Hybrid Transfer Learning on Jetson AGX Xavier (Volta GPU)

art · September 1, 2022, 3:35pm

I am running the Hybrid Transfer Learning example at the following URL:

XanaduAI/quantum-transfer-learning/blob/master/c2q_transfer_learning_cifar.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Example 3: Hybrid transfer learning for image classification (CIFAR)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is an example of a hybrid network for image classification, developed according to the *classical-to-quantum transfer learning* scheme presented in [1].\n",
    "\n",
    "This notebook is inspired by the official PyTorch  [tutorial on transfer learning](https://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html) by Sasank Chilamkurthy [2].\n",
    "\n",
    "The starting point is a convolutional neural network—ResNet18, introduced by Microsoft in 2016 [3]—which is pre-trained on the public ImageNet dataset. We replace the last fully connected layer with a *dressed quantum circuit* [1] that we train on a different dataset. \n",
    "\n",
    "Specifically, we focus on the following sub-classes of the CIFAR 10 dataset:\n",

This file has been truncated. show original

For the default settings (batch_size=8, quantum=True) timing is
as follows:

default.qubit 1.3 s per batch
lightning.qubit and lightning.gpu 2.7 s per batch

Do these seem about right?

qml.about():

Platform info: Linux-5.10.104-tegra-aarch64-with-glibc2.31
Python version: 3.10.4
Numpy version: 1.23.2
Scipy version: 1.9.0
Installed devices:

lightning.gpu (PennyLane-Lightning-GPU-0.26.0.dev0)
default.gaussian (PennyLane-0.25.1)
default.mixed (PennyLane-0.25.1)
default.qubit (PennyLane-0.25.1)
default.qubit.autograd (PennyLane-0.25.1)
default.qubit.jax (PennyLane-0.25.1)
default.qubit.tf (PennyLane-0.25.1)
default.qubit.torch (PennyLane-0.25.1)
default.qutrit (PennyLane-0.25.1)
lightning.qubit (PennyLane-Lightning-0.25.0)
qiskit.aer (PennyLane-qiskit-0.24.0)
qiskit.basicaer (PennyLane-qiskit-0.24.0)
qiskit.ibmq (PennyLane-qiskit-0.24.0)
qiskit.ibmq.circuit_runner (PennyLane-qiskit-0.24.0)
qiskit.ibmq.sampler (PennyLane-qiskit-0.24.0)

PyTorch version is 1.12.1 without CUDA.

CatalinaAlbornoz · September 1, 2022, 10:49pm

Hi @art,

I’m getting slightly lower numbers for default.qubit (about 0.9s).

Topic		Replies	Views
How to combine Quantum transfer learning and QNN PennyLane Help	3	243	November 15, 2023
Extracting features using Hybrid QNN PennyLane Help	5	160	March 19, 2024
QNN with lightning.gpu device PennyLane Help	7	705	September 6, 2022
Quantum Transfer Learning PennyLane Help	8	1371	November 15, 2023
Hybrid neural network speed suggestions PennyLane Help	5	2116	March 6, 2020

Hybrid Transfer Learning on Jetson AGX Xavier (Volta GPU)

Related Topics