document changes

Author: shubham soni

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

@@ -10,7 +10,7 @@ ms.subservice: automl
 ms.custom: event-tier1-build-2022, ignite-2022
 ms.topic: how-to
 ms.date: 07/13/2022
-#Customer intent: I'm a data scientist with ML knowledge in the computer vision space, looking to build ML models using image data in Azure Machine Learning with full control of the model algorithm, hyperparameters, and training and deployment environments.
+#Customer intent: I'm a data scientist with ML knowledge in the computer vision space, looking to build ML models using image data in Azure Machine Learning with full control of the model architecture, hyperparameters, and training and deployment environments.
 ---
 
 # Set up AutoML to train computer vision models
@@ -285,18 +285,18 @@ Automatic sweeps can yield competitive results for many datasets. Additionally,
 
 An AutoML training job uses a primary metric for model optimization and hyperparameter tuning. The primary metric depends on the task type as shown below; other primary metric values are currently not supported. 
 
-* `accuracy` for IMAGE_CLASSIFICATION
-* `iou` for IMAGE_CLASSIFICATION_MULTILABEL
-* `mean_average_precision` for IMAGE_OBJECT_DETECTION
-* `mean_average_precision` for IMAGE_INSTANCE_SEGMENTATION
+* Accuracy for image classification
+* Intersection over union for image classification multilabel
+* Mean average precision for image object detection
+* Mean average precision for image instance segmentation
 
 ### Job limits
 
 You can control the resources spent on your AutoML Image training job by specifying the `timeout_minutes`, `max_trials` and the `max_concurrent_trials` for the job in limit settings as described in the below example.
 
 Parameter | Detail
 -----|----
-`max_trials` |  Parameter for maximum number of configurations to sweep. Must be an integer between 1 and 1000. When exploring just the default hyperparameters for a given model algorithm, set this parameter to 1. The default value is 1.
+`max_trials` |  Parameter for maximum number of configurations to sweep. Must be an integer between 1 and 1000. When exploring just the default hyperparameters for a given model architecture, set this parameter to 1. The default value is 1.
 `max_concurrent_trials`| Maximum number of runs that can run concurrently. If specified, must be an integer between 1 and 100.  The default value is 1. <br><br> **NOTE:** <li> The number of concurrent runs is gated on the resources available in the specified compute target. Ensure that the compute target has the available resources for the desired concurrency.  <li> `max_concurrent_trials` is capped at `max_trials` internally. For example, if user sets `max_concurrent_trials=4`, `max_trials=2`, values would be internally updated as `max_concurrent_trials=2`, `max_trials=2`.
 `timeout_minutes`| The amount of time in minutes before the experiment terminates. If none specified, default experiment timeout_minutes is seven days (maximum 60 days)
 
@@ -357,26 +357,26 @@ A number of runs between 10 and 20 will likely work well on many datasets. The [
 
 ### Individual runs
 
-In individual runs, you directly control the model algorithm and hyperparameters. The model algorithm is passed via the `model_name` parameter.
+In individual runs, you directly control the model architecture and hyperparameters. The model architecture is passed via the `model_name` parameter.
 
-#### Supported model algorithms
+#### Supported model architectures
 
 The following table summarizes the supported models for each computer vision task.
 
-Task |  Model algorithms | String literal syntax<br> ***`default_model`\**** denoted with \*
+Task |  model architectures | String literal syntax<br> ***`default_model`\**** denoted with \*
 ---|----------|----------
 Image classification<br> (multi-class and multi-label)| **MobileNet**: Light-weighted models for mobile applications <br> **ResNet**: Residual networks<br> **ResNeSt**: Split attention networks<br> **SE-ResNeXt50**: Squeeze-and-Excitation networks<br> **ViT**: Vision transformer networks| `mobilenetv2`   <br>`resnet18` <br>`resnet34` <br> `resnet50`  <br> `resnet101` <br> `resnet152`    <br> `resnest50` <br> `resnest101`  <br> `seresnext`  <br> `vits16r224` (small) <br> ***`vitb16r224`\**** (base) <br>`vitl16r224` (large)|
 Object detection | **YOLOv5**: One stage object detection model   <br>  **Faster RCNN ResNet FPN**: Two stage object detection models  <br> **RetinaNet ResNet FPN**: address class imbalance with Focal Loss <br> <br>*Note: Refer to [`model_size` hyperparameter](reference-automl-images-hyperparameters.md#model-specific-hyperparameters) for YOLOv5 model sizes.*| ***`yolov5`\**** <br> `fasterrcnn_resnet18_fpn` <br> `fasterrcnn_resnet34_fpn` <br> `fasterrcnn_resnet50_fpn` <br> `fasterrcnn_resnet101_fpn` <br> `fasterrcnn_resnet152_fpn` <br> `retinanet_resnet50_fpn` 
 Instance segmentation | **MaskRCNN ResNet FPN**| `maskrcnn_resnet18_fpn` <br> `maskrcnn_resnet34_fpn` <br> ***`maskrcnn_resnet50_fpn`\****  <br> `maskrcnn_resnet101_fpn` <br> `maskrcnn_resnet152_fpn`
 
 
-In addition to controlling the model algorithm, you can also tune hyperparameters used for model training. While many of the hyperparameters exposed are model-agnostic, there are instances where hyperparameters are task-specific or model-specific. [Learn more about the available hyperparameters for these instances](reference-automl-images-hyperparameters.md). 
+In addition to controlling the model architecture, you can also tune hyperparameters used for model training. While many of the hyperparameters exposed are model-agnostic, there are instances where hyperparameters are task-specific or model-specific. [Learn more about the available hyperparameters for these instances](reference-automl-images-hyperparameters.md). 
 
 # [Azure CLI](#tab/cli)
 
 [!INCLUDE [cli v2](../../includes/machine-learning-cli-v2.md)]
 
-If you wish to use the default hyperparameter values for a given algorithm (say yolov5), you can specify it using the model_name key in the training_parameters section. For example,
+If you wish to use the default hyperparameter values for a given architecture (say yolov5), you can specify it using the model_name key in the training_parameters section. For example,
 
 ```yaml
 training_parameters:
@@ -386,7 +386,7 @@ training_parameters:
 
  [!INCLUDE [sdk v2](../../includes/machine-learning-sdk-v2.md)]
 
-If you wish to use the default hyperparameter values for a given algorithm (say yolov5), you can specify it using the model_name parameter in the set_training_parameters method of the task specific `automl` job. For example,
+If you wish to use the default hyperparameter values for a given architecture (say yolov5), you can specify it using the model_name parameter in the set_training_parameters method of the task specific `automl` job. For example,
 
 ```python
 image_object_detection_job.set_training_parameters(model_name="yolov5")
@@ -439,9 +439,9 @@ search_space:
 
 #### Define the parameter search space
 
-You can define the model algorithms and hyperparameters to sweep in the parameter space. You can either specify a single model algorithm or multiple ones. 
+You can define the model architectures and hyperparameters to sweep in the parameter space. You can either specify a single model architecture or multiple ones. 
 
-* See [Individual runs](#individual-runs) for the list of supported model algorithms for each task type. 
+* See [Individual runs](#individual-runs) for the list of supported model architectures for each task type. 
 * See [Hyperparameters for computer vision tasks](reference-automl-images-hyperparameters.md)  hyperparameters for each computer vision task type. 
 * See [details on supported distributions for discrete and continuous hyperparameters](how-to-tune-hyperparameters.md#define-the-search-space).
 

articles/machine-learning/how-to-configure-auto-train.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-inference-onnx-automl-image-models.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](how-to-auto-train-image-models.md#configure-experiments) 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 architectures in AutoML.
 
 
 # [Object detection with Faster R-CNN or RetinaNet](#tab/object-detect-cnn)

articles/machine-learning/reference-automl-images-cli-classification.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-object-detection.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-hyperparameters.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  |
 | ------------- |-------------|-----|