Authorizations
Path Parameters
Project ID
Learn Block ID, use the impulse functions to retrieve the ID
Response
OK
Whether the operation succeeded
Whether the block is trained
The Keras script. This script might be empty if the mode is visual.
DEPRECATED, see "thresholds" instead. Minimum confidence rating required for the neural network. Scores below this confidence are tagged as uncertain.
The model type that is currently selected.
int8
, float32
, akida
, requiresRetrain
The mode (visual or expert) to use for editing this network.
visual
, expert
The visual layers (if in visual mode) for the neural network. This will be an empty array when in expert mode.
Number of training cycles. If in expert mode this will be 0.
Learning rate (between 0 and 1). If in expert mode this will be 0.
The default batch size if a value is not configured.
Python-formatted tuple of input axes
The data augmentation policy to use with image input
none
, all
Whether to profile the i8 model (might take a very long time)
If set, skips creating embeddings and measuring memory (used in tests)
Whether the 'Advanced training settings' UI element should be expanded.
Whether the 'Augmentation training settings' UI element should be expanded.
List of configurable thresholds for this block.
Optional error description (set if 'success' was false)
The type of learning block (anomaly, keras, keras-transfer-image, keras-transfer-kws, keras-object-detection, keras-regression). Each behaves differently.
anomaly
, anomaly-gmm
, keras
, keras-transfer-image
, keras-transfer-kws
, keras-object-detection
, keras-regression
, keras-akida
, keras-akida-transfer-image
, keras-akida-object-detection
, keras-visual-anomaly
The batch size used during training.
Train/test split (between 0 and 1)
Whether to automatically balance class weights, use this for skewed datasets.
Use learned optimizer and ignore learning rate.
This metadata key is used to prevent group data leakage between train and validation datasets.
Training parameters, this list depends on the list of parameters that the model exposes.
Capacity level for visual anomaly detection (GMM). Determines which set of default configurations to use. The higher capacity, the higher number of (Gaussian) components, and the more adapted the model becomes to the original distribution
low
, medium
, high
Last shown variant on the Keras screen. Used to keep the same view after refreshing.
int8
, float32
, akida
Training parameters specific to the type of the learn block. Parameters may be adjusted depending on the model defined in the visual layers. Used for our built-in blocks.