x0c\\x00\\x00\\t127.0.0.1\\x00\\x0b\\x00\\x04\\x03\\x00\\x01\\x02\\x00\\n\\x00\\x1c\\x00\\x1a\\x00\\x17\\x00\\x19\\x00\\x1c\\x00\\x1b\\x00\\x18\\x00\\x1a\\x00\\x16\\x00\\x0e\\x00\\r\\x00\\x0b\\x00\\x0c\\x00\\t\\x00\\n\\x00#\\x00\\x00\\x00\\r\\x00 \\x00\\x1e\", b'\\x06\\x02\\x06\\x03\\x05', b'', b'\\x03', b'\\x04\\x02\\x04', b'\\x01\\x03', b'\\x03', b'\\x02', b'\\x03']\nBad pipe message: %s [b'\\x02\\xc2~\\xda1\\xee\\xd4\\x9c\\xf3\\x08\\xf6']\nBad pipe message: %s [b\"O\\x11L,\\x99\\x00\\x00\\xf4\\xc00\\xc0,\\xc0(\\xc0$\\xc0\\x14\\xc0\\n\\x00\\xa5\\x00\\xa3\\x00\\xa1\\x00\\x9f\\x00k\\x00j\\x00i\\x00h\\x009\\x008\\x007\\x006\\x00\\x88\\x00\\x87\\x00\\x86\\x00\\x85\\xc0\\x19\\x00\\xa7\\x00m\\x00:\\x00\\x89\\xc02\\xc0.\\xc0*\\xc0&\\xc0\\x0f\\xc0\\x05\\x00\\x9d\\x00=\\x005\\x00\\x84\\xc0/\\xc0+\\xc0'\\xc0#\\xc0\\x13\\xc0\\t\\x00\\xa4\\x00\\xa2\\x00\\xa0\\x00\\x9e\\x00g\\x00@\"]\nBad pipe message: %s [b\"Es\\xa6z1/\\x87s'\\xd5\\xe5I\\x176b#G\\x10 \\xa4\\xad\\xc7\\x1e\\xcfrs\\x19H\\xaf\\x01\\x0cJTm\\xbe\\xd3X\\xca\\x94\\xebc'\\x8f\\xf6\\x8f\\xa6>\\x99x\\x0eS\\x00\\x08\\x13\\x02\\x13\\x03\\x13\\x01\\x00\\xff\\x01\\x00\\x00\\x8f\\x00\\x00\\x00\\x0e\\x00\\x0c\\x00\\x00\\t127.0.0.1\\x00\\x0b\\x00\\x04\\x03\\x00\\x01\\x02\\x00\\n\\x00\\x0c\\x00\\n\\x00\\x1d\\x00\\x17\\x00\\x1e\\x00\\x19\\x00\\x18\\x00#\\x00\\x00\\x00\\x16\\x00\\x00\\x00\\x17\\x00\\x00\\x00\\r\\x00\\x1e\\x00\\x1c\\x04\\x03\\x05\\x03\\x06\\x03\\x08\\x07\\x08\\x08\\x08\\t\", b'\\x08\\x0b\\x08\\x04\\x08\\x05\\x08']\nBad pipe message: %s [b'\\x01\\x05\\x01\\x06\\x01']\nBad pipe message: %s [b'\\x0b\\x13\\xc5a>C\\x18I\\xcaF\\x19\\xad\\x9e\\xf8\\xf0\\xf2\\x98\\x1e\\x00\\x00\\xa6\\xc0,\\xc00\\x00\\xa3\\x00\\x9f\\xcc\\xa9\\xcc\\xa8\\xcc\\xaa', b\"\\xc0\\xad\\xc0\\xa3\\xc0\\x9f\\xc0]\\xc0a\\xc0W\\xc0S\\xc0+\\xc0/\\x00\\xa2\\x00\\x9e\\xc0\\xae\\xc0\\xac\\xc0\\xa2\\xc0\\x9e\\xc0\\\\\\xc0`\\xc0V\\xc0R\\xc0$\\xc0(\\x00k\\x00j\\xc0s\\xc0w\\x00\\xc4\\x00\\xc3\\xc0#\\xc0'\\x00g\\x00@\\xc0r\\xc0v\\x00\\xbe\\x00\\xbd\\xc0\\n\\xc0\\x14\\x009\\x008\\x00\\x88\\x00\\x87\\xc0\\t\\xc0\\x13\\x003\\x002\\x00\\x9a\\x00\\x99\\x00E\\x00D\\xc0\\x07\\xc0\\x11\\xc0\\x08\\xc0\\x12\\x00\\x16\\x00\\x13\\x00\\x9d\\xc0\\xa1\\xc0\\x9d\\xc0Q\\x00\\x9c\\xc0\\xa0\\xc0\\x9c\\xc0P\\x00=\\x00\\xc0\\x00<\\x00\\xba\\x005\\x00\\x84\\x00/\\x00\\x96\\x00A\\x00\\x05\\x00\\n\\x00\\xff\\x01\\x00\\x00j\\x00\\x00\\x00\\x0e\\x00\\x0c\\x00\\x00\\t127.0.0.1\\x00\\x0b\\x00\\x04\\x03\\x00\\x01\\x02\\x00\\n\\x00\\x0c\\x00\\n\\x00\\x1d\\x00\\x17\\x00\", b'\\x19\\x00\\x18\\x00#\\x00\\x00\\x00\\x16\\x00\\x00\\x00\\x17\\x00\\x00\\x00\\r\\x000\\x00.\\x04\\x03\\x05\\x03\\x06\\x03\\x08\\x07']\nBad pipe message: %s [b'\\x08\\t\\x08\\n\\x08\\x0b\\x08']\nBad pipe message: %s [b'\\x05\\x08\\x06']\nBad pipe message: %s [b'\\x05\\x01\\x06', b'', b'\\x03\\x03']\nBad pipe message: %s [b'']\nBad pipe message: %s [b'', b'\\x02']\nBad pipe message: %s [b'\\x05\\x02\\x06']\nBad pipe message: %s [b'h\\x1f\\x8cg9\\x8bqQ^\\xdc\\xae\\x9b\\xdbz0\\xe6\\xc9\\x06\\x00\\x00>\\xc0\\x14\\xc0\\n\\x009\\x008\\x007\\x006\\xc0\\x0f\\xc0\\x05\\x005\\xc0\\x13\\xc0\\t\\x003\\x002\\x001\\x000\\xc0\\x0e\\xc0\\x04\\x00/\\x00\\x9a\\x00\\x99\\x00\\x98\\x00\\x97\\x00\\x96\\x00\\x07\\xc0\\x11\\xc0\\x07\\xc0\\x0c\\xc0\\x02\\x00\\x05\\x00\\x04\\x00\\xff\\x02\\x01\\x00\\x00C\\x00\\x00\\x00\\x0e\\x00\\x0c\\x00\\x00\\t127.0.0.1\\x00\\x0b\\x00\\x04\\x03\\x00\\x01\\x02\\x00\\n\\x00\\x1c\\x00\\x1a\\x00\\x17\\x00\\x19\\x00\\x1c\\x00\\x1b\\x00\\x18\\x00\\x1a\\x00\\x16\\x00\\x0e\\x00\\r\\x00\\x0b\\x00\\x0c\\x00']\nBad pipe message: %s [b'\\n\\x00#\\x00\\x00\\x00\\x0f\\x00']\nBad pipe message: %s [b'\\xc6\\xe7\\xcf\\xd7\\xd58\\x8b\\x04\\xeee\\xce\\r\\x84\\xbc\\xdd\\xcf\\x99\\xe1\\x00\\x00\\xa2\\xc0\\x14\\xc0\\n\\x009\\x008\\x007\\x006\\x00\\x88\\x00\\x87\\x00\\x86\\x00\\x85\\xc0\\x19\\x00:\\x00\\x89\\xc0\\x0f\\xc0\\x05\\x005\\x00\\x84\\xc0\\x13\\xc0\\t\\x003\\x002\\x001\\x000\\x00\\x9a\\x00\\x99\\x00\\x98\\x00\\x97\\x00E\\x00D\\x00C\\x00B\\xc0\\x18\\x004\\x00\\x9b\\x00F\\xc0\\x0e\\xc0\\x04\\x00/\\x00\\x96\\x00A\\x00\\x07\\xc0\\x11\\xc0\\x07\\xc0\\x16\\x00\\x18\\xc0\\x0c\\xc0\\x02\\x00\\x05\\x00\\x04\\xc0\\x12\\xc0\\x08\\x00\\x16\\x00\\x13\\x00\\x10\\x00\\r\\xc0\\x17\\x00\\x1b\\xc0']\nBad pipe message: %s [b'\\x03\\x00\\n\\x00\\x15\\x00\\x12\\x00\\x0f\\x00\\x0c\\x00']\nBad pipe message: %s [b'\\t\\x00\\x14\\x00\\x11\\x00\\x19\\x00\\x08\\x00\\x06\\x00\\x17\\x00\\x03\\xc0\\x10\\xc0\\x06\\xc0\\x15\\xc0\\x0b\\xc0\\x01']\nBad pipe message: %s [b'\\x04o\\x98r\\x8d\\x9dmQ\\xac/\\xa1\\xd2\\x1f\\xa5\\xbe\\xed\\xb4\\xff\\x00\\x00\\xf4\\xc00\\xc0,\\xc0(\\xc0$\\xc0\\x14\\xc0\\n\\x00\\xa5\\x00\\xa3\\x00\\xa1\\x00\\x9f\\x00k\\x00j\\x00i\\x00h\\x009\\x008\\x007\\x006\\x00\\x88']\nBad pipe message: %s [b\"\\xa0\\xf7\\x16S\\xd2\\x85\\xfa\\x11B+A\\x9b\\xe4>\\xd1\\n>\\xa7\\x00\\x00|\\xc0,\\xc00\\x00\\xa3\\x00\\x9f\\xcc\\xa9\\xcc\\xa8\\xcc\\xaa\\xc0\\xaf\\xc0\\xad\\xc0\\xa3\\xc0\\x9f\\xc0]\\xc0a\\xc0W\\xc0S\\xc0+\\xc0/\\x00\\xa2\\x00\\x9e\\xc0\\xae\\xc0\\xac\\xc0\\xa2\\xc0\\x9e\\xc0\\\\\\xc0`\\xc0V\\xc0R\\xc0$\\xc0(\\x00k\\x00j\\xc0#\\xc0'\\x00g\\x00@\\xc0\\n\\xc0\\x14\\x009\\x008\\xc0\\t\\xc0\\x13\\x003\\x002\\x00\\x9d\\xc0\\xa1\\xc0\\x9d\\xc0Q\\x00\\x9c\\xc0\\xa0\\xc0\\x9c\\xc0P\\x00=\\x00<\\x005\\x00/\\x00\\x9a\\x00\\x99\\xc0\\x07\\xc0\\x11\\x00\\x96\\x00\\x05\\x00\\xff\\x01\\x00\\x00j\\x00\\x00\\x00\\x0e\\x00\\x0c\\x00\\x00\\t127.0.0.1\\x00\\x0b\\x00\\x04\\x03\\x00\\x01\\x02\\x00\\n\\x00\\x0c\\x00\\n\\x00\\x1d\\x00\\x17\\x00\\x1e\\x00\\x19\\x00\\x18\\x00#\\x00\\x00\\x00\\x16\\x00\\x00\\x00\\x17\\x00\\x00\\x00\\r\\x000\\x00.\\x04\\x03\\x05\\x03\\x06\\x03\", b'\\x08\\x08\\x08\\t\\x08\\n\\x08', b'\\x04\\x08\\x05\\x08\\x06\\x04\\x01\\x05\\x01\\x06']\nBad pipe message: %s [b'', b'\\x03\\x03']\nBad pipe message: %s [b'']\nBad pipe message: %s [b'', b'\\x02']\nBad pipe message: %s [b'\\x05\\x02\\x06']\nBad pipe message: %s [b'\\xe1\\xc9v\\x04\\x0eH\\xba\\xff\\xc3\\xb7\\x93\\x0c\\xf7v\\x18\\x0b~\\xae\\x00\\x00\\xa6\\xc0,\\xc00\\x00\\xa3\\x00\\x9f\\xcc\\xa9\\xcc\\xa8\\xcc\\xaa\\xc0\\xaf\\xc0\\xad\\xc0\\xa3\\xc0\\x9f\\xc0]']\nBad pipe message: %s [b\"\\xc0W\\xc0S\\xc0+\\xc0/\\x00\\xa2\\x00\\x9e\\xc0\\xae\\xc0\\xac\\xc0\\xa2\\xc0\\x9e\\xc0\\\\\\xc0`\\xc0V\\xc0R\\xc0$\\xc0(\\x00k\\x00j\\xc0s\\xc0w\\x00\\xc4\\x00\\xc3\\xc0#\\xc0'\\x00g\\x00@\\xc0r\\xc0v\\x00\\xbe\\x00\\xbd\\xc0\\n\\xc0\\x14\\x009\\x008\\x00\\x88\\x00\\x87\\xc0\\t\\xc0\\x13\\x003\\x002\\x00\\x9a\\x00\\x99\\x00E\\x00D\\xc0\\x07\\xc0\\x11\\xc0\\x08\\xc0\\x12\\x00\\x16\\x00\\x13\\x00\\x9d\\xc0\\xa1\\xc0\\x9d\\xc0Q\\x00\\x9c\\xc0\\xa0\\xc0\\x9c\\xc0P\\x00=\\x00\\xc0\\x00<\\x00\\xba\\x005\\x00\\x84\\x00/\\x00\\x96\\x00A\\x00\\x05\\x00\\n\\x00\\xff\\x01\\x00\\x00j\\x00\\x00\\x00\\x0e\\x00\\x0c\\x00\\x00\\t127.0.0.1\\x00\\x0b\\x00\\x04\\x03\\x00\\x01\\x02\\x00\\n\\x00\\x0c\\x00\\n\\x00\\x1d\\x00\\x17\\x00\\x1e\\x00\\x19\\x00\\x18\\x00#\\x00\\x00\\x00\", b'\\x00\\x00\\x17\\x00\\x00\\x00\\r\\x000\\x00.\\x04\\x03\\x05\\x03\\x06\\x03\\x08\\x07\\x08\\x08']"
        }
      ],
      "execution_count": 24,
      "metadata": {
        "collapsed": true,
        "jupyter": {
          "source_hidden": false,
          "outputs_hidden": false
        },
        "nteract": {
          "transient": {
            "deleting": false
          }
        },
        "gather": {
          "logged": 1684345969907
        }
      }
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python38-azureml",
      "language": "python",
      "display_name": "Python 3.8 - AzureML"
    },
    "language_info": {
      "name": "python",
      "version": "3.8.5",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "kernel_info": {
      "name": "python38-azureml"
    },
    "microsoft": {
      "host": {
        "AzureML": {
          "notebookHasBeenCompleted": true
        }
      },
      "ms_spell_check": {
        "ms_spell_check_language": "en"
      }
    },
    "nteract": {
      "version": "nteract-front-end@1.0.0"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}