Options to configure a MediaPipe Embedder Task
Signature:
export declare interface EmbedderOptions
Properties
| Property | Modifiers | Type | Description |
|---|---|---|---|
| l2Normalize | boolean | undefined | Whether to normalize the returned feature vector with L2 norm. Use this option only if the model does not already contain a native L2_NORMALIZATION TF Lite Op. In most cases, this is already the case and L2 norm is thus achieved through TF Lite inference. | |
| quantize | boolean | undefined | Whether the returned embedding should be quantized to bytes via scalar quantization. Embeddings are implicitly assumed to be unit-norm and therefore any dimension is guaranteed to have a value in [-1.0, 1.0]. Use the l2_normalize option if this is not the case. |
EmbedderOptions.l2Normalize
Whether to normalize the returned feature vector with L2 norm. Use this option only if the model does not already contain a native L2_NORMALIZATION TF Lite Op. In most cases, this is already the case and L2 norm is thus achieved through TF Lite inference.
Signature:
l2Normalize?: boolean | undefined;
EmbedderOptions.quantize
Whether the returned embedding should be quantized to bytes via scalar quantization. Embeddings are implicitly assumed to be unit-norm and therefore any dimension is guaranteed to have a value in [-1.0, 1.0]. Use the l2_normalize option if this is not the case.
Signature:
quantize?: boolean | undefined;