Data Augmentation

Easily augment your data with SmartML advanced options


Deep learning often improves with more data available. One way to do this with a limited dataset is to manipulate existing data in various ways. Augmentation techniques can create variations of your training set images which improves the ability of the fit models to generalize what they have learned to new images.

SmartML provides several data augmentation options for advanced users:

  • Rotate

  • Crop

  • Gamma contrast

  • Shear

  • Horizontal flip

  • Vertical flip (off by default -- should generally not be used except for overhead scenes).

These augmentation options can be encoded into a JSON object, such as:

"aug": "Sequential",
"args": [[
{"aug": "HorizontalFlip", "args": [0.5]},
# Omit by default -- {"aug": "VerticalFlip", "args": [0.5]},
{"aug": "CropAndPad", "kwargs": {"percent":{"tuple": [-0.05,0.05]}, "keep_size": False, "sample_independently": False}},
{"aug": "ShearX", "args": [{"tuple": [-5,5]}]}, # This and ShearY both included when "Shear" selected
{"aug": "ShearY", "args": [{"tuple": [-5,5]}]},
{"aug": "Rotate", "args": [{"tuple": [-5,5]}]},

Where can I set augmentation options?

The augmentation options are configured when creating your model version. The Augmentation JSON text area can be found in the SmartML Hyperparameters section, an optional section for advanced configuration.

Enter your Augmentation JSON in this text area and click "Save and Start Training" to begin your training run.