DynamicQuantizeMatMul

DynamicQuantizeMatMul

Description

DynamicQuantizeMatMul is an ONNX operator that performs a matrix multiplication while applying dynamic quantization to the weights and/or inputs during execution.

Documentation illustration (illustration unavailable in the archive).

Input parameters

specified_outputs_name : array, this parameter lets you manually assign custom names to the output tensors of a node.

 Graphs in : cluster, ONNX model architecture.

A (heterogeneous) – T1 : object, N-dimensional matrix A.
B (heterogeneous) – T2 : object, N-dimensional matrix B.
b_scale (heterogeneous) – T1 : object, scale of quantized input ‘B’. It could be a scalar or a 1-D tensor, which means a per-tensor or per-column quantization. If it’s a 1-D tensor, its number of elements should be equal to the number of columns of input ‘B’.
b_zero_point (optional, heterogeneous) – T2 : object, zero point tensor for input ‘B’. It’s optional and default value is 0. It could be a scalar or a 1-D tensor, which means a per-tensor or per-column quantization. If it’s a 1-D tensor, its number of elements should be equal to the number of columns of input ‘B’.
bias (optional, heterogeneous) – T1 : object, 1D input tensor, whose dimension is same as B’s last dimension.

Documentation illustration (illustration unavailable in the archive).

 Parameters : cluster,

 training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
 lda coeff : float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value “1”.

 name (optional) : string, name of the node.

Output parameters

Y (heterogeneous) – T1 : object, matrix multiply results from A * B.

Type Constraints

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install Deep Learning library to run it).