{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torchvision"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "torch.cuda.is_available()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[0.2504, 0.6128, 0.9066, 0.9701],\n",
      "        [0.9145, 0.5638, 0.2492, 0.8657],\n",
      "        [0.9521, 0.5454, 0.6647, 0.9666],\n",
      "        [0.9705, 0.8375, 0.9598, 0.4804]])\n"
     ]
    }
   ],
   "source": [
    "r = torch.rand(4,4)\n",
    "print(r)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[-0.6323, -0.4558, -0.9853,  1.5795],\n",
      "        [-1.5415,  0.3864, -0.0094,  0.4048],\n",
      "        [ 1.2190,  0.7174,  0.0796,  0.0580],\n",
      "        [-0.8419,  1.5195,  0.9428,  0.5261]])\n",
      "torch.float32\n"
     ]
    }
   ],
   "source": [
    "r2 = torch.randn(4,4)\n",
    "print(r2)\n",
    "print(r2.dtype)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([7, 9, 9, 8, 8])\n",
      "torch.int64\n"
     ]
    }
   ],
   "source": [
    "in_array = torch.randint(6,10,(5,))\n",
    "print(in_array)\n",
    "print(in_array.dtype)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[6, 6, 7],\n",
      "        [9, 7, 6],\n",
      "        [9, 8, 6]])\n"
     ]
    }
   ],
   "source": [
    "in_array_2 = torch.randint(6,10,(3,3))\n",
    "print(in_array_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5\n",
      "9\n"
     ]
    }
   ],
   "source": [
    "print(torch.numel(in_array))\n",
    "print(torch.numel(in_array_2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[0, 0, 0],\n",
      "        [0, 0, 0],\n",
      "        [0, 0, 0]])\n",
      "torch.int64\n",
      "tensor([[1., 1., 1.],\n",
      "        [1., 1., 1.],\n",
      "        [1., 1., 1.]])\n",
      "torch.float32\n"
     ]
    }
   ],
   "source": [
    "z = torch.zeros(3,3, dtype=torch.long)\n",
    "print(z)\n",
    "print(z.dtype)\n",
    "o = torch.ones(3,3)\n",
    "print(o)\n",
    "print(o.dtype)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[ 0.0830, -0.5093, -0.0874,  0.4360],\n",
      "        [-0.4503,  1.4857, -0.9082,  0.9302],\n",
      "        [-1.1958,  0.2207,  1.0333,  0.1410],\n",
      "        [-0.0071, -2.7461,  0.8460,  0.8057]], dtype=torch.float64)\n"
     ]
    }
   ],
   "source": [
    "r2_like = torch.randn_like(r2, dtype=torch.double)\n",
    "print(r2_like)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[-0.3819,  0.1570, -0.0787,  2.5496],\n",
      "        [-0.6270,  0.9503,  0.2398,  1.2705],\n",
      "        [ 2.1711,  1.2629,  0.7444,  1.0246],\n",
      "        [ 0.1286,  2.3570,  1.9026,  1.0065]])\n"
     ]
    }
   ],
   "source": [
    "add_result = torch.add(r,r2)\n",
    "print(add_result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([4, 4])"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "add_result.size()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[-0.3819,  0.1570, -0.0787,  2.5496],\n",
      "        [-0.6270,  0.9503,  0.2398,  1.2705],\n",
      "        [ 2.1711,  1.2629,  0.7444,  1.0246],\n",
      "        [ 0.1286,  2.3570,  1.9026,  1.0065]])\n"
     ]
    }
   ],
   "source": [
    "# this function reassings the value to r2\n",
    "r2.add_(r)\n",
    "print(r2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([0.1570, 0.9503, 1.2629, 2.3570])\n",
      "tensor([[-0.3819,  0.1570],\n",
      "        [-0.6270,  0.9503],\n",
      "        [ 2.1711,  1.2629],\n",
      "        [ 0.1286,  2.3570]])\n",
      "tensor([[-0.3819,  0.1570, -0.0787,  2.5496],\n",
      "        [-0.6270,  0.9503,  0.2398,  1.2705],\n",
      "        [ 2.1711,  1.2629,  0.7444,  1.0246]])\n",
      "tensor(1.0246)\n",
      "1.0245939493179321\n",
      "tensor([2.1711, 1.2629, 0.7444, 1.0246])\n"
     ]
    }
   ],
   "source": [
    "print(r2[:,1])\n",
    "print(r2[:,:2])\n",
    "print(r2[:3,:])\n",
    "num_ten = r2[2,3]\n",
    "print(num_ten)\n",
    "print(num_ten.item())\n",
    "print(r2[2,:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}