{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import torch\n",
    "import torch.nn as nn\n",
    "import torch.optim as optim\n",
    "import torch.nn.functional as F"
   ]
  },{
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
"import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import numpy as np

class Testen(nn.Module):   \n",
"    def __init__(self):  \n",
"        super(Testen, self).__init__()  \n",
"        self.layer_1 = torch.nn.Linear(20, 20)\n",
"        self.layer_2 = torch.nn.Linear(30, 30)\n",
"        self.layer_3 = torch.nn.Linear(30, 50)\n",
"\n",
"    def forward(self, x):\n",
"        x = x.view(-1, 3072)\n",
"        x = F.relu(self.layer_1(x))\n",
"        x = F.relu(self.layer_2(x))\n",
"        x = F.relu(self.layer_3(x))\n",
"        return x\n"
]
  },{
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "net = Rompear()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "criterion = nn.CrossEntropyLoss() \n",
    "optimizer = optim.Adam(net.parameters(), lr = 0.0001)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')\n",
    "net.to(device)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "##############################\n",
    "# REPLACE WITH YOUR OWN DATA #\n",
    "##############################\n",
    "x = torch.from_numpy(np.random.rand(1042,32,3,32,32)).type(dtype=torch.float).to(device) #(samples, channels, heigth, width)  \n",
    "y = torch.from_numpy(np.random.randint(20,size=(1042, 32))).to(device) #(number_of_classes, samples)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for epoch in range(2):  # loop over the dataset multiple times \n",
    "    running_loss = 0.0 \n",
    "    for i in range(0, x.shape[0]):\n",
    "        # get the inputs \n",
    "        inputs, labels = x[i], y[i]\n",
    "\n",
    "        # zero the parameter gradients \n",
    "        optimizer.zero_grad() \n",
    "\n",
    "        # forward + backward + optimize \n",
    "        outputs = net(inputs) \n",
    "        loss = criterion(outputs, labels) \n",
    "        loss.backward() \n",
    "        optimizer.step() \n",
    "\n",
    "        # print statistics \n",
    "        running_loss += loss.item() \n",
    "        if i % 200 == 199:\n",
    "            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 200)) \n",
    "            running_loss = 0.0 \n",
    "print('Finished Training')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}