jprdonnelly/MachineLearningNotebooks
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

update samples from Release-60 as a part of SDK release

Browse Source
This commit is contained in:
amlrelsa-ms
2020-08-04 06:12:06 +00:00
parent 0ab8b141ee
commit 5b684070e1
62 changed files with 278 additions and 16066 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
tutorials/machine-learning-pipelines-advanced/tutorial-pipeline-batch-scoring-classification.ipynb
View File

@@ -124,9 +124,7 @@
"\n",
"input_images = Dataset.File.from_files((batchscore_blob, \"batchscoring/images/\"))\n",
"label_ds = Dataset.File.from_files((batchscore_blob, \"batchscoring/labels/\"))\n",
"output_dir = PipelineData(name=\"scores\", \n",
" datastore=def_data_store, \n",
" output_path_on_compute=\"batchscoring/results\")"
"output_dir = PipelineData(name=\"scores\", datastore=def_data_store)"
]
},
{
@@ -142,15 +140,13 @@
"metadata": {},
"outputs": [],
"source": [
"input_images = input_images.register(workspace = ws, name = \"input_images\")\n",
"label_ds = label_ds.register(workspace = ws, name = \"label_ds\", create_new_version=True)"
"input_images = input_images.register(workspace=ws, name=\"input_images\")\n",
"label_ds = label_ds.register(workspace=ws, name=\"label_ds\", create_new_version=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"cell_type": "markdown",
"metadata": {},
"outputs": [],
"source": [
"## Download and register the model"
]
@@ -277,7 +273,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Before running the pipeline, you create an object that defines the python environment and dependencies needed by your script `batch_scoring.py`. The main dependency required is Tensorflow, but you also install `azureml-defaults` for background processes from the SDK. Create a `RunConfiguration` object using the dependencies, and also specify Docker and Docker-GPU support."
"Before running the pipeline, you create an object that defines the python environment and dependencies needed by your script `batch_scoring.py`. The main dependency required is Tensorflow, but you also install `azureml-core` and `azureml-dataset-runtime[fuse]` for background processes from the SDK. Create a `RunConfiguration` object using the dependencies, and also specify Docker and Docker-GPU support."
]
},
{
@@ -291,7 +287,7 @@
"from azureml.core.runconfig import DEFAULT_GPU_IMAGE\n",
"\n",
"cd = CondaDependencies.create(pip_packages=[\"tensorflow-gpu==1.15.2\",\n",
" \"azureml-core\", \"azureml-dataprep[fuse]\"])\n",
" \"azureml-core\", \"azureml-dataset-runtime[fuse]\"])\n",
"\n",
"env = Environment(name=\"parallelenv\")\n",
"env.python.conda_dependencies=cd\n",
@@ -319,6 +315,7 @@
" entry_script=\"batch_scoring.py\",\n",
" source_directory=\"scripts\",\n",
" output_action=\"append_row\",\n",
" append_row_file_name=\"parallel_run_step.txt\",\n",
" mini_batch_size=\"20\",\n",
" error_threshold=1,\n",
" compute_target=compute_target,\n",
@@ -424,15 +421,15 @@
"metadata": {},
"outputs": [],
"source": [
"batch_run = next(pipeline_run.get_children())\n",
"batch_output = batch_run.get_output_data(\"scores\")\n",
"batch_output.download(local_path=\"inception_results\")\n",
"\n",
"import pandas as pd\n",
"for root, dirs, files in os.walk(\"inception_results\"):\n",
" for file in files:\n",
" if file.endswith(\"parallel_run_step.txt\"):\n",
" result_file = os.path.join(root,file)\n",
"import tempfile\n",
"\n",
"batch_run = pipeline_run.find_step_run(batch_score_step.name)[0]\n",
"batch_output = batch_run.get_output_data(output_dir.name)\n",
"\n",
"target_dir = tempfile.mkdtemp()\n",
"batch_output.download(local_path=target_dir)\n",
"result_file = os.path.join(target_dir, batch_output.path_on_datastore, parallel_run_config.append_row_file_name)\n",
"\n",
"df = pd.read_csv(result_file, delimiter=\":\", header=None)\n",
"df.columns = [\"Filename\", \"Prediction\"]\n",