Model Settings
  • 01 Sep 2023
  • 4 Minutes to read
  • Dark
    Light
  • PDF

Model Settings

  • Dark
    Light
  • PDF

Article Summary

Model Reports

After you train a model, LandingLens creates a report for that model. To view a model's report:

  1. Open the project.
  2. Click Models at the top of the page.Open Models
  3. Select the model from the Model drop-down menu.
    Select the Model
  4. Click the Actions icon (...) next to the model name.
    Click the Actions Icon
  5. View the displayed report, which has these tabs:

Settings

The Settings tab shows the model Learning Curve and Configuration

The Learning Curve graph shows how the model performed during training (y axis), and how long it took to train the model (x axis).

Model Training Learning Curve
Note:
When you train a model, a virtual computer in the cloud warms up. Because of this step, the start time on the graph is not 0 seconds. Instead, the graph starts after the amount of time it took to acquire the virtual computer.

The Configuration section provides more details on your model training. For example, you can see how many epoch cycles your model went through.

Model Training Configuration

Data Snapshot

The Data Snapshot tab shows all the images, labels, and predictions included in the dataset for the model. For more information about how to manage datasets, go to Dataset Versioning.

Data Snapshot

Logs

The Logs tab shows data that can be helpful for troubleshooting. If you experienced any issues during model training, you can provide these logs to a Landing AI associate.

Model Logs

Dataset Versioning

Each time you save a model, LandingLens also saves the whole data and the model's predictions. Saved data includes the images, labels, metadata, and labeling tasks. You can think of this as the "snapshot" of your dataset at that point in time.

You can:

Note:
A dataset snapshot only includes data available when a model was saved. If you update a dataset after saving a model, those changes are not saved. Changes include: uploaded images, deleted images, updated labels, updated metadata, and updated labeling tasks. If you want to save changes, train a model again and then save it.

Download a CSV of Dataset Data

For Object Detection and Classification projects, click Download CSV to download a CSV of information about the dataset. The CSV includes several columns of data, including Project Name, Image Name, Split.

To download a CSV of dataset data:

  1. Open the project.
  2. Click Models at the top of the page.Open Models
  3. Select the model that has the dataset you're interested in from the Model drop-down menu.
    Select the Model
  4. Click the Actions icon (...) next to the model name.
    Click the Actions Icon
  5. Click the Dataset Snapshot tab.
    Data Snapshot
  6. Click the Actions icon (...) and select Download CSV.
    Download the CSV
  7. The file is downloaded to your computer. For a description of all data in the file, go to CSV Data.

CSV Data

When you download a CSV of a dataset, the file includes the information described in the following table.

ItemDescriptionExample
Project NameName of the LandingLens project.Defect Detection
Project TypeProject type ("bounding_box" is Object Detection).classification
Image NameThe file name of the image uploaded to LandingLens.sample_003.jpg
Image IDUnique ID assigned to the image.29786892
SplitThe split assigned to the image.train
Upload TimeThe time the image was uploaded to LandingLens. All times are in Coordinated Universal Time (UTC).Mon Jun 26 2023 16:37:10 GMT+0000 (Coordinated Universal Time)
Image WidthThe width (in pixels) of the image when it was uploaded to LandingLens.4771
Image HeightThe height (in pixels) of the image when it was uploaded to LandingLens.2684
Model NameThe name of the model in LandingLens.100% Precision and Recall
MetadataAny metadata assigned to the image. If the image doesn't have any metadata, the value is "{}". {"Author":"Eric Smith","Organization":"QA"}
GT_ClassThe Classes you assigned to the image (ground truth or “GT”) .

For Object Detection, this also includes the number of objects you labeled. 
{"Screw":3}
PRED_ClassThe Classes the model predicted.

For Object Detection, this also includes the number of objects predicted.

If the model didn't predict any objects, the value is {"null":1}.
{"Screw":2}
Model_CorrectIf the model's prediction matched the original label (ground truth or “GT”), the value is true.

If the model's prediction didn't match the original label (ground truth or “GT”), the value is false.

Only applicable to Classification projects.
true
PRED_Class_Confidence / PRED_ConfidenceThe model's Confidence Score for each object predicted.

If the model didn't predict any objects, the value is {}.
[{"Screw":0.94796216},{"Screw":0.9787127}]
Class_TotalAreaThe total area (in pixels) of the model's predicted area.

If the model didn't predict any objects, the value is {}.

Only applicable to Object Detection projects.
{"Screw":76060}
GT-PRED JSONThe JSON output comparing the original labels (ground truth or "GT") to the model's predictions. For more information, go to JSON Output.{"gtDefectName":"No Fire","predDefectName":"No Fire","predConfidence":0.9684047}

Revert to a Saved Dataset

Caution:
If you've made any changes to your dataset since the last time you saved the model, those changes will be lost if you revert to a saved dataset. Changes include uploaded images, new labels, new metadata, and new label tasks. If you want to save any changes, train a model before you revert to a saved dataset.

If you are the Project Owner, you can revert your project to use one of the saved datasets. For example, let's say that you saved a model, and later added more images and labels. After training the model a second time, you see that the first model performed better, so you want to go back to that dataset. You can do this by reverting the dataset.

After you revert to a different dataset, you can change the dataset again, including to a dataset that was trained later. 

Only Project Owners can revert the dataset. The button to revert datasets does not display to other users.

To revert to a saved dataset:

  1. Open the project.
  2. Click Models at the top of the page.Open Models
  3. Select the model that has the dataset you want to revert to from the Model drop-down menu.
    Select the Model
  4. Click the Actions icon (...) next to the model name.
    Click the Actions Icon
  5. Click the Dataset Snapshot tab.
    Data Snapshot
  6. Click the Actions icon (...) and select Revert current project to this data version.
    Revert to the Selected Dataset
  7. Read the information on the pop-up and click Yes, Revert.
    Confirm That You Want to Revert the Dataset
  8. LandingLens closes the pop-up windows and loads the Model you reverted to.

Was this article helpful?