7.2multiple_neurons.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p style=\"text-align:center\">\n",
    "    <a href=\"https://skills.network/?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0110ENSkillsNetwork952-2022-01-01\" target=\"_blank\">\n",
    "    <img src=\"https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/assets/logos/SN_web_lightmode.png\" width=\"200\" alt=\"Skills Network Logo\"  />\n",
    "    </a>\n",
    "</p>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h1>Neural Networks More Hidden Neutrons</h1>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2>Objective</h2><ul><li> How to create complex Neural Network in pytorch.</li></ul> \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2>Table of Contents</h2>\n",
    "\n",
    "<ul>\n",
    "    <li><a href=\"#Prep\">Preperation</a></li>\n",
    "    <li><a href=\"#Data\">Get Our Data</a></li>\n",
    "    <li><a href=\"#Train\">Define the Neural Network, Optimizer, and Train the Model</a></li>\n",
    "</ul>\n",
    "<p>Estimated Time Needed: <strong>25 min</strong></p>\n",
    "\n",
    "<hr>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2 id=\"Prep\">Preparation</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We'll need to import the following libraries for this lab.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import torch\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt \n",
    "%matplotlib inline\n",
    "import torch.nn as nn\n",
    "import torch.nn.functional as F\n",
    "from torch.utils.data import Dataset, DataLoader"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define the plotting functions.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def get_hist(model,data_set):\n",
    "    activations=model.activation(data_set.x)\n",
    "    for i,activation in enumerate(activations):\n",
    "        plt.hist(activation.numpy(),4,density=True)\n",
    "        plt.title(\"Activation layer \" + str(i+1))\n",
    "        plt.xlabel(\"Activation\")\n",
    "        plt.xlabel(\"Activation\")\n",
    "        plt.legend()\n",
    "        plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def PlotStuff(X,Y,model=None,leg=False):\n",
    "    \n",
    "    plt.plot(X[Y==0].numpy(),Y[Y==0].numpy(),'or',label='training points y=0 ' )\n",
    "    plt.plot(X[Y==1].numpy(),Y[Y==1].numpy(),'ob',label='training points y=1 ' )\n",
    "\n",
    "    if model!=None:\n",
    "        plt.plot(X.numpy(),model(X).detach().numpy(),label='neral network ')\n",
    "\n",
    "    plt.legend()\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2 id=\"Data\">Get Our Data</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define the class to get our dataset.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "class Data(Dataset):\n",
    "    def __init__(self):\n",
    "        self.x=torch.linspace(-20, 20, 100).view(-1,1)\n",
    "  \n",
    "        self.y=torch.zeros(self.x.shape[0])\n",
    "        self.y[(self.x[:,0]>-10)& (self.x[:,0]<-5)]=1\n",
    "        self.y[(self.x[:,0]>5)& (self.x[:,0]<10)]=1\n",
    "        self.y=self.y.view(-1,1)\n",
    "        self.len=self.x.shape[0]\n",
    "    def __getitem__(self,index):    \n",
    "            \n",
    "        return self.x[index],self.y[index]\n",
    "    def __len__(self):\n",
    "        return self.len\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2 id=\"Train\">Define the Neural Network, Optimizer and Train the Model</h2>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define the class for creating our model.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "class Net(nn.Module):\n",
    "    def __init__(self,D_in,H,D_out):\n",
    "        super(Net,self).__init__()\n",
    "        self.linear1=nn.Linear(D_in,H)\n",
    "        self.linear2=nn.Linear(H,D_out)\n",
    "\n",
    "        \n",
    "    def forward(self,x):\n",
    "        x=torch.sigmoid(self.linear1(x))  \n",
    "        x=torch.sigmoid(self.linear2(x))\n",
    "        return x"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create the function to train our model, which accumulate lost for each iteration to obtain the cost.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    " def train(data_set,model,criterion, train_loader, optimizer, epochs=5,plot_number=10):\n",
    "    cost=[]\n",
    "    \n",
    "    for epoch in range(epochs):\n",
    "        total=0\n",
    "        \n",
    "        for x,y in train_loader:\n",
    "            optimizer.zero_grad()\n",
    "            \n",
    "            yhat=model(x)\n",
    "            loss=criterion(yhat,y)\n",
    "            optimizer.zero_grad()\n",
    "            loss.backward()\n",
    "            optimizer.step()\n",
    "            total+=loss.item()\n",
    "            \n",
    "        if epoch%plot_number==0:\n",
    "            PlotStuff(data_set.x,data_set.y,model)\n",
    "        \n",
    "        cost.append(total)\n",
    "    plt.figure()\n",
    "    plt.plot(cost)\n",
    "    plt.xlabel('epoch')\n",
    "    plt.ylabel('cost')\n",
    "    plt.show()\n",
    "    return cost"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "data_set=Data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "PlotStuff(data_set.x,data_set.y,leg=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create our model with 9\n",
    "neurons in the hidden layer. And then create a BCE loss and an Adam optimizer.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "torch.manual_seed(0)\n",
    "model=Net(1,9,1)\n",
    "learning_rate=0.1\n",
    "criterion=nn.BCELoss()\n",
    "optimizer=torch.optim.Adam(model.parameters(), lr=learning_rate)\n",
    "train_loader=DataLoader(dataset=data_set,batch_size=100)\n",
    "COST=train(data_set,model,criterion, train_loader, optimizer, epochs=600,plot_number=200)"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "# this is for exercises\n",
    "model= torch.nn.Sequential(\n",
    "    torch.nn.Linear(1, 6), \n",
    "    torch.nn.Sigmoid(),\n",
    "    torch.nn.Linear(6,1),\n",
    "    torch.nn.Sigmoid()\n",
    "\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.plot(COST)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "\n",
    "<a href=\"https://dataplatform.cloud.ibm.com/registration/stepone?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0110ENSkillsNetwork952-2022-01-01&context=cpdaas&apps=data_science_experience%2Cwatson_machine_learning\"><img src=\"https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DL0110EN-SkillsNetwork/Template/module%201/images/Watson_Studio.png\"></a>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h2>About the Authors:</h2> \n",
    "\n",
    "<a href=\"https://www.linkedin.com/in/joseph-s-50398b136/?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0110ENSkillsNetwork952-2022-01-01\">Joseph Santarcangelo</a> has a PhD in Electrical Engineering, his research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition. Joseph has been working for IBM since he completed his PhD. \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Other contributors: <a href=\"https://www.linkedin.com/in/michelleccarey/?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0110ENSkillsNetwork952-2022-01-01\">Michelle Carey</a>, <a href=\"www.linkedin.com/in/jiahui-mavis-zhou-a4537814a\">Mavis Zhou</a>, <a href=\"https://www.linkedin.com/in/fanjiang0619/?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0110ENSkillsNetwork952-2022-01-01\">Fan Jiang</a>, <a href=\"https://www.linkedin.com/in/yi-leng-yao-84451275/?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0110ENSkillsNetwork952-2022-01-01\">Yi Leng Yao</a>, <a href=\"https://www.linkedin.com/in/sacchitchadha/?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0110ENSkillsNetwork952-2022-01-01\">Sacchit Chadha</a>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "## Change Log\n",
    "\n",
    "|  Date (YYYY-MM-DD) |  Version | Changed By  |  Change Description |\n",
    "|---|---|---|---|\n",
    "| 2020-09-23  | 2.0  | Shubham  |  Migrated Lab to Markdown and added to course repo in GitLab |\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "\n",
    "\n",
    "## <h3 align=\"center\"> © IBM Corporation 2020. All rights reserved. <h3/>\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python",
   "language": "python",
   "name": "conda-env-python-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}