fix od batch scoring notebook (Azure#2220)

* fix od batch scoring notebook * format file * update broken path
vs-li · Apr 21, 2023 · 88ab31e · 88ab31e
1 parent 5210e44
commit 88ab31e
Showing 1 changed file with 36 additions and 7 deletions.
diff --git a/...sk-fridge-items-batch-scoring/image-object-detection-batch-scoring-non-mlflow-model.ipynb b/...sk-fridge-items-batch-scoring/image-object-detection-batch-scoring-non-mlflow-model.ipynb
@@ -799,7 +799,7 @@
     "## 6.2 Configure environment\n",
     "It is recommended to use the same envionment for model deployment as the model training, therefore we are creating the Environment object using the conda environment file downloaded as artifacts. We also need to specify the base image, which in case of vision tasks, is `mcr.microsoft.com/azureml/openmpi4.1.0-cuda11.1-cudnn8-ubuntu18.04`\n",
     "\n",
-    "To read more about environments, please follow this [notebook](./../../assets/environment/environment.ipynb)"
+    "To read more about environments, please follow this [notebook](./../../../assets/environment/environment.ipynb)"
    ]
   },
   {
@@ -813,7 +813,7 @@
     "env = Environment(\n",
     "    name=\"automl-images-env\",\n",
     "    description=\"environment for automl images inference\",\n",
-    "    image=\"mcr.microsoft.com/azureml/openmpi4.1.0-cuda11.1-cudnn8-ubuntu18.04\",\n",
+    "    image=\"mcr.microsoft.com/azureml/openmpi4.1.0-cuda11.1-cudnn8-ubuntu20.04\",\n",
     "    conda_file=\"artifact_downloads/outputs/conda_env_v_1_0_0.yml\",\n",
     ")"
    ]
@@ -1079,7 +1079,7 @@
     "# get the details of the job\n",
     "job_name = job.name\n",
     "batch_job = ml_client.jobs.get(name=job_name)\n",
-    "print(batch_job.status)\n",
+    "print(batch_job)\n",
     "# stream the job logs\n",
     "ml_client.jobs.stream(name=job_name)"
    ]
@@ -1097,13 +1097,42 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "output_dir = \"./scoring_results\"\n",
-    "ml_client.jobs.download(\n",
-    "    name=job.name, output_name=deployment.output_file_name, download_path=output_dir\n",
+    "from azureml.core import Experiment, Workspace\n",
+    "from azureml.pipeline.core import PipelineRun, StepRun, PortDataReference\n",
+    "\n",
+    "workspace_obj = Workspace(\n",
+    "    subscription_id=ml_client.subscription_id,\n",
+    "    resource_group=ml_client.resource_group_name,\n",
+    "    workspace_name=ml_client.workspace_name,\n",
     ")\n",
     "\n",
+    "# Get the Pipeline Run\n",
+    "experiment = Experiment(workspace=workspace_obj, name=batch_job.experiment_name)\n",
+    "pipeline_run = PipelineRun(experiment, batch_job.name)\n",
+    "\n",
+    "# Get the Step Run\n",
+    "step_run_id = pipeline_run.find_step_run(\"BatchScoring\")[0].id\n",
+    "node_id = pipeline_run.get_graph().node_name_dict[\"BatchScoring\"][0].node_id\n",
+    "print(\n",
+    "    \"Pipeline Run ID: {} Step Run ID: {}, Step Run Node ID: {}\".format(\n",
+    "        pipeline_run.id, step_run_id, node_id\n",
+    "    )\n",
+    ")\n",
+    "step_run = StepRun(experiment, step_run_id, pipeline_run.id, node_id)\n",
+    "\n",
+    "# Download Data\n",
+    "port_data_reference = step_run.get_output_data(\"score\")\n",
+    "port_data_reference.download(local_path=\".\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "# Print the first five lines of the output\n",
-    "result_file = os.path.join(output_dir, deployment.output_file_name)\n",
+    "result_file = os.path.join(\"azureml\", step_run_id, \"score\", deployment.output_file_name)\n",
     "with open(result_file) as f:\n",
     "    for x in range(5):\n",
     "        print(next(f))"