plans-jit-experiment.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING:root:Torch was already hooked... skipping hooking process\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Setting up Sandbox...\n",
      "Done!\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "import json\n",
    "import requests\n",
    "import random\n",
    "\n",
    "import torch as th\n",
    "from torch import nn\n",
    "import syft as sy\n",
    "\n",
    "sy.create_sandbox(globals(), verbose=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import torchvision\n",
    "\n",
    "# An instance of your model.\n",
    "model = torchvision.models.resnet18()\n",
    "\n",
    "# An example input you would normally provide to your model's forward() method.\n",
    "example = torch.rand(1, 3, 224, 224)\n",
    "\n",
    "# Use torch.jit.trace to generate a torch.jit.ScriptModule via tracing.\n",
    "traced_script_module = torch.jit.trace(model, example)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "import io\n",
    "buffer = io.BytesIO()\n",
    "torch.jit.save(traced_script_module, buffer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "buffer_output = buffer.getvalue()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b'PK\\x03\\x04\\x00\\x00\\x08\\x08\\x00\\x00'"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "buffer_output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "other_buffer = io.BytesIO(buffer_output)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = torch.jit.load(other_buffer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 0.0008, -0.0082,  0.0355,  ...,  0.0083, -0.0411,  0.0243],\n",
       "        [ 0.0008, -0.0082,  0.0355,  ...,  0.0083, -0.0411,  0.0243],\n",
       "        [ 0.0008, -0.0082,  0.0355,  ...,  0.0083, -0.0411,  0.0243],\n",
       "        ...,\n",
       "        [ 0.0008, -0.0082,  0.0355,  ...,  0.0083, -0.0411,  0.0243],\n",
       "        [ 0.0008, -0.0082,  0.0355,  ...,  0.0083, -0.0411,  0.0243],\n",
       "        [ 0.0008, -0.0082,  0.0355,  ...,  0.0083, -0.0411,  0.0243]],\n",
       "       grad_fn=<DifferentiableGraphBackward>)"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x(th.ones((64, 3, 7, 7)))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}