Merge pull request #222714 from shubhamiit/sonishubham/docUpdate

AutoML Images document changes

Author: prmerger-automator[bot]

articles/machine-learning/how-to-auto-train-image-models.md

@@ -207,9 +207,9 @@ Classification | Regression | Time Series Forecasting
 
 With additional algorithms below.
 
-* [Image Classification Multi-class Algorithms](how-to-auto-train-image-models.md#supported-model-algorithms)
-* [Image Classification Multi-label Algorithms](how-to-auto-train-image-models.md#supported-model-algorithms)
-* [Image Object Detection Algorithms](how-to-auto-train-image-models.md#supported-model-algorithms)
+* [Image Classification Multi-class Algorithms](how-to-auto-train-image-models.md#supported-model-architectures)
+* [Image Classification Multi-label Algorithms](how-to-auto-train-image-models.md#supported-model-architectures)
+* [Image Object Detection Algorithms](how-to-auto-train-image-models.md#supported-model-architectures)
 * [NLP Text Classification Multi-label Algorithms](how-to-auto-train-nlp-models.md#language-settings)
 * [NLP Text Named Entity Recognition (NER) Algorithms](how-to-auto-train-nlp-models.md#language-settings)
 

articles/machine-learning/how-to-configure-auto-train.md

@@ -145,7 +145,7 @@ env = Environment(
 )
 ```
 
-Use the following model specific arguments to submit the script. For more details on arguments, refer to [model specific hyperparameters](reference-automl-images-hyperparameters.md#model-specific-hyperparameters) and for supported object detection model names refer to the [supported model algorithm section](how-to-auto-train-image-models.md#supported-model-algorithms).
+Use the following model specific arguments to submit the script. For more details on arguments, refer to [model specific hyperparameters](how-to-auto-train-image-models.md#configure-experiments) and for supported object detection model names refer to the [supported model architecture section](how-to-auto-train-image-models.md#supported-model-architectures).
 
 To get the argument values needed to create the batch scoring model, refer to the scoring scripts generated under the outputs folder of the AutoML training runs. Use the hyperparameter values available in the model settings variable inside the scoring file for the best child run.
 
@@ -778,7 +778,7 @@ assert batch_size == img_data.shape[0]
 
 # [Object detection with Faster R-CNN or RetinaNet](#tab/object-detect-cnn)
 
-For object detection with the Faster R-CNN algorithm, follow the same preprocessing steps as image classification, except for image cropping. You can resize the image with height `600` and width `800`. You can get the expected input height and width with the following code.
+For object detection with the Faster R-CNN architecture, follow the same preprocessing steps as image classification, except for image cropping. You can resize the image with height `600` and width `800`. You can get the expected input height and width with the following code.
 
 ```python
 batch, channel, height_onnx, width_onnx = session.get_inputs()[0].shape
@@ -841,7 +841,7 @@ assert batch_size == img_data.shape[0]
 
 # [Object detection with YOLO](#tab/object-detect-yolo)
 
-For object detection with the YOLO algorithm, follow the same preprocessing steps as image classification, except for image cropping. You can resize the image with height `600` and width `800`, and get the expected input height and width with the following code.
+For object detection with the YOLO architecture, follow the same preprocessing steps as image classification, except for image cropping. You can resize the image with height `600` and width `800`, and get the expected input height and width with the following code.
 
 ```python
 batch, channel, height_onnx, width_onnx = session.get_inputs()[0].shape
@@ -1144,7 +1144,7 @@ for image_idx, class_idx in zip(image_wise_preds[0], image_wise_preds[1]):
     print('image: {}, class_index: {}, class_name: {}'.format(image_files[image_idx], class_idx, classes[class_idx]))
 ```
 
-For multi-class and multi-label classification, you can follow the same steps mentioned earlier for all the supported algorithms in AutoML.
+For multi-class and multi-label classification, you can follow the same steps mentioned earlier for all the supported model architectures in AutoML.
 
 
 # [Object detection with Faster R-CNN or RetinaNet](#tab/object-detect-cnn)

articles/machine-learning/how-to-inference-onnx-automl-image-models.md

@@ -44,7 +44,7 @@ The source JSON schema can be found at https://azuremlsdk2.blob.core.windows.net
 | `validation_data` | object |  The validation data to be used within the job. It should contain both training features and label column (optionally a sample weights column). If `validation_data` is specified, then `training_data` and `target_column_name` parameters must be specified. For more information on keys and their descriptions, see [Training or validation data](#training-or-validation-data) section. For an example, see [Consume data](./how-to-auto-train-image-models.md?tabs=cli#consume-data) section| |  |
 | `validation_data_size` | float |  What fraction of the data to hold out for validation when user validation data isn't specified. | A value in range (0.0, 1.0) |  |
 | `limits` | object | Dictionary of limit configurations of the job. The key is name for the limit within the context of the job and the value is limit value. For more information, see [Configure your experiment settings](./how-to-auto-train-image-models.md?tabs=cli#job-limits) section. | | |
-| `training_parameters` | object | Dictionary containing training parameters for the job. Provide an object that has keys as listed in following sections. <br> - [Model agnostic hyperparameters](./reference-automl-images-hyperparameters.md#model-agnostic-hyperparameters) <br> - [Image classification (multi-class and multi-label) specific hyperparameters](./reference-automl-images-hyperparameters.md#image-classification-multi-class-and-multi-label-specific-hyperparameters). <br> <br> For an example, see [Supported model algorithms](./how-to-auto-train-image-models.md?tabs=cli#supported-model-algorithms) section. | | |
+| `training_parameters` | object | Dictionary containing training parameters for the job. Provide an object that has keys as listed in following sections. <br> - [Model agnostic hyperparameters](./reference-automl-images-hyperparameters.md#model-agnostic-hyperparameters) <br> - [Image classification (multi-class and multi-label) specific hyperparameters](./reference-automl-images-hyperparameters.md#image-classification-multi-class-and-multi-label-specific-hyperparameters). <br> <br> For an example, see [Supported model architectures](./how-to-auto-train-image-models.md?tabs=cli#supported-model-architectures) section. | | |
 | `sweep` | object | Dictionary containing sweep parameters for the job. It has two keys - `sampling_algorithm` (**required**) and `early_termination`. For more information and an example, see [Sampling methods for the sweep](./how-to-auto-train-image-models.md?tabs=cli#sampling-methods-for-the-sweep), [Early termination policies](./how-to-auto-train-image-models.md?tabs=cli#early-termination-policies) sections. | | |
 | `search_space` | object | Dictionary of the hyperparameter search space. The key is the name of the hyperparameter and the value is the parameter expression. The user can find the possible hyperparameters from parameters specified for `training_parameters` key. For an example, see [Sweeping hyperparameters for your model](./how-to-auto-train-image-models.md?tabs=cli#manually-sweeping-model-hyperparameters) section. | | |
 | `search_space.<hyperparameter>` | object | There are two types of hyperparameters: <br> - **Discrete Hyperparameters**: Discrete hyperparameters are specified as a [`choice`](./reference-yaml-job-sweep.md#choice) among discrete values. `choice` can be one or more comma-separated values, a `range` object, or any arbitrary `list` object. Advanced discrete hyperparameters can also be specified using a distribution - [`randint`](./reference-yaml-job-sweep.md#randint), [`qlognormal`, `qnormal`](./reference-yaml-job-sweep.md#qlognormal-qnormal), [`qloguniform`, `quniform`](./reference-yaml-job-sweep.md#qloguniform-quniform). For more information, see this [section](./how-to-tune-hyperparameters.md#discrete-hyperparameters). <br> - **Continuous hyperparameters**: Continuous hyperparameters are specified as a distribution over a continuous range of values. Currently supported distributions are - [`lognormal`, `normal`](./reference-yaml-job-sweep.md#lognormal-normal), [`loguniform`](./reference-yaml-job-sweep.md#loguniform), [`uniform`](./reference-yaml-job-sweep.md#uniform). For more information, see this [section](./how-to-tune-hyperparameters.md#continuous-hyperparameters). <br> <br> See [Parameter expressions](./reference-yaml-job-sweep.md#parameter-expressions) for the set of possible expressions to use.  | | |

articles/machine-learning/reference-automl-images-cli-classification.md

@@ -31,7 +31,7 @@ For information on all the keys in Yaml syntax, see [Yaml syntax](./reference-au
 | --- | ---- | ----------- | -------------- | ------------- |
 | `task` | const | **Required.** The type of AutoML task. | `image_instance_segmentation` | `image_instance_segmentation` |
 | `primary_metric` | string |  The metric that AutoML will optimize for model selection. |`mean_average_precision` | `mean_average_precision` |
-| `training_parameters` | object | Dictionary containing training parameters for the job. Provide an object that has keys as listed in following sections. <br> - [Model specific hyperparameters](./reference-automl-images-hyperparameters.md#model-specific-hyperparameters) for maskrcnn_* (if you're using maskrcnn_* for instance segmentation) <br> - [Model agnostic hyperparameters](./reference-automl-images-hyperparameters.md#model-agnostic-hyperparameters) <br> - [Object detection and instance segmentation task specific hyperparameters](./reference-automl-images-hyperparameters.md#object-detection-and-instance-segmentation-task-specific-hyperparameters). <br> <br> For an example, see [Supported model algorithms](./how-to-auto-train-image-models.md?tabs=cli#supported-model-algorithms) section.| | |
+| `training_parameters` | object | Dictionary containing training parameters for the job. Provide an object that has keys as listed in following sections. <br> - [Model specific hyperparameters](./reference-automl-images-hyperparameters.md#model-specific-hyperparameters) for maskrcnn_* (if you're using maskrcnn_* for instance segmentation) <br> - [Model agnostic hyperparameters](./reference-automl-images-hyperparameters.md#model-agnostic-hyperparameters) <br> - [Object detection and instance segmentation task specific hyperparameters](./reference-automl-images-hyperparameters.md#object-detection-and-instance-segmentation-task-specific-hyperparameters). <br> <br> For an example, see [Supported model architectures](./how-to-auto-train-image-models.md?tabs=cli#supported-model-architectures) section.| | |
 
 ## Remarks
 

articles/machine-learning/reference-automl-images-cli-instance-segmentation.md

@@ -32,7 +32,7 @@ For information on all the keys in Yaml syntax, see [Yaml syntax](./reference-au
 | --- | ---- | ----------- | -------------- | ------------- |
 | `task` | const | **Required.** The type of AutoML task. | `image_object_detection` | `image_object_detection` |
 | `primary_metric` | string |  The metric that AutoML will optimize for model selection. |`mean_average_precision` | `mean_average_precision` |
-| `training_parameters` | object | Dictionary containing training parameters for the job. Provide an object that has keys as listed in following sections. <br> - [Model Specific Hyperparameters](./reference-automl-images-hyperparameters.md#model-specific-hyperparameters) for yolov5 (if you're using yolov5 for object detection) <br> - [Model agnostic hyperparameters](./reference-automl-images-hyperparameters.md#model-agnostic-hyperparameters) <br> - [Object detection and instance segmentation task specific hyperparameters](./reference-automl-images-hyperparameters.md#object-detection-and-instance-segmentation-task-specific-hyperparameters). <br> <br> For an example, see [Supported model algorithms](./how-to-auto-train-image-models.md?tabs=cli#supported-model-algorithms) section.| | |
+| `training_parameters` | object | Dictionary containing training parameters for the job. Provide an object that has keys as listed in following sections. <br> - [Model Specific Hyperparameters](./reference-automl-images-hyperparameters.md#model-specific-hyperparameters) for yolov5 (if you're using yolov5 for object detection) <br> - [Model agnostic hyperparameters](./reference-automl-images-hyperparameters.md#model-agnostic-hyperparameters) <br> - [Object detection and instance segmentation task specific hyperparameters](./reference-automl-images-hyperparameters.md#object-detection-and-instance-segmentation-task-specific-hyperparameters). <br> <br> For an example, see [Supported model architectures](./how-to-auto-train-image-models.md?tabs=cli#supported-model-architectures) section.| | |
 
 ## Remarks
 

articles/machine-learning/reference-automl-images-cli-object-detection.md

@@ -22,11 +22,11 @@ ms.date: 01/18/2022
 
 Learn which hyperparameters are available specifically for computer vision tasks in automated ML experiments.
 
-With support for computer vision tasks, you can control the model algorithm and sweep hyperparameters. These model algorithms and hyperparameters are passed in as the parameter space for the sweep. While many of the hyperparameters exposed are model-agnostic, there are instances where hyperparameters are model-specific or task-specific.
+With support for computer vision tasks, you can control the model architecture and sweep hyperparameters. These model architectures and hyperparameters are passed in as the parameter space for the sweep. While many of the hyperparameters exposed are model-agnostic, there are instances where hyperparameters are model-specific or task-specific.
 
 ## Model-specific hyperparameters
 
-This table summarizes hyperparameters specific to the `yolov5` algorithm.
+This table summarizes hyperparameters specific to the `yolov5` architecture.
 
 | Parameter name       | Description           | Default  |
 | ------------- |-------------|----|
@@ -98,7 +98,7 @@ The following table summarizes hyperparmeters for image classification (multi-cl
 The following hyperparameters are for object detection and instance segmentation tasks.
 
 > [!WARNING]
-> These parameters are not supported with the `yolov5` algorithm. See the [model specific hyperparameters](#model-specific-hyperparameters) section for `yolov5` supported hyperparmeters.
+> These parameters are not supported with the `yolov5` architecture. See the [model specific hyperparameters](#model-specific-hyperparameters) section for `yolov5` supported hyperparmeters.
 
 | Parameter name       | Description           | Default  |
 | ------------- |-------------|-----|

articles/machine-learning/reference-automl-images-hyperparameters.md

@@ -137,7 +137,7 @@ This compute is used later while creating the task specific `automl` job.
 
 ## Experiment setup
 
-You can use an Experiment to track your model training runs.
+You can use an Experiment to track your model training jobs.
 
 # [Azure CLI](#tab/cli)
 [!INCLUDE [cli v2](../../includes/machine-learning-cli-v2.md)]
@@ -309,7 +309,7 @@ You can create data inputs from training and validation MLTable with the followi
 
 ## Configure your object detection experiment
 
-To configure automated ML runs for image-related tasks, create a task specific AutoML job.
+To configure automated ML jobs for image-related tasks, create a task specific AutoML job.
 
 # [Azure CLI](#tab/cli)
 [!INCLUDE [cli v2](../../includes/machine-learning-cli-v2.md)]
@@ -377,7 +377,7 @@ When you've configured your AutoML Job to the desired settings, you can submit t
 
 ### Manual hyperparameter sweeping for image tasks
 
-In your AutoML job, you can specify the model algorithms by using `model_name` parameter and configure the settings to perform a hyperparameter sweep over a defined search space to find the optimal model.
+In your AutoML job, you can specify the model architectures by using `model_name` parameter and configure the settings to perform a hyperparameter sweep over a defined search space to find the optimal model.
 
 In this example, we will train an object detection model with `yolov5` and `fasterrcnn_resnet50_fpn`, both of which are pretrained on COCO, a large-scale object detection, segmentation, and captioning dataset that contains over thousands of labeled images with over 80 label categories.
 
@@ -403,11 +403,11 @@ limits:
 
 ---
 
-The following code defines the search space in preparation for the hyperparameter sweep for each defined algorithm, `yolov5` and `fasterrcnn_resnet50_fpn`.  In the search space, specify the range of values for `learning_rate`, `optimizer`, `lr_scheduler`, etc., for AutoML to choose from as it attempts to generate a model with the optimal primary metric. If hyperparameter values are not specified, then default values are used for each algorithm.
+The following code defines the search space in preparation for the hyperparameter sweep for each defined architecture, `yolov5` and `fasterrcnn_resnet50_fpn`.  In the search space, specify the range of values for `learning_rate`, `optimizer`, `lr_scheduler`, etc., for AutoML to choose from as it attempts to generate a model with the optimal primary metric. If hyperparameter values are not specified, then default values are used for each architecture.
 
 For the tuning settings, use random sampling to pick samples from this parameter space by using the `random` sampling_algorithm. The job limits configured above, tells automated ML to try a total of 10 trials with these different samples, running two trials at a time on our compute target, which was set up using four nodes. The more parameters the search space has, the more trials you need to find optimal models.
 
-The Bandit early termination policy is also used. This policy terminates poor performing configurations; that is, those configurations that are not within 20% slack of the best performing configuration, which significantly saves compute resources.
+The Bandit early termination policy is also used. This policy terminates poor performing trials; that is, those trials that are not within 20% slack of the best performing trial, which significantly saves compute resources.
 
 # [Azure CLI](#tab/cli)
 
@@ -482,9 +482,9 @@ When you've configured your AutoML Job to the desired settings, you can submit t
 
 ---
 
-When doing a hyperparameter sweep, it can be useful to visualize the different configurations that were tried using the HyperDrive UI. You can navigate to this UI by going to the 'Child runs' tab in the UI of the main automl_image_run from above, which is the HyperDrive parent run. Then you can go into the 'Child runs' tab of this one.
+When doing a hyperparameter sweep, it can be useful to visualize the different trials that were tried using the HyperDrive UI. You can navigate to this UI by going to the 'Child jobs' tab in the UI of the main automl_image_job from above, which is the HyperDrive parent job. Then you can go into the 'Child jobs' tab of this one.
 
-Alternatively, here below you can see directly the HyperDrive parent run and navigate to its 'Child runs' tab:
+Alternatively, here below you can see directly the HyperDrive parent job and navigate to its 'Child jobs' tab:
 
 # [Azure CLI](#tab/cli)
 
@@ -506,9 +506,9 @@ hd_job
 
 ## Register and deploy model
 
-Once the run completes, you can register the model that was created from the best run (configuration that resulted in the best primary metric). You can either register the model after downloading or by specifying the azureml path with corresponding jobid.  
+Once the job completes, you can register the model that was created from the best trial (configuration that resulted in the best primary metric). You can either register the model after downloading or by specifying the azureml path with corresponding jobid.  
 
-### Get the best run
+### Get the best trial
 
 
 # [Azure CLI](#tab/cli)