7.2multiple_neurons.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<center>\n",
    "    <img src=\"https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DL0110EN-SkillsNetwork/Template/module%201/images/IDSNlogo.png\" width=\"300\" alt=\"cognitiveclass.ai logo\"  />\n",
    "</center>\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": 3,
   "metadata": {},
   "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": 4,
   "metadata": {},
   "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": 5,
   "metadata": {},
   "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": 6,
   "metadata": {},
   "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": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Net(nn.Module):\n",
    "    #In the constructor, you are defining the layers.\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",
    "    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": 9,
   "metadata": {},
   "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",
    "            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": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_set=Data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "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": [
    "<a href=\"https://dataplatform.cloud.ibm.com/registration/stepone?context=cpdaas&apps=data_science_experience,watson_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/\">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/\">Michelle Carey</a>, <a href=\"www.linkedin.com/in/jiahui-mavis-zhou-a4537814a\">Mavis Zhou</a>, <a href=\"https://www.linkedin.com/in/fanjiang0619/\">Fan Jiang</a>, <a href=\"https://www.linkedin.com/in/yi-leng-yao-84451275/\">Yi Leng Yao</a>, <a href=\"https://www.linkedin.com/in/sacchitchadha/\">Sacchit Chadha</a>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 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"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <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": "3.6.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}