hereismari

hereismari

def maxpool2d(a_sh, kernel_size: int = 1, stride: int = 1, padding: int = 0,
              dilation: int = 1, ceil_mode=False)
    """Applies a 2D max pooling over an input signal composed of several input planes.

    This interface is similar to torch.nn.MaxPool2D.

    Args:
        kernel_size: the size of the window to take a max over
        stride: the stride of the window
        padding: implicit zero padding to be added on both sides

hereismari

hereismari

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hosting models on Grid\n",
    "\n",
    "## 2. Host model on a grid node"
   ]

hereismari

EMLaaS: Secure model serving

Project 1 - Notebooks providing EMLaaS for image classification

This consists of: hosting a model (regular CNN??? I've tried resnet50 but not supported, I'll try other popular architectures) and being able to query it using a rest api.

• 1.1. host non-encrypted model
  • WIP demo: train model
  • WIP demo: host model
• This demo was using jit.trace. I think we probably want to stick with plans for now. Working on it.

hereismari

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Host model on a grid node"
   ]
  },
  {

hereismari

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hosting models on Grid\n",
    "\n",
    "Grid offers both: Machine Learning as a Service and Encrypted Machine Learning as a service. This is a series of notebooks showing how you can serve your models on Grid.\n",
    "\n",

hereismari

def test_execute_plan_module_remotely(hook, start_proc):
    """Test plan execution remotely."""
    hook.local_worker.is_client_worker = False

    class Net(nn.Module):
        def __init__(self):
            super(Net, self).__init__()
            self.fc1 = nn.Linear(2, 3)
            self.fc2 = nn.Linear(3, 2)

hereismari

def test_execute_plan_module_remotely(hook, start_proc):
    """Test plan execution remotely."""
    hook.local_worker.is_client_worker = False

    class Net(nn.Module):
        def __init__(self):
            super(Net, self).__init__()
            self.fc1 = nn.Linear(2, 3)
            self.fc2 = nn.Linear(3, 2)