TensorRT SCALAR MULTIPLICATION BETWEEN TWO MATRIX

AI & Data Science Deep Learning (Training & Inference) TensorRT
, ,
1

Description

I’m trying to implement a scalar multiplication layer in tensorrt. Can anyone please help me through this

Environment

TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

CODE:
x_se = torch.cat((x4_se,x3_se,x2_se,x1_se), dim=1)
attention_vectors = x_se.view(batch_size, 4, self.split_channel, 1, 1)
attention_vectors = self.softmax(attention_vectors)
feats_weight = feats * attention_vectors

CAN anyone suggest any methods to do scalar multiplication(feats_weight) in TensorRT?

4

Hi,

Hope the following may be helpful to you.
https://docs.nvidia.com/deeplearning/tensorrt/api/python_api/infer/Graph/Layers.html#tensorrt.IMatrixMultiplyLayer

Thank you