From 0c424abdd6d183117513837ff8cfe8da3bc31f9b Mon Sep 17 00:00:00 2001 From: Javier Date: Fri, 15 Jan 2021 13:11:23 +0000 Subject: [PATCH] Fix docs for HelloWorld (#360) * Fix docs for HellowWorld * Fix docs for HellowWorld * Add more details --- InnerEye/ML/configs/segmentation/HelloWorld.py | 12 ++++++++---- docs/hello_world_model.md | 9 ++++++--- 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/InnerEye/ML/configs/segmentation/HelloWorld.py b/InnerEye/ML/configs/segmentation/HelloWorld.py index 58b9ba57..d7ada2cd 100644 --- a/InnerEye/ML/configs/segmentation/HelloWorld.py +++ b/InnerEye/ML/configs/segmentation/HelloWorld.py @@ -26,9 +26,13 @@ class HelloWorld(SegmentationModelBase): 2) Configure the UNet3D implemented in this package 3) Configure Azure HyperDrive based parameter search - - This model can be trained from the commandline: ../InnerEye/runner.py --model=HelloWorld - - If you have set up AzureML then parameter search can be performed for this model by running: - ../InnerEye/runner.py --model=HelloWorld --hyperdrive=True + * This model can be trained from the commandline: python InnerEye/runner.py --model=HelloWorld + + * If you want to test that your AzureML workspace is working: + - Upload to datasets storage account for your AzureML workspace: Test/ML/test_data/dataset.csv and + Test/ML/test_data/train_and_test_data and name the folder "hello_world" + - If you have set up AzureML then parameter search can be performed for this model by running: + python InnerEye/ML/ runner.py --model=HelloWorld --azureml=True --hyperdrive=True In this example, the model is trained on 2 input image channels channel1 and channel2, and predicts 2 foreground classes region, region_1. @@ -39,7 +43,7 @@ class HelloWorld(SegmentationModelBase): super().__init__( # Data definition - in this section we define where to load the dataset from local_dataset=full_ml_test_data_path(), - + azure_dataset_id="hello_world", # Model definition - in this section we define what model to use and some related configurations architecture="UNet3D", feature_channels=[4], diff --git a/docs/hello_world_model.md b/docs/hello_world_model.md index 5b238a82..eaf37184 100644 --- a/docs/hello_world_model.md +++ b/docs/hello_world_model.md @@ -7,6 +7,9 @@ We have created this file to demonstrate how to: 1. Configure the UNet3D implemented in this package 1. Configure Azure HyperDrive based parameter search -- This model can be trained from the commandline: ../InnerEye/runner.py --model=HelloWorld -- If you have set up AzureML then parameter search can be performed for this model by running: -../InnerEye/runner.py --model=HelloWorld --hyperdrive=True +* This model can be trained from the commandline, from the root of the repo: `python InnerEye/runner.py --model=HelloWorld` +* If you want to test your AzureML workspace with the HelloWorld model: + * Upload to datasets storage account for your AzureML workspace: `Test/ML/test_data/dataset.csv` and + `Test/ML/test_data/train_and_test_data` and name the folder "hello_world" + * If you have set up AzureML then parameter search can be performed for this model by running: + `python InnerEye/ML/ runner.py --model=HelloWorld --azureml=True --hyperdrive=True`