Enable Image Transformer for Processing of Image Data
Specify whether to use pretrained deep learning models for processing of image data as part of the feature engineering pipeline. When this is enabled, a column of Uniform Resource Identifiers (URIs) to images is converted to a numeric representation using ImageNet-pretrained deep learning models. This is enabled by default.
Supported ImageNet Pretrained Architectures for Image Transformer
Specify the supported ImageNet pretrained architectures for image transformer. Select from the following:
xception (Selected by default)
If an internet connection is available, non-default models are downloaded automatically. If an internet connection is not available, non-default models must be downloaded from http://s3.amazonaws.com/artifacts.h2o.ai/releases/ai/h2o/pretrained/dai_image_models_1_10.zip and extracted into
Multiple transformers can be activated at the same time to allow the selection of multiple options. In this case, embeddings from the different architectures are concatenated together (in a single embedding).
Dimensionality of Feature Space Created by Image Transformer
Specify the dimensionality of the feature (embedding) space created by Image Transformer. Select from the following:
Note: Multiple transformers can be activated at the same time to allow the selection of multiple options.
Enable Fine-Tuning of the Pretrained Models Used for the Image Transformer
Specify whether to enable fine-tuning of the ImageNet pretrained models used for the Image Transformer. This is disabled by default.
Number of Epochs for Fine-Tuning Used for the Image Transformer
Specify the number of epochs for fine-tuning ImageNet pretrained models used for the Image Transformer. This value defaults to 2.
List of Augmentations for Fine-Tuning Used for the Image Transformer
Specify the list of possible image augmentations to apply while fine-tuning the ImageNet pretrained models used for the Image Transformer. Select from the following:
Note: For more information on individual augmentations, see https://albumentations.ai/docs/.
Batch Size for the Image Transformer
Specify the batch size for the Image Transformer. By default, the batch size is set to -1 (selected automatically).
Note: Larger architectures and batch sizes use more memory.
Image Download Timeout in Seconds
When providing images through URLs, specify the maximum number of seconds to wait for an image to download. This value defaults to 60 sec.
Maximum Allowed Fraction of Missing Values for Image Column
Specify the maximum allowed fraction of missing elements in a string column for it to be considered as a potential image path. This value defaults to 0.1.
Minimum Fraction of Images That Need to Be of Valid Types for Image Column to Be Used
Specify the fraction of unique image URIs that need to have valid endings (as defined by
string_col_as_image_valid_types) for a string column to be considered as image data. This value defaults to 0.8.
Enable GPU(s) for Faster Transformations With the Image Transformer
Specify whether to use any available GPUs to transform images into embeddings with the Image Transformer. Enabling this setting can lead to significantly faster transformation speeds. This is enabled by default.
Note: This setting only applies when scoring inside Driverless AI or with Py Scoring.