{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.0.0\n"
     ]
    }
   ],
   "source": [
    "import torch; print(torch.__version__)\n",
    "import torch.nn as nn"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "outputs": [],
   "source": [
    "# Define the neural network architecture\n",
    "class SimpleNN(nn.Module):\n",
    "    def __init__(self, input_size, output_size):\n",
    "        super(SimpleNN, self).__init__()\n",
    "        self.fc1 = nn.Linear(input_size, 3)\n",
    "        self.relu1 = nn.ReLU()\n",
    "        self.fc2 = nn.Linear(3, 2)\n",
    "        self.relu2 = nn.ReLU()\n",
    "        self.fc3 = nn.Linear(2, output_size)\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = self.fc1(x)\n",
    "        x = self.relu1(x)\n",
    "        x = self.fc2(x)\n",
    "        x = self.relu2(x)\n",
    "        x = self.fc3(x)\n",
    "        return x"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "outputs": [],
   "source": [
    "# Set the parameters\n",
    "input_size = 4  # Number of input features\n",
    "output_size = 3  # Number of output neurons (binary classification)\n",
    "\n",
    "# Create the neural network\n",
    "model = SimpleNN(input_size, output_size)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "outputs": [],
   "source": [
    "input = torch.randn(size=(4,))\n",
    "output = model(input)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "outputs": [
    {
     "data": {
      "text/plain": "tensor([-0.5835,  0.2246, -0.0567], grad_fn=<AddBackward0>)"
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "outputs": [],
   "source": [
    "target = torch.tensor([0.0, 0.0, 1.0])"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "outputs": [
    {
     "data": {
      "text/plain": "tensor([0., 0., 1.])"
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "target"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "- https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html#torch.nn.CrossEntropyLoss"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "outputs": [],
   "source": [
    "cross_entropy_loss = nn.CrossEntropyLoss()"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "outputs": [],
   "source": [
    "loss = cross_entropy_loss(output, target)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "outputs": [
    {
     "data": {
      "text/plain": "tensor(1.0700, grad_fn=<DivBackward1>)"
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loss"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "outputs": [
    {
     "data": {
      "text/plain": "tensor(1.0700, grad_fn=<MulBackward0>)"
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "-1.0 * torch.log(torch.softmax(output, dim=-1))[2]"
   ],
   "metadata": {
    "collapsed": false
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}