Skip To Content

Create samples for deep learning training

Available with Image Server

Training samples are used to derive image chips to train deep learning models in Deep Learning Studio. Image chips are small images containing the feature or object of interest used to train the deep learning model. Create training samples by completing the Prepare training data step. When you select the Prepare training data step, you must configure the project for collecting samples.

    After selecting the option to prepare training, the configure project wizard appears and guides you through the process. Once you have created the project, follow the steps below to configure the project for training.
  1. Select the Deep Learning Studio project and open it.
  2. On the step choice page, select Prepare training data to start the process of collecting training samples.
    Tip:

    A prompt to configure the project for preparing training data appears if it has not been configured previously.

  3. In the prompt, click Yes to configure the project as instructed in the Configure the project for training section of the Work with Deep Learning Studio projects topic.
  4. The Prepare training data menu appears with all available substeps to complete the training sample preparation process.
  5. Click the Collect training samples substep.
  6. Use the collection tools to select all of the training samples in the selected work unit.
  7. Click Complete or Complete and next to collect the next work unit.
  8. Once the work unit is marked as complete, it cannot be selected in the Collect training samples substep. Once the work unit is ready for review, mark it as complete to change the status to pending review.

    Caution:

    If the work unit was marked as complete incorrectly, it must be set to Queued in the Review training samples substep in order to be available again.

  9. Click the Review training samples substep to open the Work unit management dashboard.

    The dashboard allows you to see the status of the work units and samples to review the progress of the project. The graphics change colors based on the status and update as the work units are reviewed.

    Note:

    A work unit can only be reviewed when the collector has marked that work unit as complete.

    In the Work unit management dashboard, information about the project appears on the right side of the dashboard.

    Note:

    To get information about a work unit, click the map or the entry in the table for specific information about that work unit.

    The work units can be reviewed individually or collectively.

  10. If you want to review the work units individually, select the work unit to begin the process of reviewing the training samples.
  11. In the map view, information about the training samples in the work unit is listed, including which user created the samples and time of sample collection. In the table view, the work units appear in a list with the same information.
  12. Click the Review this work unit button.

    The work unit opens with all of the collected samples listed.

  13. Click individual training samples in the Training samples list to review them.

    When a sample is selected, the Approve selected and Reject selected options appear on the dialog box.

  14. To zoom in to the highlighted training sample, select the Visit mode option. The map zooms and pans the map to the highlighted training sample.
    Tip:

    More than one sample can be selected and approved without reviewing each individual sample. You can also approve or reject all of the samples in one step by choosing either the Approval all pending or Reject all pending option. By choosing an option, the selected work units, and training samples within each, will be processed.

    Once all of the training samples have been approved or rejected, a message appears indicating they have all been reviewed.

  15. Mark the work unit as Completed.

    The substep returns to the dashboard, where you can review the progress of all the work units.

  16. If you want to review the work units collectively, create a selection of work units and then change their status. Click the Filter button to open the Filter open dialog box.
    1. Enable one or more of the four options to filter the work units and set the filtering criteria.
      Tip:

      You can select any combination of filter options to select the desired work units. You will see the number of selected work units in parentheses next to the filter option.

    2. Once you have selected a filter option, click Apply to filter the work units and create the selection.
    3. Click the Update button to open the Update work unit(s) dialog box.
      Tip:

      The Update button is only enabled after a selection is made.

      You can update all of the selected work units in one step rather than review them individually. This process allows you to alter the status of many work units at once.

    4. Choose which property to alter the work units to from the available options.
    5. Click Apply to change the work unit status, assigned user, or sample status.
  17. Click the Back button to see the previous menu.
  18. Click Manage image chips when the project has enough approved training samples.
  19. Click the Export button to start the process of exporting the image chips based on the training samples.
  20. The options for the process are available to indicate where the image chips will be exported, as well as additional configuration options about the image chips to be created.
  21. Optionally, adjust the configuration options and click Export.
  22. The progress of the image chip creation appears in the substep and an entry appears indicating information about the image chips with visual previews of them.

Once the image chips are created, the next step is to train the deep learning model, which will be completed in the Train model substep.

By following this workflow, you can create the training samples and the image chips for deep learning model training in a complete end-to-end workflow. There are several optional substeps available for use in the project. The additional substeps are provided to allow modification of existing projects as the analysis is conducted. The following are the three required substeps:

  • Collect training samples
  • Review training samples
  • Manage image chips

When the image chips are created, they are available for the deep learning training process in the Train model step. If the trained model does not meet the expectations for the analysis, this substep can be revisited. You can modify or collect additional training samples and create image chips to use in the next model training process.