{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4a54ab90",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6533ad3a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "torch.cuda.is_available()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d44a0818",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[6.7262e-44, 0.0000e+00, 6.8664e-44],\n",
       "        [0.0000e+00, 3.4130e+20, 3.0694e-41],\n",
       "        [3.8088e+20, 3.0694e-41, 1.4013e-45],\n",
       "        [0.0000e+00, 0.0000e+00, 0.0000e+00],\n",
       "        [1.3452e-43, 0.0000e+00, 1.3452e-43]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = torch.empty(5, 3)\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "637d9ebe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[0., 0., 0., 0., 0.],\n",
       "        [0., 0., 0., 0., 0.],\n",
       "        [0., 0., 0., 0., 0.]])"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = torch.zeros((3, 5), dtype=torch.float)\n",
    "x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "dd60207e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[0.1210, 0.4432, 0.5018, 0.2111, 0.1256],\n",
      "        [0.6894, 0.3928, 0.0216, 0.1406, 0.5416],\n",
      "        [0.0044, 0.4856, 0.2907, 0.9889, 0.2060]])\n",
      "tensor([[0.7810, 0.4015, 0.9711, 0.1654, 0.3593],\n",
      "        [0.5972, 0.1060, 0.6192, 0.6601, 0.9575],\n",
      "        [0.3084, 0.4609, 0.6921, 0.3311, 0.6630]])\n",
      "tensor([[0.9020, 0.8447, 1.4729, 0.3764, 0.4850],\n",
      "        [1.2866, 0.4987, 0.6409, 0.8006, 1.4991],\n",
      "        [0.3128, 0.9465, 0.9828, 1.3200, 0.8690]])\n"
     ]
    }
   ],
   "source": [
    "x.shape\n",
    "x = torch.rand_like(x, dtype=torch.float)\n",
    "y = torch.rand_like(x, dtype=torch.float)\n",
    "print(x)\n",
    "print(y)\n",
    "z = x+y\n",
    "print(z)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "0d2ed6cd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[0.2814, 0.6475, 0.3659, 0.4057],\n",
      "        [0.9773, 0.5319, 0.7534, 0.8681],\n",
      "        [0.4856, 0.3504, 0.0362, 0.6139]], requires_grad=True)\n"
     ]
    }
   ],
   "source": [
    "x = torch.rand((3, 4), requires_grad=True)\n",
    "print(x)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}