{
 "cells": [
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:34.735042Z",
     "start_time": "2024-09-30T06:24:33.640162Z"
    }
   },
   "cell_type": "code",
   "source": "import torch",
   "id": "e385fc3e5349bef2",
   "outputs": [],
   "execution_count": 2
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:34.770875Z",
     "start_time": "2024-09-30T06:24:34.769086Z"
    }
   },
   "cell_type": "code",
   "source": "import numpy as np",
   "id": "5e5756cd9697c301",
   "outputs": [],
   "execution_count": 3
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:34.832973Z",
     "start_time": "2024-09-30T06:24:34.828625Z"
    }
   },
   "cell_type": "code",
   "source": [
    "data = [[1,2], [3,4]]\n",
    "x_data = torch.tensor(data)\n",
    "print(x_data)\n",
    "np_array = np.array(data)\n",
    "print(np_array)\n",
    "x_data = torch.from_numpy(np_array)\n",
    "print(x_data)"
   ],
   "id": "c933f4f596ad8f11",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[1, 2],\n",
      "        [3, 4]])\n",
      "[[1 2]\n",
      " [3 4]]\n",
      "tensor([[1, 2],\n",
      "        [3, 4]])\n"
     ]
    }
   ],
   "execution_count": 4
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:34.884394Z",
     "start_time": "2024-09-30T06:24:34.881417Z"
    }
   },
   "cell_type": "code",
   "source": [
    "x_data = torch.tensor(data, dtype=torch.float)\n",
    "print(x_data)"
   ],
   "id": "f00ded5999db8fd8",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[1., 2.],\n",
      "        [3., 4.]])\n"
     ]
    }
   ],
   "execution_count": 5
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:34.936237Z",
     "start_time": "2024-09-30T06:24:34.933906Z"
    }
   },
   "cell_type": "code",
   "source": [
    "x_data = torch.tensor(data, dtype=torch.bool)\n",
    "print(x_data)"
   ],
   "id": "e95516603c93e1dd",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[True, True],\n",
      "        [True, True]])\n"
     ]
    }
   ],
   "execution_count": 6
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:34.989723Z",
     "start_time": "2024-09-30T06:24:34.985714Z"
    }
   },
   "cell_type": "code",
   "source": [
    "initial_tensor = torch.tensor([[4., 5.], [6., 7.]])\n",
    "print(initial_tensor)\n",
    "\n",
    "# Initialise a new tensor of 1s\n",
    "new_tensor_ones = torch.ones_like(initial_tensor)\n",
    "print(new_tensor_ones)\n",
    "\n",
    "# Initialise a new tensor of 0s\n",
    "new_tensor_zeros = torch.zeros_like(initial_tensor)\n",
    "print(new_tensor_zeros)\n",
    "\n",
    "# Initialise a new tensor with all elements sampled from a uniform distribution between 0 and 1\n",
    "new_tensor_rand = torch.rand_like(initial_tensor)\n",
    "print(new_tensor_rand)\n",
    "\n",
    "# Initialise a new tensor where all elements are sampled from a normal distribution\n",
    "new_tensor_randn = torch.randn_like(initial_tensor)\n",
    "print(new_tensor_randn)"
   ],
   "id": "772ca3015568d8e0",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[4., 5.],\n",
      "        [6., 7.]])\n",
      "tensor([[1., 1.],\n",
      "        [1., 1.]])\n",
      "tensor([[0., 0.],\n",
      "        [0., 0.]])\n",
      "tensor([[0.0317, 0.8632],\n",
      "        [0.0142, 0.9799]])\n",
      "tensor([[-0.0114, -1.1777],\n",
      "        [-0.5821, -0.9272]])\n"
     ]
    }
   ],
   "execution_count": 7
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:35.042240Z",
     "start_time": "2024-09-30T06:24:35.037846Z"
    }
   },
   "cell_type": "code",
   "source": [
    "shape = (2, 3, 4)\n",
    "\n",
    "x_zeros = torch.zeros(shape)\n",
    "print(x_zeros)\n",
    "\n",
    "x_ones = torch.ones(shape)\n",
    "print(x_ones)\n",
    "\n",
    "torch.manual_seed(142)\n",
    "random = torch.rand(shape)\n",
    "print(random)"
   ],
   "id": "f863644d805df89d",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[[0., 0., 0., 0.],\n",
      "         [0., 0., 0., 0.],\n",
      "         [0., 0., 0., 0.]],\n",
      "\n",
      "        [[0., 0., 0., 0.],\n",
      "         [0., 0., 0., 0.],\n",
      "         [0., 0., 0., 0.]]])\n",
      "tensor([[[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]],\n",
      "\n",
      "        [[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]]])\n",
      "tensor([[[0.9278, 0.3969, 0.7987, 0.3094],\n",
      "         [0.9321, 0.6097, 0.1127, 0.6895],\n",
      "         [0.1704, 0.6049, 0.5771, 0.4412]],\n",
      "\n",
      "        [[0.4884, 0.0448, 0.6659, 0.1933],\n",
      "         [0.6323, 0.0458, 0.6127, 0.1192],\n",
      "         [0.0961, 0.9311, 0.6790, 0.5379]]])\n"
     ]
    }
   ],
   "execution_count": 8
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:35.091909Z",
     "start_time": "2024-09-30T06:24:35.089647Z"
    }
   },
   "cell_type": "code",
   "source": [
    "x = torch.arange(start=0, end=10, step=2)\n",
    "print(x)"
   ],
   "id": "6e9ca1f3bbfb2718",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([0, 2, 4, 6, 8])\n"
     ]
    }
   ],
   "execution_count": 9
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "^the above is only 1D, there may be an optional argument though...",
   "id": "a3141e2557699a4a"
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:35.143042Z",
     "start_time": "2024-09-30T06:24:35.140899Z"
    }
   },
   "cell_type": "code",
   "source": [
    "x = torch.rand(3,2)\n",
    "print(x.shape)\n",
    "print(x.dtype)\n",
    "print(x.size(0))"
   ],
   "id": "5b3e919a9cbb8f09",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([3, 2])\n",
      "torch.float32\n",
      "3\n"
     ]
    }
   ],
   "execution_count": 10
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:35.195706Z",
     "start_time": "2024-09-30T06:24:35.192294Z"
    }
   },
   "cell_type": "code",
   "source": [
    "x = torch.Tensor([[11, 12], [13, 14], [15, 16]])\n",
    "print(x)\n",
    "# we can change the shape from (2,3) to (3,2)\n",
    "x_view = x.view(2,3)\n",
    "print(x_view)\n",
    "\n",
    "# You can also use torch.reshape() for this\n",
    "x_reshaped = torch.reshape(x, (2,3))\n",
    "print(x_reshaped)"
   ],
   "id": "804762b8904cfed9",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[11., 12.],\n",
      "        [13., 14.],\n",
      "        [15., 16.]])\n",
      "tensor([[11., 12., 13.],\n",
      "        [14., 15., 16.]])\n",
      "tensor([[11., 12., 13.],\n",
      "        [14., 15., 16.]])\n"
     ]
    }
   ],
   "execution_count": 11
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:35.348807Z",
     "start_time": "2024-09-30T06:24:35.244104Z"
    }
   },
   "cell_type": "code",
   "source": [
    "print(x.device)\n",
    "print(torch.cuda.is_available())\n",
    "\n",
    "#to leverage the gpu we use\n",
    "if torch.cuda.is_available():\n",
    "    x.to('cuda')"
   ],
   "id": "6135c1b0838167f7",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "cpu\n",
      "True\n"
     ]
    }
   ],
   "execution_count": 12
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:35.360355Z",
     "start_time": "2024-09-30T06:24:35.356131Z"
    }
   },
   "cell_type": "code",
   "source": [
    "#element-wise ops\n",
    "x = torch.ones(2, 3, 4)\n",
    "print(x)\n",
    "\n",
    "print(x + 3)\n",
    "print(x - 0.5)\n",
    "print(x*2)\n",
    "print(x/2)\n"
   ],
   "id": "ff0fbbed6cbe3eba",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]],\n",
      "\n",
      "        [[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]]])\n",
      "tensor([[[4., 4., 4., 4.],\n",
      "         [4., 4., 4., 4.],\n",
      "         [4., 4., 4., 4.]],\n",
      "\n",
      "        [[4., 4., 4., 4.],\n",
      "         [4., 4., 4., 4.],\n",
      "         [4., 4., 4., 4.]]])\n",
      "tensor([[[0.5000, 0.5000, 0.5000, 0.5000],\n",
      "         [0.5000, 0.5000, 0.5000, 0.5000],\n",
      "         [0.5000, 0.5000, 0.5000, 0.5000]],\n",
      "\n",
      "        [[0.5000, 0.5000, 0.5000, 0.5000],\n",
      "         [0.5000, 0.5000, 0.5000, 0.5000],\n",
      "         [0.5000, 0.5000, 0.5000, 0.5000]]])\n",
      "tensor([[[2., 2., 2., 2.],\n",
      "         [2., 2., 2., 2.],\n",
      "         [2., 2., 2., 2.]],\n",
      "\n",
      "        [[2., 2., 2., 2.],\n",
      "         [2., 2., 2., 2.],\n",
      "         [2., 2., 2., 2.]]])\n",
      "tensor([[[0.5000, 0.5000, 0.5000, 0.5000],\n",
      "         [0.5000, 0.5000, 0.5000, 0.5000],\n",
      "         [0.5000, 0.5000, 0.5000, 0.5000]],\n",
      "\n",
      "        [[0.5000, 0.5000, 0.5000, 0.5000],\n",
      "         [0.5000, 0.5000, 0.5000, 0.5000],\n",
      "         [0.5000, 0.5000, 0.5000, 0.5000]]])\n"
     ]
    }
   ],
   "execution_count": 13
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:35.412117Z",
     "start_time": "2024-09-30T06:24:35.406579Z"
    }
   },
   "cell_type": "code",
   "source": [
    "x = torch.ones(2, 2, 4)\n",
    "print(x)\n",
    "\n",
    "y = torch.ones(2, 2, 4)\n",
    "print(y)\n",
    "\n",
    "z_cat = torch.cat([x, y], dim=0)\n",
    "print(z_cat)\n",
    "z_cat = torch.cat([x, y], dim=1)\n",
    "print(z_cat)"
   ],
   "id": "223a8b26c3830428",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]],\n",
      "\n",
      "        [[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]]])\n",
      "tensor([[[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]],\n",
      "\n",
      "        [[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]]])\n",
      "tensor([[[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]],\n",
      "\n",
      "        [[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]],\n",
      "\n",
      "        [[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]],\n",
      "\n",
      "        [[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]]])\n",
      "tensor([[[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]],\n",
      "\n",
      "        [[1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.],\n",
      "         [1., 1., 1., 1.]]])\n"
     ]
    }
   ],
   "execution_count": 14
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:25:20.953845Z",
     "start_time": "2024-09-30T06:25:20.936621Z"
    }
   },
   "cell_type": "code",
   "source": [
    "x = torch.tensor([1, 2, 3], dtype=torch.float)\n",
    "y = torch.tensor([4, 5, 6], dtype=torch.float)\n",
    "print(x+y)\n",
    "\n",
    "# you can also use torch.add()\n",
    "print(torch.add(x,y))\n",
    "print(torch.add(x,y).sum())\n",
    "print(x.dot(y))\n",
    "x = torch.tensor([[1, 2, 3], [4, 5, 6]], dtype=torch.float)\n",
    "print(x.shape)\n",
    "y = torch.tensor([[1, 2], [3, 4], [5, 6]], dtype=torch.float)\n",
    "print(y.shape)\n",
    "\n",
    "# Matrix Multiplication\n",
    "print(torch.matmul(x, y))\n",
    "\n",
    "# you can also use torch.mm() \n",
    "print(torch.mm(x, y))\n",
    "\n",
    "# or you can use x@y\n",
    "print(x@y)"
   ],
   "id": "ec744f2ae5a78d3f",
   "outputs": [
    {
     "ename": "RuntimeError",
     "evalue": "The size of tensor a (30) must match the size of tensor b (3) at non-singleton dimension 0",
     "output_type": "error",
     "traceback": [
      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
      "\u001B[0;31mRuntimeError\u001B[0m                              Traceback (most recent call last)",
      "Cell \u001B[0;32mIn[19], line 3\u001B[0m\n\u001B[1;32m      1\u001B[0m x \u001B[38;5;241m=\u001B[39m torch\u001B[38;5;241m.\u001B[39mtensor([\u001B[38;5;241m1\u001B[39m, \u001B[38;5;241m2\u001B[39m, \u001B[38;5;241m3\u001B[39m]\u001B[38;5;241m*\u001B[39m\u001B[38;5;241m10\u001B[39m, dtype\u001B[38;5;241m=\u001B[39mtorch\u001B[38;5;241m.\u001B[39mfloat)\n\u001B[1;32m      2\u001B[0m y \u001B[38;5;241m=\u001B[39m torch\u001B[38;5;241m.\u001B[39mtensor([\u001B[38;5;241m4\u001B[39m, \u001B[38;5;241m5\u001B[39m, \u001B[38;5;241m6\u001B[39m], dtype\u001B[38;5;241m=\u001B[39mtorch\u001B[38;5;241m.\u001B[39mfloat)\n\u001B[0;32m----> 3\u001B[0m \u001B[38;5;28mprint\u001B[39m(x\u001B[38;5;241m+\u001B[39my)\n\u001B[1;32m      5\u001B[0m \u001B[38;5;66;03m# you can also use torch.add()\u001B[39;00m\n\u001B[1;32m      6\u001B[0m \u001B[38;5;28mprint\u001B[39m(torch\u001B[38;5;241m.\u001B[39madd(x,y))\n",
      "\u001B[0;31mRuntimeError\u001B[0m: The size of tensor a (30) must match the size of tensor b (3) at non-singleton dimension 0"
     ]
    }
   ],
   "execution_count": 19
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:25:04.822706Z",
     "start_time": "2024-09-30T06:25:04.820059Z"
    }
   },
   "cell_type": "code",
   "source": [
    "print(x)\n",
    "z = x*10\n",
    "print(z)"
   ],
   "id": "8d0c58929ce3d86b",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[10., 20., 30.],\n",
      "        [40., 50., 60.]])\n"
     ]
    }
   ],
   "execution_count": 18
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-09-30T06:24:39.089263Z",
     "start_time": "2024-09-30T06:24:39.086120Z"
    }
   },
   "cell_type": "code",
   "source": "",
   "id": "39a77d2056fa55d",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[10., 20., 30.],\n",
      "        [40., 50., 60.]])\n"
     ]
    }
   ],
   "execution_count": 17
  }
 ],
 "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": 5
}