From a943bbd39af82da67f9cf26cecc7998586997406 Mon Sep 17 00:00:00 2001 From: pollfly <75068813+pollfly@users.noreply.github.com> Date: Sun, 25 Aug 2024 13:50:12 +0300 Subject: [PATCH] Small edits (#906) --- docs/clearml_data/clearml_data_sdk.md | 6 +++--- docs/clearml_sdk/task_sdk.md | 12 ++++++------ docs/faq.md | 8 ++++---- docs/fundamentals/projects.md | 2 +- docs/getting_started/ds/ds_first_steps.md | 2 +- docs/guides/advanced/execute_remotely.md | 2 +- .../notebooks/image/hyperparameter_search.md | 2 +- docs/guides/reporting/html_reporting.md | 5 ++--- docs/guides/reporting/hyper_parameters.md | 4 ++-- docs/guides/reporting/plotly_reporting.md | 2 +- docs/guides/reporting/using_artifacts.md | 2 +- docs/guides/services/aws_autoscaler.md | 2 +- docs/guides/services/cleanup_service.md | 2 +- docs/guides/storage/examples_storagehelper.md | 14 +++++++------- docs/hyperdatasets/frame_groups.md | 4 ++-- docs/integrations/fastai.md | 2 +- docs/webapp/webapp_profile.md | 2 +- 17 files changed, 36 insertions(+), 37 deletions(-) diff --git a/docs/clearml_data/clearml_data_sdk.md b/docs/clearml_data/clearml_data_sdk.md index f28f5340..9216cb17 100644 --- a/docs/clearml_data/clearml_data_sdk.md +++ b/docs/clearml_data/clearml_data_sdk.md @@ -259,7 +259,7 @@ dataset.get_logger().report_histogram( ## Uploading Files -To upload the dataset files to network storage, use the [`Dataset.upload`](../references/sdk/dataset.md#upload) method. +To upload the dataset files to network storage, use [`Dataset.upload()`](../references/sdk/dataset.md#upload). Use the `output_url` parameter to specify storage target, such as S3 / GS / Azure. For example: * A shared folder: `/mnt/share/folder` @@ -319,7 +319,7 @@ Dataset.delete( ``` ## Renaming Datasets -Rename a dataset using the [`Dataset.rename`](../references/sdk/dataset.md#datasetrename) class method. All the datasets +Rename a dataset using the [`Dataset.rename()`](../references/sdk/dataset.md#datasetrename) class method. All the datasets with the given `dataset_project` and `dataset_name` will be renamed. ```python @@ -331,7 +331,7 @@ Dataset.rename( ``` ## Moving Datasets to Another Project -Move a dataset to another project using the [`Dataset.move_to_project`](../references/sdk/dataset.md#datasetmove_to_projetc) +Move a dataset to another project using the [`Dataset.move_to_project()`](../references/sdk/dataset.md#datasetmove_to_projetc) class method. All the datasets with the given `dataset_project` and `dataset_name` will be moved to the new dataset project. diff --git a/docs/clearml_sdk/task_sdk.md b/docs/clearml_sdk/task_sdk.md index cc198969..442cdcc3 100644 --- a/docs/clearml_sdk/task_sdk.md +++ b/docs/clearml_sdk/task_sdk.md @@ -196,7 +196,7 @@ Pass one of the following in the `continue_last_task` parameter: iteration after the last reported one. Pass `0`, to disable the automatic last iteration offset. To also specify a task ID, use the `reuse_last_task_id` parameter. -You can also continue a task previously executed in offline mode, using the `Task.import_offline_session` method. +You can also continue a task previously executed in offline mode, using `Task.import_offline_session()`. See [Offline Mode](#offline-mode). ### Empty Task Creation @@ -263,7 +263,7 @@ A task can be identified by its project and name, and by a unique identifier (UU a task can be changed after an experiment has been executed, but its ID can't be changed. Programmatically, task objects can be retrieved by querying the system based on either the task ID or a project and name -combination using the [`Task.get_task`](../references/sdk/task.md#taskget_task) class method. If a project / name +combination using the [`Task.get_task()`](../references/sdk/task.md#taskget_task) class method. If a project / name combination is used, and multiple tasks have the exact same name, the function will return the *last modified task*. For example: @@ -283,7 +283,7 @@ The task's outputs, such as artifacts and models, can also be retrieved. ## Querying / Searching Tasks -Search and filter tasks programmatically. Input search parameters into the [`Task.get_tasks`](../references/sdk/task.md#taskget_tasks) +Search and filter tasks programmatically. Input search parameters into the [`Task.get_tasks()`](../references/sdk/task.md#taskget_tasks) class method, which returns a list of task objects that match the search. Pass `allow_archived=False` to filter out archived tasks. @@ -570,7 +570,7 @@ You can work with tasks in Offline Mode, in which all the data and logs that the session folder, which can later be uploaded to the [ClearML Server](../deploying_clearml/clearml_server.md). You can enable offline mode in one of the following ways: -* Before initializing a task, use the [`Task.set_offline`](../references/sdk/task.md#taskset_offline) class method and set +* Before initializing a task, use the [`Task.set_offline()`](../references/sdk/task.md#taskset_offline) class method and set the `offline_mode` argument to `True`: ```python @@ -607,7 +607,7 @@ Upload the execution data that the Task captured offline to the ClearML Server u ``` Pass the path to the zip folder containing the captured information with the `--import-offline-session` parameter -* [`Task.import_offline_session`](../references/sdk/task.md#taskimport_offline_session) class method +* [`Task.import_offline_session()`](../references/sdk/task.md#taskimport_offline_session) class method ```python from clearml import Task @@ -903,7 +903,7 @@ This method saves configuration objects as blobs (i.e. ClearML is not aware of t ```python # connect a configuration dictionary model_config_dict = { - 'value': 13.37, 'dict': {'sub_value': 'string'}, 'list_of_ints': [1, 2, 3, 4], + 'value': 13.37, 'dict': {'sub_value': 'string'}, 'list_of_ints': [1, 2, 3, 4], } model_config_dict = task.connect_configuration( name='dictionary', configuration=model_config_dict diff --git a/docs/faq.md b/docs/faq.md index 184eaf39..8eb40fbc 100644 --- a/docs/faq.md +++ b/docs/faq.md @@ -455,7 +455,7 @@ You cannot undo the deletion of a ClearML object. #### Can I change the random seed my experiment uses? Yes! By default, ClearML initializes Tasks with an initial seed of `1337` to ensure reproducibility. To set a different -value for your task, use the [`Task.set_random_seed`](references/sdk/task.md#taskset_random_seed) class method and +value for your task, use the [`Task.set_random_seed()`](references/sdk/task.md#taskset_random_seed) class method and provide the new seed value, **before initializing the task**. You can disable the deterministic behavior entirely by passing `Task.set_random_seed(None)`. @@ -557,7 +557,7 @@ Yes! You can use ClearML's Offline Mode, in which all the data and logs that a t local folder. You can enable offline mode in one of the following ways: -* Before initializing a task, use the [`Task.set_offline`](references/sdk/task.md#taskset_offline) class method and set +* Before initializing a task, use the [`Task.set_offline()`](references/sdk/task.md#taskset_offline) class method and set the `offline_mode` argument to `True` * Before running a task, set `CLEARML_OFFLINE_MODE=1` @@ -578,7 +578,7 @@ ClearML Task: Offline session stored in /home/user/.clearml/cache/offline/b78684 In order to upload to the ClearML Server the execution data that the Task captured offline, do one of the following: * Use the `import-offline-session ` option of the [clearml-task](apps/clearml_task.md) CLI -* Use the [`Task.import_offline_session`](references/sdk/task.md#taskimport_offline_session) method. +* Use the [`Task.import_offline_session()`](references/sdk/task.md#taskimport_offline_session) method. See [Storing Task Data Offline](guides/set_offline.md). @@ -627,7 +627,7 @@ tutorial. #### How can I report more than one scatter 2D series on the same plot? -The [`Logger.report_scatter2d`](references/sdk/logger.md#report_scatter2d) +The [`Logger.report_scatter2d()`](references/sdk/logger.md#report_scatter2d) method reports all series with the same `title` and `iteration` parameter values on the same plot. For example, the following two scatter2D series are reported on the same plot, because both have a `title` of `example_scatter` and an `iteration` of `1`: diff --git a/docs/fundamentals/projects.md b/docs/fundamentals/projects.md index e065206e..0b590dc6 100644 --- a/docs/fundamentals/projects.md +++ b/docs/fundamentals/projects.md @@ -46,7 +46,7 @@ Projects can also be created using the [`projects.create`](../references/api/pro ### View All Projects in System -To view all projects in the system, use the `Task.get_projects` class method: +To view all projects in the system, use the [`Task.get_projects()`](../references/sdk/task.md#taskgetprojects) class method: ```python project_list = Task.get_projects() diff --git a/docs/getting_started/ds/ds_first_steps.md b/docs/getting_started/ds/ds_first_steps.md index 04a80b99..fb998a71 100644 --- a/docs/getting_started/ds/ds_first_steps.md +++ b/docs/getting_started/ds/ds_first_steps.md @@ -63,7 +63,7 @@ pip install clearml page, click **Create new credentials**. The **LOCAL PYTHON** tab shows the data required by the setup wizard (a copy to clipboard action is available on - hover) + hover). 1. At the command prompt `Paste copied configuration here:`, copy and paste the ClearML credentials. The setup wizard confirms the credentials. diff --git a/docs/guides/advanced/execute_remotely.md b/docs/guides/advanced/execute_remotely.md index 6d11f102..aaa77375 100644 --- a/docs/guides/advanced/execute_remotely.md +++ b/docs/guides/advanced/execute_remotely.md @@ -3,7 +3,7 @@ title: Remote Execution --- The [execute_remotely_example](https://github.com/allegroai/clearml/blob/master/examples/advanced/execute_remotely_example.py) -script demonstrates the use of the [`Task.execute_remotely`](../../references/sdk/task.md#execute_remotely) method. +script demonstrates the use of the [`Task.execute_remotely()`](../../references/sdk/task.md#execute_remotely) method. :::note Make sure to have at least one [ClearML Agent](../../clearml_agent.md) running and assigned to listen to the `default` queue: diff --git a/docs/guides/frameworks/pytorch/notebooks/image/hyperparameter_search.md b/docs/guides/frameworks/pytorch/notebooks/image/hyperparameter_search.md index 7eda945c..ead05100 100644 --- a/docs/guides/frameworks/pytorch/notebooks/image/hyperparameter_search.md +++ b/docs/guides/frameworks/pytorch/notebooks/image/hyperparameter_search.md @@ -45,7 +45,7 @@ optimizer = HyperParameterOptimizer( # Configuring optimization parameters execution_queue='dan_queue', # queue to schedule the experiments for execution max_number_of_concurrent_tasks=2, # number of concurrent experiments - optimization_time_limit=60., # set the time limit for the optimization process + optimization_time_limit=60, # set the time limit for the optimization process compute_time_limit=120, # set the compute time limit (sum of execution time on all machines) total_max_jobs=20, # set the maximum number of experiments for the optimization. # Converted to total number of iteration for OptimizerBOHB diff --git a/docs/guides/reporting/html_reporting.md b/docs/guides/reporting/html_reporting.md index 386acafb..decbc0d9 100644 --- a/docs/guides/reporting/html_reporting.md +++ b/docs/guides/reporting/html_reporting.md @@ -3,8 +3,7 @@ title: HTML Reporting --- The [html_reporting.py](https://github.com/allegroai/clearml/blob/master/examples/reporting/html_reporting.py) example -demonstrates reporting local HTML files and HTML by URL, using the [Logger.report_media](../../references/sdk/logger.md#report_media) -method. +demonstrates reporting local HTML files and HTML by URL using [`Logger.report_media()`](../../references/sdk/logger.md#report_media). ClearML reports these HTML debug samples in the **ClearML Web UI** **>** experiment details **>** **DEBUG SAMPLES** tab. @@ -31,7 +30,7 @@ Logger.current_logger().report_media( ## Reporting HTML Local Files -Report the following using the `Logger.report_media` parameter method `local_path` parameter: +Report the following using `Logger.report_media()`'s `local_path` parameter: * [Interactive HTML](#interactive-html) * [Bokeh GroupBy HTML](#bokeh-groupby-html) * [Bokeh Graph HTML](#bokeh-graph-html) diff --git a/docs/guides/reporting/hyper_parameters.md b/docs/guides/reporting/hyper_parameters.md index 532dc4f3..ac14d0a6 100644 --- a/docs/guides/reporting/hyper_parameters.md +++ b/docs/guides/reporting/hyper_parameters.md @@ -54,8 +54,8 @@ TensorFlow Definitions appear in **HYPEPARAMETERS** **>** **TF_DEFINE**. ## Parameter Dictionaries -Connect a parameter dictionary to a Task by calling the [`Task.connect`](../../references/sdk/task.md#connect) -method, and ClearML logs the parameters. ClearML also tracks changes to the parameters. +Connect a parameter dictionary to a Task by calling [`Task.connect()`](../../references/sdk/task.md#connect), +and ClearML logs the parameters. ClearML also tracks changes to the parameters. ```python parameters = { diff --git a/docs/guides/reporting/plotly_reporting.md b/docs/guides/reporting/plotly_reporting.md index 6870df6c..5ec57dfa 100644 --- a/docs/guides/reporting/plotly_reporting.md +++ b/docs/guides/reporting/plotly_reporting.md @@ -5,7 +5,7 @@ title: Plotly Reporting The [plotly_reporting.py](https://github.com/allegroai/clearml/blob/master/examples/reporting/plotly_reporting.py) example demonstrates ClearML's Plotly integration and reporting. -Report Plotly plots in ClearML by calling the [`Logger.report_plotly`](../../references/sdk/logger.md#report_plotly) method, and passing a complex +Report Plotly plots in ClearML by calling the [`Logger.report_plotly()`](../../references/sdk/logger.md#report_plotly) method, and passing a complex Plotly figure, using the `figure` parameter. In this example, the Plotly figure is created using `plotly.express.scatter` (see the [Plotly documentation](https://plotly.com/python/line-and-scatter/)): diff --git a/docs/guides/reporting/using_artifacts.md b/docs/guides/reporting/using_artifacts.md index 8a27e046..a0ebee68 100644 --- a/docs/guides/reporting/using_artifacts.md +++ b/docs/guides/reporting/using_artifacts.md @@ -27,7 +27,7 @@ Artifact details (location and size) can be viewed in ClearML's **web UI > exper ## Task 2: Accessing an Artifact -After the second task is initialized, the script uses the [`Task.get_task`](../../references/sdk/task.md#taskget_task) +After the second task is initialized, the script uses the [`Task.get_task()`](../../references/sdk/task.md#taskget_task) class method to get the first task and access its artifacts, specifically the `data file` artifact. The `get_local_copy` method downloads the files and returns a path. diff --git a/docs/guides/services/aws_autoscaler.md b/docs/guides/services/aws_autoscaler.md index 3c8c36eb..85e6035d 100644 --- a/docs/guides/services/aws_autoscaler.md +++ b/docs/guides/services/aws_autoscaler.md @@ -152,7 +152,7 @@ Make sure a `clearml-agent` is assigned to that queue. ### Configuration The values configured through the wizard are stored in the task's hyperparameters and configuration objects by using the -[`Task.connect`](../../references/sdk/task.md#connect) and [`Task.set_configuration_object`](../../references/sdk/task.md#set_configuration_object) +[`Task.connect()`](../../references/sdk/task.md#connect) and [`Task.set_configuration_object()`](../../references/sdk/task.md#set_configuration_object) methods respectively. They can be viewed in the WebApp, in the task's **CONFIGURATION** page under **HYPERPARAMETERS** and **CONFIGURATION OBJECTS > General**. ClearML automatically logs command line arguments defined with argparse. View them in the experiments **CONFIGURATION** diff --git a/docs/guides/services/cleanup_service.md b/docs/guides/services/cleanup_service.md index f49068d9..85a01fbf 100644 --- a/docs/guides/services/cleanup_service.md +++ b/docs/guides/services/cleanup_service.md @@ -52,7 +52,7 @@ an `APIClient` object that establishes a session with the ClearML Server, and ac * [`Task.delete`](../../references/sdk/task.md#delete) - Delete a Task. ## Configuration -The experiment's hyperparameters are explicitly logged to ClearML using the [`Task.connect`](../../references/sdk/task.md#connect) +The experiment's hyperparameters are explicitly logged to ClearML using the [`Task.connect()`](../../references/sdk/task.md#connect) method. View them in the WebApp, in the experiment's **CONFIGURATION** page under **HYPERPARAMETERS > General**. The task can be reused. Clone the task, edit its parameters, and enqueue the task to run in ClearML Agent [services mode](../../clearml_agent/clearml_agent_services_mode.md). diff --git a/docs/guides/storage/examples_storagehelper.md b/docs/guides/storage/examples_storagehelper.md index 472ef4b1..26fe6cdc 100644 --- a/docs/guides/storage/examples_storagehelper.md +++ b/docs/guides/storage/examples_storagehelper.md @@ -16,7 +16,7 @@ class. The storage examples include: ## Working with Files ### Downloading a File -To download a ZIP file from storage to the `global` cache context, use the [`StorageManager.get_local_copy`](../../references/sdk/storage.md#storagemanagerget_local_copy) +To download a ZIP file from storage to the `global` cache context, use the [`StorageManager.get_local_copy()`](../../references/sdk/storage.md#storagemanagerget_local_copy) class method, and specify the destination location as the `remote_url` argument: ```python @@ -42,7 +42,7 @@ StorageManager.get_local_copy(remote_url="s3://MyBucket/MyFolder/file.ext", extr ``` By default, the `StorageManager` reports its download progress to the console every 5MB. You can change this using the -[`StorageManager.set_report_download_chunk_size`](../../references/sdk/storage.md#storagemanagerset_report_download_chunk_size) +[`StorageManager.set_report_download_chunk_size()`](../../references/sdk/storage.md#storagemanagerset_report_download_chunk_size) class method, and specifying the chunk size in MB (not supported for Azure and GCP storage). ```python @@ -51,7 +51,7 @@ StorageManager.set_report_download_chunk_size(chunk_size_mb=10) ### Uploading a File -To upload a file to storage, use the [`StorageManager.upload_file`](../../references/sdk/storage.md#storagemanagerupload_file) +To upload a file to storage, use the [`StorageManager.upload_file()`](../../references/sdk/storage.md#storagemanagerupload_file) class method. Specify the full path of the local file as the `local_file` argument, and the remote URL as the `remote_url` argument. @@ -64,7 +64,7 @@ StorageManager.upload_file( Use the `retries` parameter to set the number of times file upload should be retried in case of failure. By default, the `StorageManager` reports its upload progress to the console every 5MB. You can change this using the -[`StorageManager.set_report_upload_chunk_size`](../../references/sdk/storage.md#storagemanagerset_report_upload_chunk_size) +[`StorageManager.set_report_upload_chunk_size()`](../../references/sdk/storage.md#storagemanagerset_report_upload_chunk_size) class method, and specifying the chunk size in MB (not supported for Azure and GCP storage). ```python @@ -73,7 +73,7 @@ StorageManager.set_report_upload_chunk_size(chunk_size_mb=10) ## Working with Folders ### Downloading a Folder -Download a folder to a local machine using the [`StorageManager.download_folder`](../../references/sdk/storage.md#storagemanagerdownload_folder) +Download a folder to a local machine using the [`StorageManager.download_folder()`](../../references/sdk/storage.md#storagemanagerdownload_folder) class method. Specify the remote storage location as the `remote_url` argument and the target local location as the `local_folder` argument. @@ -90,7 +90,7 @@ For example: if you have a remote file `s3://bucket/sub/file.ext`, then You can input `match_wildcard` so only files matching the wildcard are downloaded. ### Uploading a Folder -Upload a local folder to remote storage using the [`StorageManager.upload_folder`](../../references/sdk/storage.md#storagemanagerupload_folder) +Upload a local folder to remote storage using the [`StorageManager.upload_folder()`](../../references/sdk/storage.md#storagemanagerupload_folder) class method. Specify the local folder to upload as the `local_folder` argument and the target remote location as the `remote_url` argument. @@ -112,7 +112,7 @@ You can input `match_wildcard` so only files matching the wildcard are uploaded. ## Setting Cache Limits -To set a limit on the number of files cached, use the [`StorageManager.set_cache_file_limit`](../../references/sdk/storage.md#storagemanagerset_cache_file_limit) +To set a limit on the number of files cached, use the [`StorageManager.set_cache_file_limit()`](../../references/sdk/storage.md#storagemanagerset_cache_file_limit) class method and specify the `cache_file_limit` argument as the maximum number of files. This does not limit the cache size, only the number of files. diff --git a/docs/hyperdatasets/frame_groups.md b/docs/hyperdatasets/frame_groups.md index 06c58c00..86843837 100644 --- a/docs/hyperdatasets/frame_groups.md +++ b/docs/hyperdatasets/frame_groups.md @@ -50,7 +50,7 @@ To add FrameGroups to a Dataset Version: 1. Append the FrameGroup object to a list of frames -1. Add that list to a DatasetVersion using the [`DatasetVersion.add_frames`](../references/hyperdataset/hyperdatasetversion.md#add_frames) +1. Add that list to a DatasetVersion using the [`DatasetVersion.add_frames()`](../references/hyperdataset/hyperdatasetversion.md#add_frames) method. Use the `upload_retries` parameter to set the number of times the upload of a frame should be retried in case of failure, before marking the frame as failed and continuing to upload the next frames. In the case that a single frame in the FrameGroup fails to upload, the entire group will not be registered. The method returns a list of frames that were @@ -116,7 +116,7 @@ myVersion.update_frames(frames) ### Deleting Frames -To delete a FrameGroup, use the [`DatasetVersion.delete_frames`](../references/hyperdataset/hyperdatasetversion.md#delete_frames) +To delete a FrameGroup, use the [`DatasetVersion.delete_frames()`](../references/hyperdataset/hyperdatasetversion.md#delete_frames) method, just like when deleting a SingleFrame, except that a FrameGroup is being referenced. ```python diff --git a/docs/integrations/fastai.md b/docs/integrations/fastai.md index a9cd4a34..dc9a6d4d 100644 --- a/docs/integrations/fastai.md +++ b/docs/integrations/fastai.md @@ -46,7 +46,7 @@ For example: ```python auto_connect_frameworks={ 'fastai': False, 'catboost': True, 'tensorflow': False, 'tensorboard': False, 'pytorch': True, - 'xgboost': False, 'scikit': True, 'lightgbm': False, + 'xgboost': False, 'scikit': True, 'lightgbm': False, 'hydra': True, 'detect_repository': True, 'tfdefines': True, 'joblib': True, 'megengine': True } diff --git a/docs/webapp/webapp_profile.md b/docs/webapp/webapp_profile.md index e47dba60..c43e493f 100644 --- a/docs/webapp/webapp_profile.md +++ b/docs/webapp/webapp_profile.md @@ -598,7 +598,7 @@ Administrators specify the total number of resources available in each pool. The workload assignment up to the available number of resources. Administrators control the execution priority within a pool across the resource profiles making use of it (e.g. if jobs -of profile A and jobs of profile B currently need to run in a pool, allocate resources for profile A jobs first or vice +of profile A and jobs of profile B currently need to run in a pool, allocate resources for profile A jobs first or vice versa). The resource pool cards are displayed on the top of the Resource Configuration settings page. Each card displays the