{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### uniform stochastic depth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "24\n",
      "25\n",
      "[0.0, 0.004347826354205608, 0.008695652708411217, 0.013043479062616825, 0.017391305416822433, 0.021739132702350616, 0.02608695812523365, 0.030434783548116684, 0.03478261083364487, 0.03913043811917305, 0.04347826540470123, 0.04782608896493912, 0.052173912525177, 0.056521736085414886, 0.06086956337094307, 0.06521739065647125, 0.06956521421670914, 0.07391304522752762, 0.0782608687877655, 0.08260869979858398, 0.08695652335882187, 0.09130434691905975, 0.09565217792987823, 0.10000000149011612]\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "\n",
    "drop_path_rate = 0.1\n",
    "depth = 24\n",
    "\n",
    "dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)]\n",
    "\n",
    "print(len(dpr))\n",
    "inter_dpr = [0.0] + dpr\n",
    "print(len(inter_dpr))\n",
    "print(dpr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]\n",
      "24\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "\n",
    "drop_path_rate = 0\n",
    "depth = 24\n",
    "\n",
    "dpr = [x.item() for x in torch.full((depth,), drop_path_rate)]\n",
    "print(dpr)\n",
    "print(len(dpr))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[[ 0,  1,  2],\n",
      "         [ 3,  4,  5],\n",
      "         [ 6,  7,  8],\n",
      "         [ 9, 10, 11],\n",
      "         [12, 13, 14]],\n",
      "\n",
      "        [[15, 16, 17],\n",
      "         [18, 19, 20],\n",
      "         [21, 22, 23],\n",
      "         [24, 25, 26],\n",
      "         [27, 28, 29]]])\n",
      "-------------------------\n",
      "tensor([[[ 2,  1,  0],\n",
      "         [ 5,  4,  3],\n",
      "         [ 8,  7,  6],\n",
      "         [11, 10,  9],\n",
      "         [14, 13, 12]],\n",
      "\n",
      "        [[17, 16, 15],\n",
      "         [20, 19, 18],\n",
      "         [23, 22, 21],\n",
      "         [26, 25, 24],\n",
      "         [29, 28, 27]]])\n",
      "-------------------------\n",
      "tensor([[[12, 13, 14],\n",
      "         [ 9, 10, 11],\n",
      "         [ 6,  7,  8],\n",
      "         [ 3,  4,  5],\n",
      "         [ 0,  1,  2]],\n",
      "\n",
      "        [[27, 28, 29],\n",
      "         [24, 25, 26],\n",
      "         [21, 22, 23],\n",
      "         [18, 19, 20],\n",
      "         [15, 16, 17]]])\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "\n",
    "x = torch.arange(30).view(2, 5, 3)\n",
    "print(x)\n",
    "print(\"-------------------------\")\n",
    "\n",
    "y = x.flip([-1])\n",
    "print(y)\n",
    "print(\"-------------------------\")\n",
    "\n",
    "z = x.flip([1])\n",
    "print(z)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0, 2, 3, 1]\n",
      "This is the i: 0\n",
      "This is the idx: 0\n",
      "This is the i: 1\n",
      "This is the idx: 2\n",
      "This is the i: 2\n",
      "This is the idx: 3\n",
      "This is the i: 3\n",
      "This is the idx: 1\n"
     ]
    }
   ],
   "source": [
    "import random\n",
    "\n",
    "indices = [0, 1, 2, 3]\n",
    "random.shuffle(indices)\n",
    "\n",
    "print(indices)\n",
    "\n",
    "for i, idx in enumerate(indices):\n",
    "    print(\"This is the i:\", i)\n",
    "    print(\"This is the idx:\", idx)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "mamba",
   "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}